djia_support_nikkei_sync_period.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
      "/home/sprkzoff/.local/lib/python3.6/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import sklearn.preprocessing\n",
    "import sklearn\n",
    "import os\n",
    "from datetime import datetime, timedelta\n",
    "from tqdm import tqdm\n",
    "\n",
    "import tensorflow as tf\n",
    "from tensorflow.keras.models import Sequential, Model\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "from tensorflow.keras.layers import LSTM, GRU, Bidirectional, Dense, Dropout, Input, TimeDistributed, LeakyReLU, BatchNormalization\n",
    "from tensorflow.keras import backend as K\n",
    "from tensorflow.keras.callbacks import ModelCheckpoint, ReduceLROnPlateau,TensorBoard"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['DJI_ema.csv',\n",
       " 'DJI_STO_20period_sma10.csv',\n",
       " 'DJI_modified_sma.csv',\n",
       " '.DS_Store',\n",
       " 'DJI_modified_features - DJI.csv',\n",
       " 'nk_fe.csv',\n",
       " 'DJI_fe.csv',\n",
       " 'N225withoutNULL.csv',\n",
       " 'dowjone1985_2019.csv',\n",
       " 'N225fillVOL.csv',\n",
       " 'test_djia.csv',\n",
       " 'DJI_denoise.csv',\n",
       " 'N225.csv',\n",
       " 'stocknews',\n",
       " 'preprocessed',\n",
       " 'downjone5y.csv']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.listdir('./data/')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_nikkei = pd.read_csv('./data/N225withoutNULL.csv')\n",
    "df_djia = pd.read_csv('./data/DJI_modified_sma.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>Date</th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Adj Close</th>\n",
       "      <th>Volume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1985-01-29</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1985-01-30</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1985-01-31</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1985-02-01</td>\n",
       "      <td>11946.959961</td>\n",
       "      <td>11946.959961</td>\n",
       "      <td>11946.959961</td>\n",
       "      <td>11946.959961</td>\n",
       "      <td>11946.959961</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1985-02-04</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Date          Open          High           Low         Close  \\\n",
       "0  1985-01-29  11843.070313  11843.070313  11843.070313  11843.070313   \n",
       "1  1985-01-30  11960.629883  11960.629883  11960.629883  11960.629883   \n",
       "2  1985-01-31  11992.309570  11992.309570  11992.309570  11992.309570   \n",
       "3  1985-02-01  11946.959961  11946.959961  11946.959961  11946.959961   \n",
       "4  1985-02-04  11891.080078  11891.080078  11891.080078  11891.080078   \n",
       "\n",
       "      Adj Close  Volume  \n",
       "0  11843.070313       0  \n",
       "1  11960.629883       0  \n",
       "2  11992.309570       0  \n",
       "3  11946.959961       0  \n",
       "4  11891.080078       0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_nikkei.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'1985-01-29'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_djia['Date'][0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Preprocess"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "  0%|          | 0/8762 [00:00<?, ?it/s]/usr/lib/python3/dist-packages/ipykernel_launcher.py:7: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  import sys\n",
      "100%|██████████| 8762/8762 [00:18<00:00, 473.16it/s]\n"
     ]
    }
   ],
   "source": [
    "# postpone 1 day and concatenate both table\n",
    "\n",
    "# decrement datetime of djia first\n",
    "df_djia_dc = df_djia.copy()\n",
    "# df_djia_dc['Date'] = df_djia['Date'] + timedelta(days=-1)\n",
    "for i in tqdm(range(len(df_djia))):\n",
    "    df_djia_dc['Date'][i] = str((datetime.strptime(df_djia.iloc[i]['Date'], '%Y-%m-%d') + timedelta(days=-1)).date())\n",
    "\n",
    "# df_djia_dc.head()\n",
    "df = pd.merge(df_nikkei, df_djia_dc, on='Date', how='inner')\n",
    "df = df.rename({'Open_x': 'Open(Nikkei)', 'High_x': 'High(Nikkei)', 'Low_x': 'Low(Nikkei)', 'Close_x': 'Close(Nikkei)',\n",
    "                'Open_y': 'Open(DJIA)', 'High_y': 'High(DJIA)', 'Low_y': 'Low(DJIA)', 'Close_y': 'Close(DJIA)'\n",
    "               }, axis=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>Date</th>\n",
       "      <th>Open(Nikkei)</th>\n",
       "      <th>High(Nikkei)</th>\n",
       "      <th>Low(Nikkei)</th>\n",
       "      <th>Close(Nikkei)</th>\n",
       "      <th>Adj Close_x</th>\n",
       "      <th>Volume_x</th>\n",
       "      <th>Open(DJIA)</th>\n",
       "      <th>High(DJIA)</th>\n",
       "      <th>Low(DJIA)</th>\n",
       "      <th>Close(DJIA)</th>\n",
       "      <th>Adj Close_y</th>\n",
       "      <th>Volume_y</th>\n",
       "      <th>sma5</th>\n",
       "      <th>sma10</th>\n",
       "      <th>sma25</th>\n",
       "      <th>sma75</th>\n",
       "      <th>sma125</th>\n",
       "      <th>sma200</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1985-01-29</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>11843.070313</td>\n",
       "      <td>0</td>\n",
       "      <td>1297.369995</td>\n",
       "      <td>1305.099976</td>\n",
       "      <td>1278.930054</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>16820000</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1985-01-30</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>11960.629883</td>\n",
       "      <td>0</td>\n",
       "      <td>1283.239990</td>\n",
       "      <td>1293.400024</td>\n",
       "      <td>1272.640015</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>14070000</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1985-01-31</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>11992.309570</td>\n",
       "      <td>0</td>\n",
       "      <td>1276.939941</td>\n",
       "      <td>1286.109985</td>\n",
       "      <td>1269.770020</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>10980000</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1985-02-04</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>11891.080078</td>\n",
       "      <td>0</td>\n",
       "      <td>1294.060059</td>\n",
       "      <td>1301.130005</td>\n",
       "      <td>1278.599976</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>13800000</td>\n",
       "      <td>1285.535986</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>1285.229980</td>\n",
       "      <td>1285.229980</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1985-02-05</td>\n",
       "      <td>11823.429688</td>\n",
       "      <td>11823.429688</td>\n",
       "      <td>11823.429688</td>\n",
       "      <td>11823.429688</td>\n",
       "      <td>11823.429688</td>\n",
       "      <td>0</td>\n",
       "      <td>1284.890015</td>\n",
       "      <td>1294.500000</td>\n",
       "      <td>1275.069946</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>14610000</td>\n",
       "      <td>1284.077979</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>1280.589966</td>\n",
       "      <td>1280.589966</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Date  Open(Nikkei)  High(Nikkei)   Low(Nikkei)  Close(Nikkei)  \\\n",
       "0  1985-01-29  11843.070313  11843.070313  11843.070313   11843.070313   \n",
       "1  1985-01-30  11960.629883  11960.629883  11960.629883   11960.629883   \n",
       "2  1985-01-31  11992.309570  11992.309570  11992.309570   11992.309570   \n",
       "3  1985-02-04  11891.080078  11891.080078  11891.080078   11891.080078   \n",
       "4  1985-02-05  11823.429688  11823.429688  11823.429688   11823.429688   \n",
       "\n",
       "    Adj Close_x  Volume_x   Open(DJIA)   High(DJIA)    Low(DJIA)  Close(DJIA)  \\\n",
       "0  11843.070313         0  1297.369995  1305.099976  1278.930054  1287.880005   \n",
       "1  11960.629883         0  1283.239990  1293.400024  1272.640015  1286.770020   \n",
       "2  11992.309570         0  1276.939941  1286.109985  1269.770020  1277.719971   \n",
       "3  11891.080078         0  1294.060059  1301.130005  1278.599976  1285.229980   \n",
       "4  11823.429688         0  1284.890015  1294.500000  1275.069946  1280.589966   \n",
       "\n",
       "   Adj Close_y  Volume_y         sma5        sma10        sma25        sma75  \\\n",
       "0  1287.880005  16820000  1287.880005  1287.880005  1287.880005  1287.880005   \n",
       "1  1286.770020  14070000  1286.770020  1286.770020  1286.770020  1286.770020   \n",
       "2  1277.719971  10980000  1277.719971  1277.719971  1277.719971  1277.719971   \n",
       "3  1285.229980  13800000  1285.535986  1285.229980  1285.229980  1285.229980   \n",
       "4  1280.589966  14610000  1284.077979  1280.589966  1280.589966  1280.589966   \n",
       "\n",
       "        sma125       sma200  \n",
       "0  1287.880005  1287.880005  \n",
       "1  1286.770020  1286.770020  \n",
       "2  1277.719971  1277.719971  \n",
       "3  1285.229980  1285.229980  \n",
       "4  1280.589966  1280.589966  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "event_col = ['Open(Nikkei)', 'High(Nikkei)', 'Low(Nikkei)', 'Close(Nikkei)',\n",
    "            'Open(DJIA)', 'High(DJIA)', 'Low(DJIA)', 'Close(DJIA)'\n",
    "            ]\n",
    "total_col = df.columns\n",
    "for col in total_col:\n",
    "    if col not in event_col:\n",
    "        df = df.drop(col, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>Open(Nikkei)</th>\n",
       "      <th>High(Nikkei)</th>\n",
       "      <th>Low(Nikkei)</th>\n",
       "      <th>Close(Nikkei)</th>\n",
       "      <th>Open(DJIA)</th>\n",
       "      <th>High(DJIA)</th>\n",
       "      <th>Low(DJIA)</th>\n",
       "      <th>Close(DJIA)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6906</th>\n",
       "      <td>22619.769531</td>\n",
       "      <td>22648.810547</td>\n",
       "      <td>22457.890625</td>\n",
       "      <td>22625.380859</td>\n",
       "      <td>26893.92969</td>\n",
       "      <td>26931.77930</td>\n",
       "      <td>26714.33984</td>\n",
       "      <td>26805.52930</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6907</th>\n",
       "      <td>22725.439453</td>\n",
       "      <td>22780.990234</td>\n",
       "      <td>22704.330078</td>\n",
       "      <td>22750.599609</td>\n",
       "      <td>26789.60938</td>\n",
       "      <td>27015.36914</td>\n",
       "      <td>26765.67969</td>\n",
       "      <td>26958.06055</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6908</th>\n",
       "      <td>22854.439453</td>\n",
       "      <td>22896.220703</td>\n",
       "      <td>22830.570313</td>\n",
       "      <td>22867.269531</td>\n",
       "      <td>27061.07031</td>\n",
       "      <td>27165.93945</td>\n",
       "      <td>27039.75977</td>\n",
       "      <td>27071.46094</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6909</th>\n",
       "      <td>22950.789063</td>\n",
       "      <td>23008.429688</td>\n",
       "      <td>22935.349609</td>\n",
       "      <td>22974.130859</td>\n",
       "      <td>27110.71094</td>\n",
       "      <td>27204.35938</td>\n",
       "      <td>26999.64063</td>\n",
       "      <td>27186.68945</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6910</th>\n",
       "      <td>22953.169922</td>\n",
       "      <td>22961.230469</td>\n",
       "      <td>22827.929688</td>\n",
       "      <td>22843.119141</td>\n",
       "      <td>27188.36914</td>\n",
       "      <td>27188.36914</td>\n",
       "      <td>26918.28906</td>\n",
       "      <td>27046.23047</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Open(Nikkei)  High(Nikkei)   Low(Nikkei)  Close(Nikkei)   Open(DJIA)  \\\n",
       "6906  22619.769531  22648.810547  22457.890625   22625.380859  26893.92969   \n",
       "6907  22725.439453  22780.990234  22704.330078   22750.599609  26789.60938   \n",
       "6908  22854.439453  22896.220703  22830.570313   22867.269531  27061.07031   \n",
       "6909  22950.789063  23008.429688  22935.349609   22974.130859  27110.71094   \n",
       "6910  22953.169922  22961.230469  22827.929688   22843.119141  27188.36914   \n",
       "\n",
       "       High(DJIA)    Low(DJIA)  Close(DJIA)  \n",
       "6906  26931.77930  26714.33984  26805.52930  \n",
       "6907  27015.36914  26765.67969  26958.06055  \n",
       "6908  27165.93945  27039.75977  27071.46094  \n",
       "6909  27204.35938  26999.64063  27186.68945  \n",
       "6910  27188.36914  26918.28906  27046.23047  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "def normalize_data(df, event_col):\n",
    "    min_max_scaler = sklearn.preprocessing.MinMaxScaler()\n",
    "    for col in event_col:\n",
    "        if col != 'Date':\n",
    "            df[col] = min_max_scaler.fit_transform(df[col].to_numpy().reshape(-1, 1))\n",
    "    return df\n",
    "\n",
    "def load_data(stock, seq_len):\n",
    "    data_raw = stock.as_matrix()\n",
    "    data = list()\n",
    "    for index in range(len(data_raw) - seq_len):\n",
    "        data.append(data_raw[index: index+seq_len])\n",
    "    data = np.array(data)\n",
    "    val_set_size = int(np.round(val_set_size_percentage/100*data.shape[0]))\n",
    "    test_set_size = int(np.round(test_set_size_percentage/100*data.shape[0]))\n",
    "    train_set_size = data.shape[0] - (val_set_size + test_set_size)\n",
    "    \n",
    "    x_train = data[:train_set_size, :-1, :]\n",
    "    y_train = data[:train_set_size, -1, :]\n",
    "    \n",
    "    x_val = data[train_set_size:train_set_size + val_set_size, :-1, :]\n",
    "    y_val = data[train_set_size:train_set_size + val_set_size, -1, :]\n",
    "    \n",
    "    x_test = data[train_set_size+val_set_size:,:-1,:]\n",
    "    y_test = data[train_set_size+val_set_size:,-1,:]\n",
    "    \n",
    "    return [x_train, y_train, x_val, y_val, x_test, y_test]\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "x_train.shape =  (5513, 19, 8)\n",
      "y_train.shape =  (5513, 8)\n",
      "x_val.shape =  (689, 19, 8)\n",
      "y_val.shape =  (689, 8)\n",
      "x_test.shape =  (689, 19, 8)\n",
      "y_test.shape =  (689, 8)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/lib/python3/dist-packages/ipykernel_launcher.py:9: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  if __name__ == '__main__':\n"
     ]
    }
   ],
   "source": [
    "# parameter for preprocessing #\n",
    "\n",
    "val_set_size_percentage = 10\n",
    "test_set_size_percentage = 10\n",
    "seq_len = 20\n",
    "\n",
    "#*****************************#\n",
    "\n",
    "# normalize index\n",
    "df_norm = normalize_data(df, event_col)\n",
    "\n",
    "# split train, val, test data\n",
    "\n",
    "x_train, y_train, x_val, y_val, x_test, y_test = load_data(df_norm, seq_len)\n",
    "\n",
    "print('x_train.shape = ', x_train.shape)\n",
    "print('y_train.shape = ', y_train.shape)\n",
    "print('x_val.shape = ', x_val.shape)\n",
    "print('y_val.shape = ', y_val.shape)\n",
    "print('x_test.shape = ', x_test.shape)\n",
    "print('y_test.shape = ', y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot graph before train\n",
    "\n",
    "# !set color in graph\n",
    "# color_palette = ...\n",
    "plt.figure(figsize=(15, 10))\n",
    "plt.grid()\n",
    "color_palette = plt.get_cmap('Set1')\n",
    "for i, col in enumerate(event_col):\n",
    "    plt.plot(df_norm[col], color=color_palette(i), label=col)\n",
    "plt.title('Stock price')\n",
    "plt.xlabel('Time [days]')\n",
    "plt.ylabel('Normalized price / volume')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2638\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>Open(Nikkei)</th>\n",
       "      <th>High(Nikkei)</th>\n",
       "      <th>Low(Nikkei)</th>\n",
       "      <th>Close(Nikkei)</th>\n",
       "      <th>Open(DJIA)</th>\n",
       "      <th>High(DJIA)</th>\n",
       "      <th>Low(DJIA)</th>\n",
       "      <th>Close(DJIA)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2638</th>\n",
       "      <td>0.258003</td>\n",
       "      <td>0.256758</td>\n",
       "      <td>0.237947</td>\n",
       "      <td>0.243070</td>\n",
       "      <td>0.252139</td>\n",
       "      <td>0.251625</td>\n",
       "      <td>0.248385</td>\n",
       "      <td>0.247049</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2639</th>\n",
       "      <td>0.258003</td>\n",
       "      <td>0.256758</td>\n",
       "      <td>0.237947</td>\n",
       "      <td>0.243070</td>\n",
       "      <td>0.247315</td>\n",
       "      <td>0.248459</td>\n",
       "      <td>0.247263</td>\n",
       "      <td>0.245836</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2640</th>\n",
       "      <td>0.247327</td>\n",
       "      <td>0.270863</td>\n",
       "      <td>0.249590</td>\n",
       "      <td>0.258785</td>\n",
       "      <td>0.246054</td>\n",
       "      <td>0.247600</td>\n",
       "      <td>0.247225</td>\n",
       "      <td>0.246570</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2641</th>\n",
       "      <td>0.243875</td>\n",
       "      <td>0.243346</td>\n",
       "      <td>0.235396</td>\n",
       "      <td>0.242311</td>\n",
       "      <td>0.251280</td>\n",
       "      <td>0.255440</td>\n",
       "      <td>0.252319</td>\n",
       "      <td>0.255637</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2642</th>\n",
       "      <td>0.244138</td>\n",
       "      <td>0.256102</td>\n",
       "      <td>0.246399</td>\n",
       "      <td>0.257487</td>\n",
       "      <td>0.255874</td>\n",
       "      <td>0.256852</td>\n",
       "      <td>0.255978</td>\n",
       "      <td>0.255342</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6906</th>\n",
       "      <td>0.488358</td>\n",
       "      <td>0.488062</td>\n",
       "      <td>0.485756</td>\n",
       "      <td>0.488699</td>\n",
       "      <td>0.983626</td>\n",
       "      <td>0.983267</td>\n",
       "      <td>0.980601</td>\n",
       "      <td>0.979176</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6907</th>\n",
       "      <td>0.491674</td>\n",
       "      <td>0.492212</td>\n",
       "      <td>0.493498</td>\n",
       "      <td>0.492630</td>\n",
       "      <td>0.979626</td>\n",
       "      <td>0.986467</td>\n",
       "      <td>0.982577</td>\n",
       "      <td>0.985018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6908</th>\n",
       "      <td>0.495723</td>\n",
       "      <td>0.495829</td>\n",
       "      <td>0.497464</td>\n",
       "      <td>0.496292</td>\n",
       "      <td>0.990036</td>\n",
       "      <td>0.992232</td>\n",
       "      <td>0.993125</td>\n",
       "      <td>0.989362</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6909</th>\n",
       "      <td>0.498747</td>\n",
       "      <td>0.499351</td>\n",
       "      <td>0.500755</td>\n",
       "      <td>0.499646</td>\n",
       "      <td>0.991939</td>\n",
       "      <td>0.993703</td>\n",
       "      <td>0.991581</td>\n",
       "      <td>0.993776</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6910</th>\n",
       "      <td>0.498822</td>\n",
       "      <td>0.497869</td>\n",
       "      <td>0.497381</td>\n",
       "      <td>0.495534</td>\n",
       "      <td>0.994917</td>\n",
       "      <td>0.993091</td>\n",
       "      <td>0.988450</td>\n",
       "      <td>0.988396</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4273 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Open(Nikkei)  High(Nikkei)  Low(Nikkei)  Close(Nikkei)  Open(DJIA)  \\\n",
       "2638      0.258003      0.256758     0.237947       0.243070    0.252139   \n",
       "2639      0.258003      0.256758     0.237947       0.243070    0.247315   \n",
       "2640      0.247327      0.270863     0.249590       0.258785    0.246054   \n",
       "2641      0.243875      0.243346     0.235396       0.242311    0.251280   \n",
       "2642      0.244138      0.256102     0.246399       0.257487    0.255874   \n",
       "...            ...           ...          ...            ...         ...   \n",
       "6906      0.488358      0.488062     0.485756       0.488699    0.983626   \n",
       "6907      0.491674      0.492212     0.493498       0.492630    0.979626   \n",
       "6908      0.495723      0.495829     0.497464       0.496292    0.990036   \n",
       "6909      0.498747      0.499351     0.500755       0.499646    0.991939   \n",
       "6910      0.498822      0.497869     0.497381       0.495534    0.994917   \n",
       "\n",
       "      High(DJIA)  Low(DJIA)  Close(DJIA)  \n",
       "2638    0.251625   0.248385     0.247049  \n",
       "2639    0.248459   0.247263     0.245836  \n",
       "2640    0.247600   0.247225     0.246570  \n",
       "2641    0.255440   0.252319     0.255637  \n",
       "2642    0.256852   0.255978     0.255342  \n",
       "...          ...        ...          ...  \n",
       "6906    0.983267   0.980601     0.979176  \n",
       "6907    0.986467   0.982577     0.985018  \n",
       "6908    0.992232   0.993125     0.989362  \n",
       "6909    0.993703   0.991581     0.993776  \n",
       "6910    0.993091   0.988450     0.988396  \n",
       "\n",
       "[4273 rows x 8 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "start = 0\n",
    "for i in range(df.shape[0]) :\n",
    "    if df.loc[i]['Close(DJIA)'] >= df.loc[i]['Close(Nikkei)'] :\n",
    "        start = i\n",
    "        break\n",
    "print(start)\n",
    "df_2 = df[start:]\n",
    "df_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7f0dfb1df048>]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot graph after 2 graph sync\n",
    "\n",
    "# !set color in graph\n",
    "# color_palette = ...\n",
    "plt.figure(figsize=(15, 10))\n",
    "plt.grid()\n",
    "color_palette = plt.get_cmap('Set1')\n",
    "plt.plot(df_2['Close(DJIA)'],color='magenta')\n",
    "plt.plot(df_2['Close(Nikkei)'],color='purple')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "x_train.shape =  (3403, 19, 8)\n",
      "y_train.shape =  (3403, 8)\n",
      "x_val.shape =  (425, 19, 8)\n",
      "y_val.shape =  (425, 8)\n",
      "x_test.shape =  (425, 19, 8)\n",
      "y_test.shape =  (425, 8)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/lib/python3/dist-packages/ipykernel_launcher.py:5: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"\n",
      "/usr/lib/python3/dist-packages/ipykernel_launcher.py:5: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"\n",
      "/usr/lib/python3/dist-packages/ipykernel_launcher.py:5: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"\n",
      "/usr/lib/python3/dist-packages/ipykernel_launcher.py:5: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"\n",
      "/usr/lib/python3/dist-packages/ipykernel_launcher.py:5: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"\n",
      "/usr/lib/python3/dist-packages/ipykernel_launcher.py:5: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"\n",
      "/usr/lib/python3/dist-packages/ipykernel_launcher.py:5: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"\n",
      "/usr/lib/python3/dist-packages/ipykernel_launcher.py:5: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"\n",
      "/usr/lib/python3/dist-packages/ipykernel_launcher.py:9: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  if __name__ == '__main__':\n"
     ]
    }
   ],
   "source": [
    "# parameter for preprocessing #\n",
    "\n",
    "val_set_size_percentage = 10\n",
    "test_set_size_percentage = 10\n",
    "seq_len = 20\n",
    "\n",
    "#*****************************#\n",
    "\n",
    "# normalize index\n",
    "df_2_norm = normalize_data(df_2, event_col)\n",
    "\n",
    "# split train, val, test data\n",
    "\n",
    "x2_train, y2_train, x2_val, y2_val, x2_test, y2_test = load_data(df_2_norm, seq_len)\n",
    "\n",
    "print('x_train.shape = ', x2_train.shape)\n",
    "print('y_train.shape = ', y2_train.shape)\n",
    "print('x_val.shape = ', x2_val.shape)\n",
    "print('y_val.shape = ', y2_val.shape)\n",
    "print('x_test.shape = ', x2_test.shape)\n",
    "print('y_test.shape = ', y2_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>Open(Nikkei)</th>\n",
       "      <th>High(Nikkei)</th>\n",
       "      <th>Low(Nikkei)</th>\n",
       "      <th>Close(Nikkei)</th>\n",
       "      <th>Open(DJIA)</th>\n",
       "      <th>High(DJIA)</th>\n",
       "      <th>Low(DJIA)</th>\n",
       "      <th>Close(DJIA)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2638</th>\n",
       "      <td>0.474720</td>\n",
       "      <td>0.471511</td>\n",
       "      <td>0.439808</td>\n",
       "      <td>0.449848</td>\n",
       "      <td>0.061221</td>\n",
       "      <td>0.051805</td>\n",
       "      <td>0.058767</td>\n",
       "      <td>0.052873</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2639</th>\n",
       "      <td>0.474720</td>\n",
       "      <td>0.471511</td>\n",
       "      <td>0.439808</td>\n",
       "      <td>0.449848</td>\n",
       "      <td>0.055165</td>\n",
       "      <td>0.047793</td>\n",
       "      <td>0.057362</td>\n",
       "      <td>0.051347</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2640</th>\n",
       "      <td>0.455077</td>\n",
       "      <td>0.497415</td>\n",
       "      <td>0.461328</td>\n",
       "      <td>0.478932</td>\n",
       "      <td>0.053581</td>\n",
       "      <td>0.046705</td>\n",
       "      <td>0.057315</td>\n",
       "      <td>0.052270</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2641</th>\n",
       "      <td>0.448725</td>\n",
       "      <td>0.446881</td>\n",
       "      <td>0.435092</td>\n",
       "      <td>0.448443</td>\n",
       "      <td>0.060142</td>\n",
       "      <td>0.056639</td>\n",
       "      <td>0.063694</td>\n",
       "      <td>0.063675</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2642</th>\n",
       "      <td>0.449209</td>\n",
       "      <td>0.470308</td>\n",
       "      <td>0.455429</td>\n",
       "      <td>0.476530</td>\n",
       "      <td>0.065909</td>\n",
       "      <td>0.058427</td>\n",
       "      <td>0.068276</td>\n",
       "      <td>0.063304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6906</th>\n",
       "      <td>0.898570</td>\n",
       "      <td>0.896280</td>\n",
       "      <td>0.897844</td>\n",
       "      <td>0.904434</td>\n",
       "      <td>0.979446</td>\n",
       "      <td>0.978799</td>\n",
       "      <td>0.975707</td>\n",
       "      <td>0.973806</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6907</th>\n",
       "      <td>0.904672</td>\n",
       "      <td>0.903900</td>\n",
       "      <td>0.912153</td>\n",
       "      <td>0.911707</td>\n",
       "      <td>0.974425</td>\n",
       "      <td>0.982854</td>\n",
       "      <td>0.978181</td>\n",
       "      <td>0.981155</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6908</th>\n",
       "      <td>0.912122</td>\n",
       "      <td>0.910542</td>\n",
       "      <td>0.919483</td>\n",
       "      <td>0.918484</td>\n",
       "      <td>0.987492</td>\n",
       "      <td>0.990158</td>\n",
       "      <td>0.991391</td>\n",
       "      <td>0.986619</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6909</th>\n",
       "      <td>0.917686</td>\n",
       "      <td>0.917011</td>\n",
       "      <td>0.925567</td>\n",
       "      <td>0.924691</td>\n",
       "      <td>0.989882</td>\n",
       "      <td>0.992022</td>\n",
       "      <td>0.989458</td>\n",
       "      <td>0.992170</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6910</th>\n",
       "      <td>0.917824</td>\n",
       "      <td>0.914290</td>\n",
       "      <td>0.919330</td>\n",
       "      <td>0.917081</td>\n",
       "      <td>0.993620</td>\n",
       "      <td>0.991247</td>\n",
       "      <td>0.985537</td>\n",
       "      <td>0.985403</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4273 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Open(Nikkei)  High(Nikkei)  Low(Nikkei)  Close(Nikkei)  Open(DJIA)  \\\n",
       "2638      0.474720      0.471511     0.439808       0.449848    0.061221   \n",
       "2639      0.474720      0.471511     0.439808       0.449848    0.055165   \n",
       "2640      0.455077      0.497415     0.461328       0.478932    0.053581   \n",
       "2641      0.448725      0.446881     0.435092       0.448443    0.060142   \n",
       "2642      0.449209      0.470308     0.455429       0.476530    0.065909   \n",
       "...            ...           ...          ...            ...         ...   \n",
       "6906      0.898570      0.896280     0.897844       0.904434    0.979446   \n",
       "6907      0.904672      0.903900     0.912153       0.911707    0.974425   \n",
       "6908      0.912122      0.910542     0.919483       0.918484    0.987492   \n",
       "6909      0.917686      0.917011     0.925567       0.924691    0.989882   \n",
       "6910      0.917824      0.914290     0.919330       0.917081    0.993620   \n",
       "\n",
       "      High(DJIA)  Low(DJIA)  Close(DJIA)  \n",
       "2638    0.051805   0.058767     0.052873  \n",
       "2639    0.047793   0.057362     0.051347  \n",
       "2640    0.046705   0.057315     0.052270  \n",
       "2641    0.056639   0.063694     0.063675  \n",
       "2642    0.058427   0.068276     0.063304  \n",
       "...          ...        ...          ...  \n",
       "6906    0.978799   0.975707     0.973806  \n",
       "6907    0.982854   0.978181     0.981155  \n",
       "6908    0.990158   0.991391     0.986619  \n",
       "6909    0.992022   0.989458     0.992170  \n",
       "6910    0.991247   0.985537     0.985403  \n",
       "\n",
       "[4273 rows x 8 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_2_norm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# hyperparameter \n",
    "batch_size = 1000\n",
    "epochs = 500\n",
    "\n",
    "# set up callback_list\n",
    "weight_path_model = \"saved_model/model_djia_support_nikkei_sync_period.h5\"\n",
    "tensorboard_path = 'Graph/djia_support_nikkei_sync_period'\n",
    "callbacks_list_model = [\n",
    "    TensorBoard(log_dir=tensorboard_path),\n",
    "    ModelCheckpoint(\n",
    "            weight_path_model,\n",
    "            save_best_only=True,\n",
    "            save_weights_only=True,\n",
    "            monitor='val_loss',\n",
    "            mode='min',\n",
    "            verbose=2\n",
    "        ),\n",
    "    ReduceLROnPlateau(monitor='val_loss', factor=0.9, patience=3, min_lr=1e-9)\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /home/sprkzoff/.local/lib/python3.6/site-packages/tensorflow/python/ops/init_ops.py:97: calling Orthogonal.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Call initializer instance with the dtype argument instead of passing it to the constructor\n",
      "WARNING:tensorflow:From /home/sprkzoff/.local/lib/python3.6/site-packages/tensorflow/python/ops/init_ops.py:97: calling Zeros.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Call initializer instance with the dtype argument instead of passing it to the constructor\n",
      "Model: \"model\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "input_1 (InputLayer)         [(None, 19, 8)]           0         \n",
      "_________________________________________________________________\n",
      "bidirectional (Bidirectional (None, 19, 512)           542720    \n",
      "_________________________________________________________________\n",
      "time_distributed (TimeDistri (None, 19, 512)           0         \n",
      "_________________________________________________________________\n",
      "time_distributed_1 (TimeDist (None, 19, 512)           2048      \n",
      "_________________________________________________________________\n",
      "gru (GRU)                    (None, 128)               246144    \n",
      "_________________________________________________________________\n",
      "leaky_re_lu_1 (LeakyReLU)    (None, 128)               0         \n",
      "_________________________________________________________________\n",
      "batch_normalization_1 (Batch (None, 128)               512       \n",
      "_________________________________________________________________\n",
      "dropout (Dropout)            (None, 128)               0         \n",
      "_________________________________________________________________\n",
      "dense (Dense)                (None, 8)                 1032      \n",
      "=================================================================\n",
      "Total params: 792,456\n",
      "Trainable params: 791,176\n",
      "Non-trainable params: 1,280\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "K.clear_session()\n",
    "\n",
    "def get_bi_gru():\n",
    "    \n",
    "    input1 = Input(shape=(19,8,))\n",
    "    x = Bidirectional(LSTM(256, return_sequences=True,  kernel_initializer='Orthogonal'))(input1)\n",
    "    x = TimeDistributed(LeakyReLU())(x)\n",
    "    x = TimeDistributed(BatchNormalization())(x)\n",
    "    x = GRU(128,kernel_initializer='Orthogonal')(x)\n",
    "    x =(LeakyReLU())(x)\n",
    "    x = (BatchNormalization())(x)\n",
    "    x = (Dropout(0.25))(x)\n",
    "    out = Dense(8,kernel_initializer='he_normal')(x)\n",
    "\n",
    "    \n",
    "    \n",
    "    model = Model(inputs=input1, outputs=out)\n",
    "    model.compile(optimizer=Adam(lr=1e-5, decay=1e-4),\n",
    "                loss='mse',\n",
    "                metrics=['mse'])   \n",
    "    \n",
    "    return model\n",
    "\n",
    "model = get_bi_gru()\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Experiment and Result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 5513 samples, validate on 689 samples\n",
      "WARNING:tensorflow:From /home/sprkzoff/.local/lib/python3.6/site-packages/tensorflow/python/ops/math_grad.py:1250: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Use tf.where in 2.0, which has the same broadcast rule as np.where\n",
      "Epoch 1/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 2.2621 - mean_squared_error: 2.2621\n",
      "Epoch 00001: val_loss improved from inf to 0.18841, saving model to saved_model/model_djia_support_nikkei_sync_period.h5\n",
      "5513/5513 [==============================] - 22s 4ms/sample - loss: 2.2395 - mean_squared_error: 2.2395 - val_loss: 0.1884 - val_mean_squared_error: 0.1884\n",
      "Epoch 2/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 1.7453 - mean_squared_error: 1.7453\n",
      "Epoch 00002: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 1.7288 - mean_squared_error: 1.7288 - val_loss: 0.1885 - val_mean_squared_error: 0.1885\n",
      "Epoch 3/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 1.3841 - mean_squared_error: 1.3841\n",
      "Epoch 00003: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 1.3671 - mean_squared_error: 1.3671 - val_loss: 0.1888 - val_mean_squared_error: 0.1888\n",
      "Epoch 4/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 1.1147 - mean_squared_error: 1.1147\n",
      "Epoch 00004: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 1.1048 - mean_squared_error: 1.1048 - val_loss: 0.1892 - val_mean_squared_error: 0.1892\n",
      "Epoch 5/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.9166 - mean_squared_error: 0.9166\n",
      "Epoch 00005: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.9125 - mean_squared_error: 0.9125 - val_loss: 0.1897 - val_mean_squared_error: 0.1897\n",
      "Epoch 6/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.8232 - mean_squared_error: 0.8232\n",
      "Epoch 00006: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.8213 - mean_squared_error: 0.8213 - val_loss: 0.1903 - val_mean_squared_error: 0.1903\n",
      "Epoch 7/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.7589 - mean_squared_error: 0.7589\n",
      "Epoch 00007: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.7593 - mean_squared_error: 0.7593 - val_loss: 0.1910 - val_mean_squared_error: 0.1910\n",
      "Epoch 8/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.7215 - mean_squared_error: 0.7215\n",
      "Epoch 00008: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.7203 - mean_squared_error: 0.7203 - val_loss: 0.1917 - val_mean_squared_error: 0.1917\n",
      "Epoch 9/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.7088 - mean_squared_error: 0.7088\n",
      "Epoch 00009: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.7054 - mean_squared_error: 0.7054 - val_loss: 0.1926 - val_mean_squared_error: 0.1926\n",
      "Epoch 10/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6825 - mean_squared_error: 0.6825\n",
      "Epoch 00010: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.6827 - mean_squared_error: 0.6827 - val_loss: 0.1934 - val_mean_squared_error: 0.1934\n",
      "Epoch 11/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6750 - mean_squared_error: 0.6750\n",
      "Epoch 00011: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.6760 - mean_squared_error: 0.6760 - val_loss: 0.1944 - val_mean_squared_error: 0.1944\n",
      "Epoch 12/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6725 - mean_squared_error: 0.6725\n",
      "Epoch 00012: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.6740 - mean_squared_error: 0.6740 - val_loss: 0.1956 - val_mean_squared_error: 0.1956\n",
      "Epoch 13/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6621 - mean_squared_error: 0.6621\n",
      "Epoch 00013: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6605 - mean_squared_error: 0.6605 - val_loss: 0.1969 - val_mean_squared_error: 0.1969\n",
      "Epoch 14/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6544 - mean_squared_error: 0.6544\n",
      "Epoch 00014: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6538 - mean_squared_error: 0.6538 - val_loss: 0.1985 - val_mean_squared_error: 0.1985\n",
      "Epoch 15/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6508 - mean_squared_error: 0.6508\n",
      "Epoch 00015: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6524 - mean_squared_error: 0.6524 - val_loss: 0.2003 - val_mean_squared_error: 0.2003\n",
      "Epoch 16/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6353 - mean_squared_error: 0.6353\n",
      "Epoch 00016: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.6338 - mean_squared_error: 0.6338 - val_loss: 0.2023 - val_mean_squared_error: 0.2023\n",
      "Epoch 17/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6407 - mean_squared_error: 0.6407\n",
      "Epoch 00017: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.6408 - mean_squared_error: 0.6408 - val_loss: 0.2046 - val_mean_squared_error: 0.2046\n",
      "Epoch 18/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6374 - mean_squared_error: 0.6374\n",
      "Epoch 00018: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.6392 - mean_squared_error: 0.6392 - val_loss: 0.2071 - val_mean_squared_error: 0.2071\n",
      "Epoch 19/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6475 - mean_squared_error: 0.6475\n",
      "Epoch 00019: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6467 - mean_squared_error: 0.6467 - val_loss: 0.2099 - val_mean_squared_error: 0.2099\n",
      "Epoch 20/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6347 - mean_squared_error: 0.6347\n",
      "Epoch 00020: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.6336 - mean_squared_error: 0.6336 - val_loss: 0.2129 - val_mean_squared_error: 0.2129\n",
      "Epoch 21/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6174 - mean_squared_error: 0.6174\n",
      "Epoch 00021: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.6183 - mean_squared_error: 0.6183 - val_loss: 0.2161 - val_mean_squared_error: 0.2161\n",
      "Epoch 22/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6309 - mean_squared_error: 0.6309\n",
      "Epoch 00022: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.6271 - mean_squared_error: 0.6271 - val_loss: 0.2195 - val_mean_squared_error: 0.2195\n",
      "Epoch 23/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6280 - mean_squared_error: 0.6280\n",
      "Epoch 00023: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6268 - mean_squared_error: 0.6268 - val_loss: 0.2233 - val_mean_squared_error: 0.2233\n",
      "Epoch 24/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6249 - mean_squared_error: 0.6249\n",
      "Epoch 00024: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.6218 - mean_squared_error: 0.6218 - val_loss: 0.2274 - val_mean_squared_error: 0.2274\n",
      "Epoch 25/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6243 - mean_squared_error: 0.6243\n",
      "Epoch 00025: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6239 - mean_squared_error: 0.6239 - val_loss: 0.2318 - val_mean_squared_error: 0.2318\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 26/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6242 - mean_squared_error: 0.6242\n",
      "Epoch 00026: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6257 - mean_squared_error: 0.6257 - val_loss: 0.2365 - val_mean_squared_error: 0.2365\n",
      "Epoch 27/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6392 - mean_squared_error: 0.6392\n",
      "Epoch 00027: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6414 - mean_squared_error: 0.6414 - val_loss: 0.2413 - val_mean_squared_error: 0.2413\n",
      "Epoch 28/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6205 - mean_squared_error: 0.6205\n",
      "Epoch 00028: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.6178 - mean_squared_error: 0.6178 - val_loss: 0.2462 - val_mean_squared_error: 0.2462\n",
      "Epoch 29/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6079 - mean_squared_error: 0.6079\n",
      "Epoch 00029: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6098 - mean_squared_error: 0.6098 - val_loss: 0.2516 - val_mean_squared_error: 0.2516\n",
      "Epoch 30/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6210 - mean_squared_error: 0.6210\n",
      "Epoch 00030: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6170 - mean_squared_error: 0.6170 - val_loss: 0.2572 - val_mean_squared_error: 0.2572\n",
      "Epoch 31/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6113 - mean_squared_error: 0.6113\n",
      "Epoch 00031: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6091 - mean_squared_error: 0.6091 - val_loss: 0.2631 - val_mean_squared_error: 0.2631\n",
      "Epoch 32/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5971 - mean_squared_error: 0.5971\n",
      "Epoch 00032: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5984 - mean_squared_error: 0.5984 - val_loss: 0.2692 - val_mean_squared_error: 0.2692\n",
      "Epoch 33/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6108 - mean_squared_error: 0.6108\n",
      "Epoch 00033: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6126 - mean_squared_error: 0.6126 - val_loss: 0.2755 - val_mean_squared_error: 0.2755\n",
      "Epoch 34/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6059 - mean_squared_error: 0.6059\n",
      "Epoch 00034: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6047 - mean_squared_error: 0.6047 - val_loss: 0.2820 - val_mean_squared_error: 0.2820\n",
      "Epoch 35/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6034 - mean_squared_error: 0.6034\n",
      "Epoch 00035: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6026 - mean_squared_error: 0.6026 - val_loss: 0.2888 - val_mean_squared_error: 0.2888\n",
      "Epoch 36/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5995 - mean_squared_error: 0.5995\n",
      "Epoch 00036: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6004 - mean_squared_error: 0.6004 - val_loss: 0.2957 - val_mean_squared_error: 0.2957\n",
      "Epoch 37/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6087 - mean_squared_error: 0.6087\n",
      "Epoch 00037: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.6061 - mean_squared_error: 0.6061 - val_loss: 0.3027 - val_mean_squared_error: 0.3027\n",
      "Epoch 38/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5986 - mean_squared_error: 0.5986\n",
      "Epoch 00038: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5985 - mean_squared_error: 0.5985 - val_loss: 0.3101 - val_mean_squared_error: 0.3101\n",
      "Epoch 39/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5934 - mean_squared_error: 0.5934\n",
      "Epoch 00039: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5950 - mean_squared_error: 0.5950 - val_loss: 0.3178 - val_mean_squared_error: 0.3178\n",
      "Epoch 40/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5997 - mean_squared_error: 0.5997\n",
      "Epoch 00040: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5995 - mean_squared_error: 0.5995 - val_loss: 0.3254 - val_mean_squared_error: 0.3254\n",
      "Epoch 41/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5936 - mean_squared_error: 0.5936\n",
      "Epoch 00041: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5958 - mean_squared_error: 0.5958 - val_loss: 0.3333 - val_mean_squared_error: 0.3333\n",
      "Epoch 42/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5859 - mean_squared_error: 0.5859\n",
      "Epoch 00042: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5860 - mean_squared_error: 0.5860 - val_loss: 0.3414 - val_mean_squared_error: 0.3414\n",
      "Epoch 43/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5807 - mean_squared_error: 0.5807\n",
      "Epoch 00043: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5818 - mean_squared_error: 0.5818 - val_loss: 0.3493 - val_mean_squared_error: 0.3493\n",
      "Epoch 44/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.6006 - mean_squared_error: 0.6006\n",
      "Epoch 00044: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5986 - mean_squared_error: 0.5986 - val_loss: 0.3574 - val_mean_squared_error: 0.3574\n",
      "Epoch 45/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5848 - mean_squared_error: 0.5848\n",
      "Epoch 00045: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5873 - mean_squared_error: 0.5873 - val_loss: 0.3655 - val_mean_squared_error: 0.3655\n",
      "Epoch 46/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5840 - mean_squared_error: 0.5840\n",
      "Epoch 00046: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5853 - mean_squared_error: 0.5853 - val_loss: 0.3737 - val_mean_squared_error: 0.3737\n",
      "Epoch 47/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5888 - mean_squared_error: 0.5888\n",
      "Epoch 00047: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5867 - mean_squared_error: 0.5867 - val_loss: 0.3819 - val_mean_squared_error: 0.3819\n",
      "Epoch 48/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5830 - mean_squared_error: 0.5830\n",
      "Epoch 00048: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5821 - mean_squared_error: 0.5821 - val_loss: 0.3902 - val_mean_squared_error: 0.3902\n",
      "Epoch 49/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5847 - mean_squared_error: 0.5847\n",
      "Epoch 00049: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5850 - mean_squared_error: 0.5850 - val_loss: 0.3986 - val_mean_squared_error: 0.3986\n",
      "Epoch 50/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5828 - mean_squared_error: 0.5828\n",
      "Epoch 00050: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 17s 3ms/sample - loss: 0.5814 - mean_squared_error: 0.5814 - val_loss: 0.4071 - val_mean_squared_error: 0.4071\n",
      "Epoch 51/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5772 - mean_squared_error: 0.5772\n",
      "Epoch 00051: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5802 - mean_squared_error: 0.5802 - val_loss: 0.4154 - val_mean_squared_error: 0.4154\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 52/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5810 - mean_squared_error: 0.5810\n",
      "Epoch 00052: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5811 - mean_squared_error: 0.5811 - val_loss: 0.4236 - val_mean_squared_error: 0.4236\n",
      "Epoch 53/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5718 - mean_squared_error: 0.5718\n",
      "Epoch 00053: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5715 - mean_squared_error: 0.5715 - val_loss: 0.4315 - val_mean_squared_error: 0.4315\n",
      "Epoch 54/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5697 - mean_squared_error: 0.5697\n",
      "Epoch 00054: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5710 - mean_squared_error: 0.5710 - val_loss: 0.4393 - val_mean_squared_error: 0.4393\n",
      "Epoch 55/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5686 - mean_squared_error: 0.5686\n",
      "Epoch 00055: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5668 - mean_squared_error: 0.5668 - val_loss: 0.4468 - val_mean_squared_error: 0.4468\n",
      "Epoch 56/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5690 - mean_squared_error: 0.5690\n",
      "Epoch 00056: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5702 - mean_squared_error: 0.5702 - val_loss: 0.4544 - val_mean_squared_error: 0.4544\n",
      "Epoch 57/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5614 - mean_squared_error: 0.5614\n",
      "Epoch 00057: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5627 - mean_squared_error: 0.5627 - val_loss: 0.4617 - val_mean_squared_error: 0.4617\n",
      "Epoch 58/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5646 - mean_squared_error: 0.5646\n",
      "Epoch 00058: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5659 - mean_squared_error: 0.5659 - val_loss: 0.4690 - val_mean_squared_error: 0.4690\n",
      "Epoch 59/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5727 - mean_squared_error: 0.5727\n",
      "Epoch 00059: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5732 - mean_squared_error: 0.5732 - val_loss: 0.4763 - val_mean_squared_error: 0.4763\n",
      "Epoch 60/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5708 - mean_squared_error: 0.5708\n",
      "Epoch 00060: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5703 - mean_squared_error: 0.5703 - val_loss: 0.4831 - val_mean_squared_error: 0.4831\n",
      "Epoch 61/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5730 - mean_squared_error: 0.5730\n",
      "Epoch 00061: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5737 - mean_squared_error: 0.5737 - val_loss: 0.4897 - val_mean_squared_error: 0.4897\n",
      "Epoch 62/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5629 - mean_squared_error: 0.5629\n",
      "Epoch 00062: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5663 - mean_squared_error: 0.5663 - val_loss: 0.4959 - val_mean_squared_error: 0.4959\n",
      "Epoch 63/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5705 - mean_squared_error: 0.5705\n",
      "Epoch 00063: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5687 - mean_squared_error: 0.5687 - val_loss: 0.5018 - val_mean_squared_error: 0.5018\n",
      "Epoch 64/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5692 - mean_squared_error: 0.5692\n",
      "Epoch 00064: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5682 - mean_squared_error: 0.5682 - val_loss: 0.5076 - val_mean_squared_error: 0.5076\n",
      "Epoch 65/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5669 - mean_squared_error: 0.5669\n",
      "Epoch 00065: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5677 - mean_squared_error: 0.5677 - val_loss: 0.5129 - val_mean_squared_error: 0.5129\n",
      "Epoch 66/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5683 - mean_squared_error: 0.5683\n",
      "Epoch 00066: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5662 - mean_squared_error: 0.5662 - val_loss: 0.5179 - val_mean_squared_error: 0.5179\n",
      "Epoch 67/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5640 - mean_squared_error: 0.5640\n",
      "Epoch 00067: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5653 - mean_squared_error: 0.5653 - val_loss: 0.5225 - val_mean_squared_error: 0.5225\n",
      "Epoch 68/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5629 - mean_squared_error: 0.5629\n",
      "Epoch 00068: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5626 - mean_squared_error: 0.5626 - val_loss: 0.5267 - val_mean_squared_error: 0.5267\n",
      "Epoch 69/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5612 - mean_squared_error: 0.5612\n",
      "Epoch 00069: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5611 - mean_squared_error: 0.5611 - val_loss: 0.5306 - val_mean_squared_error: 0.5306\n",
      "Epoch 70/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5496 - mean_squared_error: 0.5496\n",
      "Epoch 00070: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5501 - mean_squared_error: 0.5501 - val_loss: 0.5340 - val_mean_squared_error: 0.5340\n",
      "Epoch 71/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5708 - mean_squared_error: 0.5708\n",
      "Epoch 00071: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5704 - mean_squared_error: 0.5704 - val_loss: 0.5376 - val_mean_squared_error: 0.5376\n",
      "Epoch 72/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5505 - mean_squared_error: 0.5505\n",
      "Epoch 00072: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5512 - mean_squared_error: 0.5512 - val_loss: 0.5407 - val_mean_squared_error: 0.5407\n",
      "Epoch 73/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5621 - mean_squared_error: 0.5621\n",
      "Epoch 00073: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5595 - mean_squared_error: 0.5595 - val_loss: 0.5436 - val_mean_squared_error: 0.5436\n",
      "Epoch 74/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5644 - mean_squared_error: 0.5644\n",
      "Epoch 00074: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5641 - mean_squared_error: 0.5641 - val_loss: 0.5460 - val_mean_squared_error: 0.5460\n",
      "Epoch 75/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5617 - mean_squared_error: 0.5617\n",
      "Epoch 00075: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5599 - mean_squared_error: 0.5599 - val_loss: 0.5480 - val_mean_squared_error: 0.5480\n",
      "Epoch 76/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5614 - mean_squared_error: 0.5614\n",
      "Epoch 00076: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5624 - mean_squared_error: 0.5624 - val_loss: 0.5492 - val_mean_squared_error: 0.5492\n",
      "Epoch 77/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5590 - mean_squared_error: 0.5590\n",
      "Epoch 00077: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5594 - mean_squared_error: 0.5594 - val_loss: 0.5501 - val_mean_squared_error: 0.5501\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 78/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5598 - mean_squared_error: 0.5598\n",
      "Epoch 00078: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5603 - mean_squared_error: 0.5603 - val_loss: 0.5506 - val_mean_squared_error: 0.5506\n",
      "Epoch 79/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5556 - mean_squared_error: 0.5556\n",
      "Epoch 00079: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5550 - mean_squared_error: 0.5550 - val_loss: 0.5510 - val_mean_squared_error: 0.5510\n",
      "Epoch 80/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5558 - mean_squared_error: 0.5558\n",
      "Epoch 00080: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5582 - mean_squared_error: 0.5582 - val_loss: 0.5510 - val_mean_squared_error: 0.5510\n",
      "Epoch 81/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5561 - mean_squared_error: 0.5561\n",
      "Epoch 00081: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5570 - mean_squared_error: 0.5570 - val_loss: 0.5507 - val_mean_squared_error: 0.5507\n",
      "Epoch 82/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5501 - mean_squared_error: 0.5501\n",
      "Epoch 00082: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5517 - mean_squared_error: 0.5517 - val_loss: 0.5500 - val_mean_squared_error: 0.5500\n",
      "Epoch 83/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5570 - mean_squared_error: 0.5570\n",
      "Epoch 00083: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5562 - mean_squared_error: 0.5562 - val_loss: 0.5489 - val_mean_squared_error: 0.5489\n",
      "Epoch 84/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5625 - mean_squared_error: 0.5625\n",
      "Epoch 00084: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5593 - mean_squared_error: 0.5593 - val_loss: 0.5473 - val_mean_squared_error: 0.5473\n",
      "Epoch 85/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5595 - mean_squared_error: 0.5595\n",
      "Epoch 00085: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5610 - mean_squared_error: 0.5610 - val_loss: 0.5450 - val_mean_squared_error: 0.5450\n",
      "Epoch 86/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5440 - mean_squared_error: 0.5440\n",
      "Epoch 00086: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5453 - mean_squared_error: 0.5453 - val_loss: 0.5424 - val_mean_squared_error: 0.5424\n",
      "Epoch 87/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5656 - mean_squared_error: 0.5656\n",
      "Epoch 00087: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5640 - mean_squared_error: 0.5640 - val_loss: 0.5397 - val_mean_squared_error: 0.5397\n",
      "Epoch 88/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5627 - mean_squared_error: 0.5627\n",
      "Epoch 00088: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5629 - mean_squared_error: 0.5629 - val_loss: 0.5370 - val_mean_squared_error: 0.5370\n",
      "Epoch 89/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5624 - mean_squared_error: 0.5624\n",
      "Epoch 00089: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5604 - mean_squared_error: 0.5604 - val_loss: 0.5336 - val_mean_squared_error: 0.5336\n",
      "Epoch 90/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5601 - mean_squared_error: 0.5601\n",
      "Epoch 00090: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5607 - mean_squared_error: 0.5607 - val_loss: 0.5297 - val_mean_squared_error: 0.5297\n",
      "Epoch 91/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5570 - mean_squared_error: 0.5570\n",
      "Epoch 00091: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5600 - mean_squared_error: 0.5600 - val_loss: 0.5253 - val_mean_squared_error: 0.5253\n",
      "Epoch 92/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5519 - mean_squared_error: 0.5519\n",
      "Epoch 00092: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5531 - mean_squared_error: 0.5531 - val_loss: 0.5209 - val_mean_squared_error: 0.5209\n",
      "Epoch 93/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5560 - mean_squared_error: 0.5560\n",
      "Epoch 00093: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5536 - mean_squared_error: 0.5536 - val_loss: 0.5163 - val_mean_squared_error: 0.5163\n",
      "Epoch 94/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5497 - mean_squared_error: 0.5497\n",
      "Epoch 00094: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5499 - mean_squared_error: 0.5499 - val_loss: 0.5116 - val_mean_squared_error: 0.5116\n",
      "Epoch 95/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5442 - mean_squared_error: 0.5442\n",
      "Epoch 00095: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5444 - mean_squared_error: 0.5444 - val_loss: 0.5064 - val_mean_squared_error: 0.5064\n",
      "Epoch 96/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5565 - mean_squared_error: 0.5565\n",
      "Epoch 00096: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5570 - mean_squared_error: 0.5570 - val_loss: 0.5006 - val_mean_squared_error: 0.5006\n",
      "Epoch 97/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5523 - mean_squared_error: 0.5523\n",
      "Epoch 00097: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5524 - mean_squared_error: 0.5524 - val_loss: 0.4949 - val_mean_squared_error: 0.4949\n",
      "Epoch 98/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5552 - mean_squared_error: 0.5552\n",
      "Epoch 00098: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5567 - mean_squared_error: 0.5567 - val_loss: 0.4891 - val_mean_squared_error: 0.4891\n",
      "Epoch 99/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5517 - mean_squared_error: 0.5517\n",
      "Epoch 00099: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5495 - mean_squared_error: 0.5495 - val_loss: 0.4828 - val_mean_squared_error: 0.4828\n",
      "Epoch 100/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5692 - mean_squared_error: 0.5692\n",
      "Epoch 00100: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5664 - mean_squared_error: 0.5664 - val_loss: 0.4764 - val_mean_squared_error: 0.4764\n",
      "Epoch 101/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5490 - mean_squared_error: 0.5490\n",
      "Epoch 00101: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5482 - mean_squared_error: 0.5482 - val_loss: 0.4702 - val_mean_squared_error: 0.4702\n",
      "Epoch 102/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5469 - mean_squared_error: 0.5469\n",
      "Epoch 00102: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5469 - mean_squared_error: 0.5469 - val_loss: 0.4638 - val_mean_squared_error: 0.4638\n",
      "Epoch 103/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5492 - mean_squared_error: 0.5492\n",
      "Epoch 00103: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5511 - mean_squared_error: 0.5511 - val_loss: 0.4580 - val_mean_squared_error: 0.4580\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 104/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5602 - mean_squared_error: 0.5602\n",
      "Epoch 00104: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5627 - mean_squared_error: 0.5627 - val_loss: 0.4523 - val_mean_squared_error: 0.4523\n",
      "Epoch 105/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5608 - mean_squared_error: 0.5608\n",
      "Epoch 00105: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5599 - mean_squared_error: 0.5599 - val_loss: 0.4471 - val_mean_squared_error: 0.4471\n",
      "Epoch 106/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5461 - mean_squared_error: 0.5461\n",
      "Epoch 00106: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5466 - mean_squared_error: 0.5466 - val_loss: 0.4421 - val_mean_squared_error: 0.4421\n",
      "Epoch 107/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5527 - mean_squared_error: 0.5527\n",
      "Epoch 00107: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5527 - mean_squared_error: 0.5527 - val_loss: 0.4374 - val_mean_squared_error: 0.4374\n",
      "Epoch 108/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5550 - mean_squared_error: 0.5550\n",
      "Epoch 00108: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5547 - mean_squared_error: 0.5547 - val_loss: 0.4332 - val_mean_squared_error: 0.4332\n",
      "Epoch 109/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5542 - mean_squared_error: 0.5542\n",
      "Epoch 00109: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5543 - mean_squared_error: 0.5543 - val_loss: 0.4295 - val_mean_squared_error: 0.4295\n",
      "Epoch 110/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5583 - mean_squared_error: 0.5583\n",
      "Epoch 00110: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5597 - mean_squared_error: 0.5597 - val_loss: 0.4259 - val_mean_squared_error: 0.4259\n",
      "Epoch 111/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5452 - mean_squared_error: 0.5452\n",
      "Epoch 00111: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5450 - mean_squared_error: 0.5450 - val_loss: 0.4226 - val_mean_squared_error: 0.4226\n",
      "Epoch 112/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5452 - mean_squared_error: 0.5452\n",
      "Epoch 00112: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5460 - mean_squared_error: 0.5460 - val_loss: 0.4193 - val_mean_squared_error: 0.4193\n",
      "Epoch 113/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5441 - mean_squared_error: 0.5441\n",
      "Epoch 00113: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5481 - mean_squared_error: 0.5481 - val_loss: 0.4167 - val_mean_squared_error: 0.4167\n",
      "Epoch 114/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5498 - mean_squared_error: 0.5498\n",
      "Epoch 00114: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5511 - mean_squared_error: 0.5511 - val_loss: 0.4149 - val_mean_squared_error: 0.4149\n",
      "Epoch 115/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5507 - mean_squared_error: 0.5507\n",
      "Epoch 00115: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5512 - mean_squared_error: 0.5512 - val_loss: 0.4133 - val_mean_squared_error: 0.4133\n",
      "Epoch 116/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5549 - mean_squared_error: 0.5549\n",
      "Epoch 00116: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5520 - mean_squared_error: 0.5520 - val_loss: 0.4125 - val_mean_squared_error: 0.4125\n",
      "Epoch 117/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5522 - mean_squared_error: 0.5522\n",
      "Epoch 00117: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5538 - mean_squared_error: 0.5538 - val_loss: 0.4124 - val_mean_squared_error: 0.4124\n",
      "Epoch 118/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5440 - mean_squared_error: 0.5440\n",
      "Epoch 00118: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5447 - mean_squared_error: 0.5447 - val_loss: 0.4132 - val_mean_squared_error: 0.4132\n",
      "Epoch 119/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5573 - mean_squared_error: 0.5573\n",
      "Epoch 00119: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5584 - mean_squared_error: 0.5584 - val_loss: 0.4148 - val_mean_squared_error: 0.4148\n",
      "Epoch 120/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5449 - mean_squared_error: 0.5449\n",
      "Epoch 00120: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5480 - mean_squared_error: 0.5480 - val_loss: 0.4169 - val_mean_squared_error: 0.4169\n",
      "Epoch 121/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5478 - mean_squared_error: 0.5478\n",
      "Epoch 00121: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5464 - mean_squared_error: 0.5464 - val_loss: 0.4198 - val_mean_squared_error: 0.4198\n",
      "Epoch 122/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5499 - mean_squared_error: 0.5499\n",
      "Epoch 00122: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5505 - mean_squared_error: 0.5505 - val_loss: 0.4227 - val_mean_squared_error: 0.4227\n",
      "Epoch 123/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5538 - mean_squared_error: 0.5538\n",
      "Epoch 00123: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5544 - mean_squared_error: 0.5544 - val_loss: 0.4268 - val_mean_squared_error: 0.4268\n",
      "Epoch 124/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5484 - mean_squared_error: 0.5484\n",
      "Epoch 00124: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5466 - mean_squared_error: 0.5466 - val_loss: 0.4313 - val_mean_squared_error: 0.4313\n",
      "Epoch 125/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5507 - mean_squared_error: 0.5507\n",
      "Epoch 00125: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5488 - mean_squared_error: 0.5488 - val_loss: 0.4363 - val_mean_squared_error: 0.4363\n",
      "Epoch 126/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5455 - mean_squared_error: 0.5455\n",
      "Epoch 00126: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5483 - mean_squared_error: 0.5483 - val_loss: 0.4417 - val_mean_squared_error: 0.4417\n",
      "Epoch 127/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5535 - mean_squared_error: 0.5535\n",
      "Epoch 00127: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5551 - mean_squared_error: 0.5551 - val_loss: 0.4483 - val_mean_squared_error: 0.4483\n",
      "Epoch 128/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5567 - mean_squared_error: 0.5567\n",
      "Epoch 00128: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5568 - mean_squared_error: 0.5568 - val_loss: 0.4552 - val_mean_squared_error: 0.4552\n",
      "Epoch 129/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5544 - mean_squared_error: 0.5544\n",
      "Epoch 00129: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5533 - mean_squared_error: 0.5533 - val_loss: 0.4631 - val_mean_squared_error: 0.4631\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 130/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5394 - mean_squared_error: 0.5394\n",
      "Epoch 00130: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5394 - mean_squared_error: 0.5394 - val_loss: 0.4707 - val_mean_squared_error: 0.4707\n",
      "Epoch 131/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5493 - mean_squared_error: 0.5493\n",
      "Epoch 00131: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5479 - mean_squared_error: 0.5479 - val_loss: 0.4780 - val_mean_squared_error: 0.4780\n",
      "Epoch 132/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5512 - mean_squared_error: 0.5512\n",
      "Epoch 00132: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5495 - mean_squared_error: 0.5495 - val_loss: 0.4864 - val_mean_squared_error: 0.4864\n",
      "Epoch 133/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5581 - mean_squared_error: 0.5581\n",
      "Epoch 00133: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5570 - mean_squared_error: 0.5570 - val_loss: 0.4945 - val_mean_squared_error: 0.4945\n",
      "Epoch 134/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5463 - mean_squared_error: 0.5463\n",
      "Epoch 00134: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5458 - mean_squared_error: 0.5458 - val_loss: 0.5033 - val_mean_squared_error: 0.5033\n",
      "Epoch 135/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5490 - mean_squared_error: 0.5490\n",
      "Epoch 00135: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5490 - mean_squared_error: 0.5490 - val_loss: 0.5118 - val_mean_squared_error: 0.5118\n",
      "Epoch 136/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5441 - mean_squared_error: 0.5441\n",
      "Epoch 00136: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5458 - mean_squared_error: 0.5458 - val_loss: 0.5196 - val_mean_squared_error: 0.5196\n",
      "Epoch 137/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5384 - mean_squared_error: 0.5384\n",
      "Epoch 00137: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5397 - mean_squared_error: 0.5397 - val_loss: 0.5282 - val_mean_squared_error: 0.5282\n",
      "Epoch 138/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5525 - mean_squared_error: 0.5525\n",
      "Epoch 00138: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5514 - mean_squared_error: 0.5514 - val_loss: 0.5366 - val_mean_squared_error: 0.5366\n",
      "Epoch 139/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5403 - mean_squared_error: 0.5403\n",
      "Epoch 00139: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5408 - mean_squared_error: 0.5408 - val_loss: 0.5453 - val_mean_squared_error: 0.5453\n",
      "Epoch 140/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5474 - mean_squared_error: 0.5474\n",
      "Epoch 00140: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5466 - mean_squared_error: 0.5466 - val_loss: 0.5542 - val_mean_squared_error: 0.5542\n",
      "Epoch 141/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5434 - mean_squared_error: 0.5434\n",
      "Epoch 00141: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5441 - mean_squared_error: 0.5441 - val_loss: 0.5635 - val_mean_squared_error: 0.5635\n",
      "Epoch 142/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5576 - mean_squared_error: 0.5576\n",
      "Epoch 00142: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5568 - mean_squared_error: 0.5568 - val_loss: 0.5717 - val_mean_squared_error: 0.5717\n",
      "Epoch 143/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5474 - mean_squared_error: 0.5474\n",
      "Epoch 00143: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5468 - mean_squared_error: 0.5468 - val_loss: 0.5803 - val_mean_squared_error: 0.5803\n",
      "Epoch 144/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5398 - mean_squared_error: 0.5398\n",
      "Epoch 00144: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5400 - mean_squared_error: 0.5400 - val_loss: 0.5882 - val_mean_squared_error: 0.5882\n",
      "Epoch 145/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5424 - mean_squared_error: 0.5424\n",
      "Epoch 00145: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5430 - mean_squared_error: 0.5430 - val_loss: 0.5961 - val_mean_squared_error: 0.5961\n",
      "Epoch 146/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5460 - mean_squared_error: 0.5460\n",
      "Epoch 00146: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5479 - mean_squared_error: 0.5479 - val_loss: 0.6034 - val_mean_squared_error: 0.6034\n",
      "Epoch 147/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5585 - mean_squared_error: 0.5585\n",
      "Epoch 00147: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5589 - mean_squared_error: 0.5589 - val_loss: 0.6110 - val_mean_squared_error: 0.6110\n",
      "Epoch 148/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5408 - mean_squared_error: 0.5408\n",
      "Epoch 00148: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5443 - mean_squared_error: 0.5443 - val_loss: 0.6182 - val_mean_squared_error: 0.6182\n",
      "Epoch 149/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5498 - mean_squared_error: 0.5498\n",
      "Epoch 00149: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5488 - mean_squared_error: 0.5488 - val_loss: 0.6257 - val_mean_squared_error: 0.6257\n",
      "Epoch 150/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5507 - mean_squared_error: 0.5507\n",
      "Epoch 00150: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5494 - mean_squared_error: 0.5494 - val_loss: 0.6329 - val_mean_squared_error: 0.6329\n",
      "Epoch 151/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5469 - mean_squared_error: 0.5469\n",
      "Epoch 00151: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5464 - mean_squared_error: 0.5464 - val_loss: 0.6397 - val_mean_squared_error: 0.6397\n",
      "Epoch 152/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5472 - mean_squared_error: 0.5472\n",
      "Epoch 00152: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5487 - mean_squared_error: 0.5487 - val_loss: 0.6469 - val_mean_squared_error: 0.6469\n",
      "Epoch 153/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5584 - mean_squared_error: 0.5584\n",
      "Epoch 00153: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5541 - mean_squared_error: 0.5541 - val_loss: 0.6541 - val_mean_squared_error: 0.6541\n",
      "Epoch 154/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5493 - mean_squared_error: 0.5493\n",
      "Epoch 00154: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5497 - mean_squared_error: 0.5497 - val_loss: 0.6603 - val_mean_squared_error: 0.6603\n",
      "Epoch 155/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5561 - mean_squared_error: 0.5561\n",
      "Epoch 00155: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5540 - mean_squared_error: 0.5540 - val_loss: 0.6667 - val_mean_squared_error: 0.6667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 156/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5423 - mean_squared_error: 0.5423\n",
      "Epoch 00156: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5406 - mean_squared_error: 0.5406 - val_loss: 0.6724 - val_mean_squared_error: 0.6724\n",
      "Epoch 157/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5529 - mean_squared_error: 0.5529\n",
      "Epoch 00157: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5505 - mean_squared_error: 0.5505 - val_loss: 0.6780 - val_mean_squared_error: 0.6780\n",
      "Epoch 158/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5494 - mean_squared_error: 0.5494\n",
      "Epoch 00158: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5495 - mean_squared_error: 0.5495 - val_loss: 0.6836 - val_mean_squared_error: 0.6836\n",
      "Epoch 159/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5476 - mean_squared_error: 0.5476\n",
      "Epoch 00159: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5462 - mean_squared_error: 0.5462 - val_loss: 0.6888 - val_mean_squared_error: 0.6888\n",
      "Epoch 160/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5495 - mean_squared_error: 0.5495\n",
      "Epoch 00160: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5514 - mean_squared_error: 0.5514 - val_loss: 0.6937 - val_mean_squared_error: 0.6937\n",
      "Epoch 161/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5462 - mean_squared_error: 0.5462\n",
      "Epoch 00161: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5466 - mean_squared_error: 0.5466 - val_loss: 0.6984 - val_mean_squared_error: 0.6984\n",
      "Epoch 162/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5580 - mean_squared_error: 0.5580\n",
      "Epoch 00162: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5587 - mean_squared_error: 0.5587 - val_loss: 0.7034 - val_mean_squared_error: 0.7034\n",
      "Epoch 163/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5531 - mean_squared_error: 0.5531\n",
      "Epoch 00163: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5523 - mean_squared_error: 0.5523 - val_loss: 0.7080 - val_mean_squared_error: 0.7080\n",
      "Epoch 164/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5456 - mean_squared_error: 0.5456\n",
      "Epoch 00164: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5477 - mean_squared_error: 0.5477 - val_loss: 0.7121 - val_mean_squared_error: 0.7121\n",
      "Epoch 165/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5583 - mean_squared_error: 0.5583\n",
      "Epoch 00165: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5587 - mean_squared_error: 0.5587 - val_loss: 0.7169 - val_mean_squared_error: 0.7169\n",
      "Epoch 166/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5440 - mean_squared_error: 0.5440\n",
      "Epoch 00166: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5451 - mean_squared_error: 0.5451 - val_loss: 0.7215 - val_mean_squared_error: 0.7215\n",
      "Epoch 167/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5453 - mean_squared_error: 0.5453\n",
      "Epoch 00167: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5469 - mean_squared_error: 0.5469 - val_loss: 0.7243 - val_mean_squared_error: 0.7243\n",
      "Epoch 168/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5519 - mean_squared_error: 0.5519\n",
      "Epoch 00168: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5499 - mean_squared_error: 0.5499 - val_loss: 0.7277 - val_mean_squared_error: 0.7277\n",
      "Epoch 169/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5444 - mean_squared_error: 0.5444\n",
      "Epoch 00169: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5458 - mean_squared_error: 0.5458 - val_loss: 0.7305 - val_mean_squared_error: 0.7305\n",
      "Epoch 170/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5445 - mean_squared_error: 0.5445\n",
      "Epoch 00170: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5447 - mean_squared_error: 0.5447 - val_loss: 0.7334 - val_mean_squared_error: 0.7334\n",
      "Epoch 171/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5439 - mean_squared_error: 0.5439\n",
      "Epoch 00171: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5456 - mean_squared_error: 0.5456 - val_loss: 0.7363 - val_mean_squared_error: 0.7363\n",
      "Epoch 172/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5475 - mean_squared_error: 0.5475\n",
      "Epoch 00172: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5469 - mean_squared_error: 0.5469 - val_loss: 0.7386 - val_mean_squared_error: 0.7386\n",
      "Epoch 173/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5429 - mean_squared_error: 0.5429\n",
      "Epoch 00173: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5462 - mean_squared_error: 0.5462 - val_loss: 0.7414 - val_mean_squared_error: 0.7414\n",
      "Epoch 174/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5459 - mean_squared_error: 0.5459\n",
      "Epoch 00174: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5471 - mean_squared_error: 0.5471 - val_loss: 0.7439 - val_mean_squared_error: 0.7439\n",
      "Epoch 175/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5513 - mean_squared_error: 0.5513\n",
      "Epoch 00175: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5513 - mean_squared_error: 0.5513 - val_loss: 0.7462 - val_mean_squared_error: 0.7462\n",
      "Epoch 176/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5478 - mean_squared_error: 0.5478\n",
      "Epoch 00176: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5480 - mean_squared_error: 0.5480 - val_loss: 0.7489 - val_mean_squared_error: 0.7489\n",
      "Epoch 177/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5394 - mean_squared_error: 0.5394\n",
      "Epoch 00177: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5397 - mean_squared_error: 0.5397 - val_loss: 0.7507 - val_mean_squared_error: 0.7507\n",
      "Epoch 178/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5462 - mean_squared_error: 0.5462\n",
      "Epoch 00178: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5493 - mean_squared_error: 0.5493 - val_loss: 0.7535 - val_mean_squared_error: 0.7535\n",
      "Epoch 179/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5483 - mean_squared_error: 0.5483\n",
      "Epoch 00179: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5484 - mean_squared_error: 0.5484 - val_loss: 0.7556 - val_mean_squared_error: 0.7556\n",
      "Epoch 180/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5449 - mean_squared_error: 0.5449\n",
      "Epoch 00180: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5449 - mean_squared_error: 0.5449 - val_loss: 0.7572 - val_mean_squared_error: 0.7572\n",
      "Epoch 181/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5443 - mean_squared_error: 0.5443\n",
      "Epoch 00181: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5468 - mean_squared_error: 0.5468 - val_loss: 0.7591 - val_mean_squared_error: 0.7591\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 182/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5395 - mean_squared_error: 0.5395\n",
      "Epoch 00182: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5402 - mean_squared_error: 0.5402 - val_loss: 0.7612 - val_mean_squared_error: 0.7612\n",
      "Epoch 183/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5665 - mean_squared_error: 0.5665\n",
      "Epoch 00183: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5664 - mean_squared_error: 0.5664 - val_loss: 0.7617 - val_mean_squared_error: 0.7617\n",
      "Epoch 184/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5503 - mean_squared_error: 0.5503\n",
      "Epoch 00184: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5502 - mean_squared_error: 0.5502 - val_loss: 0.7632 - val_mean_squared_error: 0.7632\n",
      "Epoch 185/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5502 - mean_squared_error: 0.5502\n",
      "Epoch 00185: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5499 - mean_squared_error: 0.5499 - val_loss: 0.7634 - val_mean_squared_error: 0.7634\n",
      "Epoch 186/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5482 - mean_squared_error: 0.5482\n",
      "Epoch 00186: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 17s 3ms/sample - loss: 0.5496 - mean_squared_error: 0.5496 - val_loss: 0.7650 - val_mean_squared_error: 0.7650\n",
      "Epoch 187/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5465 - mean_squared_error: 0.5465\n",
      "Epoch 00187: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 17s 3ms/sample - loss: 0.5472 - mean_squared_error: 0.5472 - val_loss: 0.7660 - val_mean_squared_error: 0.7660\n",
      "Epoch 188/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5467 - mean_squared_error: 0.5467\n",
      "Epoch 00188: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5474 - mean_squared_error: 0.5474 - val_loss: 0.7675 - val_mean_squared_error: 0.7675\n",
      "Epoch 189/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5430 - mean_squared_error: 0.5430\n",
      "Epoch 00189: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5432 - mean_squared_error: 0.5432 - val_loss: 0.7689 - val_mean_squared_error: 0.7689\n",
      "Epoch 190/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5355 - mean_squared_error: 0.5355\n",
      "Epoch 00190: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5366 - mean_squared_error: 0.5366 - val_loss: 0.7703 - val_mean_squared_error: 0.7703\n",
      "Epoch 191/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5432 - mean_squared_error: 0.5432\n",
      "Epoch 00191: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5412 - mean_squared_error: 0.5412 - val_loss: 0.7713 - val_mean_squared_error: 0.7713\n",
      "Epoch 192/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5536 - mean_squared_error: 0.5536\n",
      "Epoch 00192: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5534 - mean_squared_error: 0.5534 - val_loss: 0.7721 - val_mean_squared_error: 0.7721\n",
      "Epoch 193/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5462 - mean_squared_error: 0.5462\n",
      "Epoch 00193: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5455 - mean_squared_error: 0.5455 - val_loss: 0.7729 - val_mean_squared_error: 0.7729\n",
      "Epoch 194/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5544 - mean_squared_error: 0.5544\n",
      "Epoch 00194: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5528 - mean_squared_error: 0.5528 - val_loss: 0.7738 - val_mean_squared_error: 0.7738\n",
      "Epoch 195/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5422 - mean_squared_error: 0.5422\n",
      "Epoch 00195: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5424 - mean_squared_error: 0.5424 - val_loss: 0.7749 - val_mean_squared_error: 0.7749\n",
      "Epoch 196/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5420 - mean_squared_error: 0.5420\n",
      "Epoch 00196: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5419 - mean_squared_error: 0.5419 - val_loss: 0.7751 - val_mean_squared_error: 0.7751\n",
      "Epoch 197/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5464 - mean_squared_error: 0.5464\n",
      "Epoch 00197: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5475 - mean_squared_error: 0.5475 - val_loss: 0.7760 - val_mean_squared_error: 0.7760\n",
      "Epoch 198/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5374 - mean_squared_error: 0.5374\n",
      "Epoch 00198: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 16s 3ms/sample - loss: 0.5364 - mean_squared_error: 0.5364 - val_loss: 0.7766 - val_mean_squared_error: 0.7766\n",
      "Epoch 199/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5432 - mean_squared_error: 0.5432\n",
      "Epoch 00199: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5398 - mean_squared_error: 0.5398 - val_loss: 0.7771 - val_mean_squared_error: 0.7771\n",
      "Epoch 200/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5461 - mean_squared_error: 0.5461\n",
      "Epoch 00200: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5459 - mean_squared_error: 0.5459 - val_loss: 0.7783 - val_mean_squared_error: 0.7783\n",
      "Epoch 201/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5469 - mean_squared_error: 0.5469\n",
      "Epoch 00201: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5464 - mean_squared_error: 0.5464 - val_loss: 0.7783 - val_mean_squared_error: 0.7783\n",
      "Epoch 202/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5446 - mean_squared_error: 0.5446\n",
      "Epoch 00202: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5441 - mean_squared_error: 0.5441 - val_loss: 0.7789 - val_mean_squared_error: 0.7789\n",
      "Epoch 203/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5422 - mean_squared_error: 0.5422\n",
      "Epoch 00203: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5417 - mean_squared_error: 0.5417 - val_loss: 0.7795 - val_mean_squared_error: 0.7795\n",
      "Epoch 204/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5515 - mean_squared_error: 0.5515\n",
      "Epoch 00204: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5494 - mean_squared_error: 0.5494 - val_loss: 0.7804 - val_mean_squared_error: 0.7804\n",
      "Epoch 205/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5470 - mean_squared_error: 0.5470\n",
      "Epoch 00205: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5472 - mean_squared_error: 0.5472 - val_loss: 0.7806 - val_mean_squared_error: 0.7806\n",
      "Epoch 206/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5533 - mean_squared_error: 0.5533\n",
      "Epoch 00206: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5525 - mean_squared_error: 0.5525 - val_loss: 0.7812 - val_mean_squared_error: 0.7812\n",
      "Epoch 207/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5455 - mean_squared_error: 0.5455\n",
      "Epoch 00207: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5488 - mean_squared_error: 0.5488 - val_loss: 0.7825 - val_mean_squared_error: 0.7825\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 208/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5424 - mean_squared_error: 0.5424\n",
      "Epoch 00208: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5419 - mean_squared_error: 0.5419 - val_loss: 0.7833 - val_mean_squared_error: 0.7833\n",
      "Epoch 209/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5535 - mean_squared_error: 0.5535\n",
      "Epoch 00209: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5535 - mean_squared_error: 0.5535 - val_loss: 0.7833 - val_mean_squared_error: 0.7833\n",
      "Epoch 210/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5445 - mean_squared_error: 0.5445\n",
      "Epoch 00210: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5423 - mean_squared_error: 0.5423 - val_loss: 0.7834 - val_mean_squared_error: 0.7834\n",
      "Epoch 211/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5438 - mean_squared_error: 0.5438\n",
      "Epoch 00211: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5444 - mean_squared_error: 0.5444 - val_loss: 0.7835 - val_mean_squared_error: 0.7835\n",
      "Epoch 212/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5546 - mean_squared_error: 0.5546\n",
      "Epoch 00212: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5532 - mean_squared_error: 0.5532 - val_loss: 0.7837 - val_mean_squared_error: 0.7837\n",
      "Epoch 213/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5423 - mean_squared_error: 0.5423\n",
      "Epoch 00213: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5441 - mean_squared_error: 0.5441 - val_loss: 0.7842 - val_mean_squared_error: 0.7842\n",
      "Epoch 214/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5452 - mean_squared_error: 0.5452\n",
      "Epoch 00214: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5462 - mean_squared_error: 0.5462 - val_loss: 0.7850 - val_mean_squared_error: 0.7850\n",
      "Epoch 215/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5455 - mean_squared_error: 0.5455\n",
      "Epoch 00215: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5437 - mean_squared_error: 0.5437 - val_loss: 0.7842 - val_mean_squared_error: 0.7842\n",
      "Epoch 216/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5451 - mean_squared_error: 0.5451\n",
      "Epoch 00216: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5456 - mean_squared_error: 0.5456 - val_loss: 0.7849 - val_mean_squared_error: 0.7849\n",
      "Epoch 217/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5425 - mean_squared_error: 0.5425\n",
      "Epoch 00217: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5439 - mean_squared_error: 0.5439 - val_loss: 0.7847 - val_mean_squared_error: 0.7847\n",
      "Epoch 218/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5514 - mean_squared_error: 0.5514\n",
      "Epoch 00218: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5490 - mean_squared_error: 0.5490 - val_loss: 0.7845 - val_mean_squared_error: 0.7845\n",
      "Epoch 219/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5379 - mean_squared_error: 0.5379\n",
      "Epoch 00219: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5405 - mean_squared_error: 0.5405 - val_loss: 0.7850 - val_mean_squared_error: 0.7850\n",
      "Epoch 220/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5463 - mean_squared_error: 0.5463\n",
      "Epoch 00220: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5462 - mean_squared_error: 0.5462 - val_loss: 0.7853 - val_mean_squared_error: 0.7853\n",
      "Epoch 221/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5445 - mean_squared_error: 0.5445\n",
      "Epoch 00221: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5442 - mean_squared_error: 0.5442 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 222/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5489 - mean_squared_error: 0.5489\n",
      "Epoch 00222: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5500 - mean_squared_error: 0.5500 - val_loss: 0.7857 - val_mean_squared_error: 0.7857\n",
      "Epoch 223/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5456 - mean_squared_error: 0.5456\n",
      "Epoch 00223: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5456 - mean_squared_error: 0.5456 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 224/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5564 - mean_squared_error: 0.5564\n",
      "Epoch 00224: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5555 - mean_squared_error: 0.5555 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 225/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5463 - mean_squared_error: 0.5463\n",
      "Epoch 00225: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5453 - mean_squared_error: 0.5453 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 226/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5487 - mean_squared_error: 0.5487\n",
      "Epoch 00226: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5476 - mean_squared_error: 0.5476 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 227/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5477 - mean_squared_error: 0.5477\n",
      "Epoch 00227: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5475 - mean_squared_error: 0.5475 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 228/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5422 - mean_squared_error: 0.5422\n",
      "Epoch 00228: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5437 - mean_squared_error: 0.5437 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 229/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5594 - mean_squared_error: 0.5594\n",
      "Epoch 00229: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5596 - mean_squared_error: 0.5596 - val_loss: 0.7865 - val_mean_squared_error: 0.7865\n",
      "Epoch 230/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5494 - mean_squared_error: 0.5494\n",
      "Epoch 00230: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5482 - mean_squared_error: 0.5482 - val_loss: 0.7867 - val_mean_squared_error: 0.7867\n",
      "Epoch 231/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5440 - mean_squared_error: 0.5440\n",
      "Epoch 00231: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5452 - mean_squared_error: 0.5452 - val_loss: 0.7865 - val_mean_squared_error: 0.7865\n",
      "Epoch 232/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5573 - mean_squared_error: 0.5573\n",
      "Epoch 00232: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 14s 3ms/sample - loss: 0.5563 - mean_squared_error: 0.5563 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 233/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5429 - mean_squared_error: 0.5429\n",
      "Epoch 00233: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5417 - mean_squared_error: 0.5417 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 234/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5466 - mean_squared_error: 0.5466\n",
      "Epoch 00234: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 15s 3ms/sample - loss: 0.5438 - mean_squared_error: 0.5438 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 235/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5488 - mean_squared_error: 0.5488\n",
      "Epoch 00235: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 13s 2ms/sample - loss: 0.5480 - mean_squared_error: 0.5480 - val_loss: 0.7857 - val_mean_squared_error: 0.7857\n",
      "Epoch 236/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5419 - mean_squared_error: 0.5419\n",
      "Epoch 00236: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5437 - mean_squared_error: 0.5437 - val_loss: 0.7855 - val_mean_squared_error: 0.7855\n",
      "Epoch 237/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5480 - mean_squared_error: 0.5480\n",
      "Epoch 00237: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5487 - mean_squared_error: 0.5487 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 238/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5456 - mean_squared_error: 0.5456\n",
      "Epoch 00238: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5476 - mean_squared_error: 0.5476 - val_loss: 0.7858 - val_mean_squared_error: 0.7858\n",
      "Epoch 239/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5443 - mean_squared_error: 0.5443\n",
      "Epoch 00239: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5434 - mean_squared_error: 0.5434 - val_loss: 0.7851 - val_mean_squared_error: 0.7851\n",
      "Epoch 240/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5458 - mean_squared_error: 0.5458\n",
      "Epoch 00240: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5456 - mean_squared_error: 0.5456 - val_loss: 0.7848 - val_mean_squared_error: 0.7848\n",
      "Epoch 241/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5488 - mean_squared_error: 0.5488\n",
      "Epoch 00241: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5481 - mean_squared_error: 0.5481 - val_loss: 0.7847 - val_mean_squared_error: 0.7847\n",
      "Epoch 242/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5435 - mean_squared_error: 0.5435\n",
      "Epoch 00242: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5433 - mean_squared_error: 0.5433 - val_loss: 0.7850 - val_mean_squared_error: 0.7850\n",
      "Epoch 243/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5562 - mean_squared_error: 0.5562\n",
      "Epoch 00243: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5588 - mean_squared_error: 0.5588 - val_loss: 0.7852 - val_mean_squared_error: 0.7852\n",
      "Epoch 244/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5465 - mean_squared_error: 0.5465\n",
      "Epoch 00244: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5490 - mean_squared_error: 0.5490 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 245/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5451 - mean_squared_error: 0.5451\n",
      "Epoch 00245: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5464 - mean_squared_error: 0.5464 - val_loss: 0.7857 - val_mean_squared_error: 0.7857\n",
      "Epoch 246/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5497 - mean_squared_error: 0.5497\n",
      "Epoch 00246: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5485 - mean_squared_error: 0.5485 - val_loss: 0.7855 - val_mean_squared_error: 0.7855\n",
      "Epoch 247/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5437 - mean_squared_error: 0.5437\n",
      "Epoch 00247: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5437 - mean_squared_error: 0.5437 - val_loss: 0.7854 - val_mean_squared_error: 0.7854\n",
      "Epoch 248/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5489 - mean_squared_error: 0.5489\n",
      "Epoch 00248: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5505 - mean_squared_error: 0.5505 - val_loss: 0.7848 - val_mean_squared_error: 0.7848\n",
      "Epoch 249/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5504 - mean_squared_error: 0.5504\n",
      "Epoch 00249: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5518 - mean_squared_error: 0.5518 - val_loss: 0.7847 - val_mean_squared_error: 0.7847\n",
      "Epoch 250/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5416 - mean_squared_error: 0.5416\n",
      "Epoch 00250: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5417 - mean_squared_error: 0.5417 - val_loss: 0.7842 - val_mean_squared_error: 0.7842\n",
      "Epoch 251/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5467 - mean_squared_error: 0.5467\n",
      "Epoch 00251: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5477 - mean_squared_error: 0.5477 - val_loss: 0.7839 - val_mean_squared_error: 0.7839\n",
      "Epoch 252/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5527 - mean_squared_error: 0.5527\n",
      "Epoch 00252: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5534 - mean_squared_error: 0.5534 - val_loss: 0.7840 - val_mean_squared_error: 0.7840\n",
      "Epoch 253/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5423 - mean_squared_error: 0.5423\n",
      "Epoch 00253: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5421 - mean_squared_error: 0.5421 - val_loss: 0.7833 - val_mean_squared_error: 0.7833\n",
      "Epoch 254/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5490 - mean_squared_error: 0.5490\n",
      "Epoch 00254: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5516 - mean_squared_error: 0.5516 - val_loss: 0.7836 - val_mean_squared_error: 0.7836\n",
      "Epoch 255/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5472 - mean_squared_error: 0.5472\n",
      "Epoch 00255: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5487 - mean_squared_error: 0.5487 - val_loss: 0.7830 - val_mean_squared_error: 0.7830\n",
      "Epoch 256/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5448 - mean_squared_error: 0.5448\n",
      "Epoch 00256: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5457 - mean_squared_error: 0.5457 - val_loss: 0.7829 - val_mean_squared_error: 0.7829\n",
      "Epoch 257/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5505 - mean_squared_error: 0.5505\n",
      "Epoch 00257: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5479 - mean_squared_error: 0.5479 - val_loss: 0.7833 - val_mean_squared_error: 0.7833\n",
      "Epoch 258/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5434 - mean_squared_error: 0.5434\n",
      "Epoch 00258: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5439 - mean_squared_error: 0.5439 - val_loss: 0.7832 - val_mean_squared_error: 0.7832\n",
      "Epoch 259/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5536 - mean_squared_error: 0.5536\n",
      "Epoch 00259: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5549 - mean_squared_error: 0.5549 - val_loss: 0.7834 - val_mean_squared_error: 0.7834\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 260/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5438 - mean_squared_error: 0.5438\n",
      "Epoch 00260: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5452 - mean_squared_error: 0.5452 - val_loss: 0.7839 - val_mean_squared_error: 0.7839\n",
      "Epoch 261/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5426 - mean_squared_error: 0.5426\n",
      "Epoch 00261: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5432 - mean_squared_error: 0.5432 - val_loss: 0.7837 - val_mean_squared_error: 0.7837\n",
      "Epoch 262/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5457 - mean_squared_error: 0.5457\n",
      "Epoch 00262: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5449 - mean_squared_error: 0.5449 - val_loss: 0.7833 - val_mean_squared_error: 0.7833\n",
      "Epoch 263/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5504 - mean_squared_error: 0.5504\n",
      "Epoch 00263: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5512 - mean_squared_error: 0.5512 - val_loss: 0.7832 - val_mean_squared_error: 0.7832\n",
      "Epoch 264/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5453 - mean_squared_error: 0.5453\n",
      "Epoch 00264: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5451 - mean_squared_error: 0.5451 - val_loss: 0.7838 - val_mean_squared_error: 0.7838\n",
      "Epoch 265/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5465 - mean_squared_error: 0.5465\n",
      "Epoch 00265: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5457 - mean_squared_error: 0.5457 - val_loss: 0.7840 - val_mean_squared_error: 0.7840\n",
      "Epoch 266/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5405 - mean_squared_error: 0.5405\n",
      "Epoch 00266: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5411 - mean_squared_error: 0.5411 - val_loss: 0.7847 - val_mean_squared_error: 0.7847\n",
      "Epoch 267/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5497 - mean_squared_error: 0.5497\n",
      "Epoch 00267: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5517 - mean_squared_error: 0.5517 - val_loss: 0.7850 - val_mean_squared_error: 0.7850\n",
      "Epoch 268/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5446 - mean_squared_error: 0.5446\n",
      "Epoch 00268: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5457 - mean_squared_error: 0.5457 - val_loss: 0.7849 - val_mean_squared_error: 0.7849\n",
      "Epoch 269/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5574 - mean_squared_error: 0.5574\n",
      "Epoch 00269: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5582 - mean_squared_error: 0.5582 - val_loss: 0.7848 - val_mean_squared_error: 0.7848\n",
      "Epoch 270/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5531 - mean_squared_error: 0.5531\n",
      "Epoch 00270: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5539 - mean_squared_error: 0.5539 - val_loss: 0.7843 - val_mean_squared_error: 0.7843\n",
      "Epoch 271/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5479 - mean_squared_error: 0.5479\n",
      "Epoch 00271: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5481 - mean_squared_error: 0.5481 - val_loss: 0.7838 - val_mean_squared_error: 0.7838\n",
      "Epoch 272/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5556 - mean_squared_error: 0.5556\n",
      "Epoch 00272: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5548 - mean_squared_error: 0.5548 - val_loss: 0.7836 - val_mean_squared_error: 0.7836\n",
      "Epoch 273/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5448 - mean_squared_error: 0.5448\n",
      "Epoch 00273: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5469 - mean_squared_error: 0.5469 - val_loss: 0.7840 - val_mean_squared_error: 0.7840\n",
      "Epoch 274/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5500 - mean_squared_error: 0.5500\n",
      "Epoch 00274: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5487 - mean_squared_error: 0.5487 - val_loss: 0.7833 - val_mean_squared_error: 0.7833\n",
      "Epoch 275/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5490 - mean_squared_error: 0.5490\n",
      "Epoch 00275: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5485 - mean_squared_error: 0.5485 - val_loss: 0.7841 - val_mean_squared_error: 0.7841\n",
      "Epoch 276/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5606 - mean_squared_error: 0.5606\n",
      "Epoch 00276: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5600 - mean_squared_error: 0.5600 - val_loss: 0.7843 - val_mean_squared_error: 0.7843\n",
      "Epoch 277/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5581 - mean_squared_error: 0.5581\n",
      "Epoch 00277: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5572 - mean_squared_error: 0.5572 - val_loss: 0.7854 - val_mean_squared_error: 0.7854\n",
      "Epoch 278/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5408 - mean_squared_error: 0.5408\n",
      "Epoch 00278: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5386 - mean_squared_error: 0.5386 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 279/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5462 - mean_squared_error: 0.5462\n",
      "Epoch 00279: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5452 - mean_squared_error: 0.5452 - val_loss: 0.7858 - val_mean_squared_error: 0.7858\n",
      "Epoch 280/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5464 - mean_squared_error: 0.5464\n",
      "Epoch 00280: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5468 - mean_squared_error: 0.5468 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 281/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5419 - mean_squared_error: 0.5419\n",
      "Epoch 00281: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5421 - mean_squared_error: 0.5421 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 282/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5576 - mean_squared_error: 0.5576\n",
      "Epoch 00282: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5558 - mean_squared_error: 0.5558 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 283/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5491 - mean_squared_error: 0.5491\n",
      "Epoch 00283: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5486 - mean_squared_error: 0.5486 - val_loss: 0.7865 - val_mean_squared_error: 0.7865\n",
      "Epoch 284/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5373 - mean_squared_error: 0.5373\n",
      "Epoch 00284: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5395 - mean_squared_error: 0.5395 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 285/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5434 - mean_squared_error: 0.5434\n",
      "Epoch 00285: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5450 - mean_squared_error: 0.5450 - val_loss: 0.7865 - val_mean_squared_error: 0.7865\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 286/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5517 - mean_squared_error: 0.5517\n",
      "Epoch 00286: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5489 - mean_squared_error: 0.5489 - val_loss: 0.7869 - val_mean_squared_error: 0.7869\n",
      "Epoch 287/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5434 - mean_squared_error: 0.5434\n",
      "Epoch 00287: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5432 - mean_squared_error: 0.5432 - val_loss: 0.7871 - val_mean_squared_error: 0.7871\n",
      "Epoch 288/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5495 - mean_squared_error: 0.5495\n",
      "Epoch 00288: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5491 - mean_squared_error: 0.5491 - val_loss: 0.7869 - val_mean_squared_error: 0.7869\n",
      "Epoch 289/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5463 - mean_squared_error: 0.5463\n",
      "Epoch 00289: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5431 - mean_squared_error: 0.5431 - val_loss: 0.7871 - val_mean_squared_error: 0.7871\n",
      "Epoch 290/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5565 - mean_squared_error: 0.5565\n",
      "Epoch 00290: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5542 - mean_squared_error: 0.5542 - val_loss: 0.7879 - val_mean_squared_error: 0.7879\n",
      "Epoch 291/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5554 - mean_squared_error: 0.5554\n",
      "Epoch 00291: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5558 - mean_squared_error: 0.5558 - val_loss: 0.7877 - val_mean_squared_error: 0.7877\n",
      "Epoch 292/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5474 - mean_squared_error: 0.5474\n",
      "Epoch 00292: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5463 - mean_squared_error: 0.5463 - val_loss: 0.7874 - val_mean_squared_error: 0.7874\n",
      "Epoch 293/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5429 - mean_squared_error: 0.5429\n",
      "Epoch 00293: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5433 - mean_squared_error: 0.5433 - val_loss: 0.7874 - val_mean_squared_error: 0.7874\n",
      "Epoch 294/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5379 - mean_squared_error: 0.5379\n",
      "Epoch 00294: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5367 - mean_squared_error: 0.5367 - val_loss: 0.7865 - val_mean_squared_error: 0.7865\n",
      "Epoch 295/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5395 - mean_squared_error: 0.5395\n",
      "Epoch 00295: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5377 - mean_squared_error: 0.5377 - val_loss: 0.7866 - val_mean_squared_error: 0.7866\n",
      "Epoch 296/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5426 - mean_squared_error: 0.5426\n",
      "Epoch 00296: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5427 - mean_squared_error: 0.5427 - val_loss: 0.7867 - val_mean_squared_error: 0.7867\n",
      "Epoch 297/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5468 - mean_squared_error: 0.5468\n",
      "Epoch 00297: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5477 - mean_squared_error: 0.5477 - val_loss: 0.7869 - val_mean_squared_error: 0.7869\n",
      "Epoch 298/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5497 - mean_squared_error: 0.5497\n",
      "Epoch 00298: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5484 - mean_squared_error: 0.5484 - val_loss: 0.7874 - val_mean_squared_error: 0.7874\n",
      "Epoch 299/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5447 - mean_squared_error: 0.5447\n",
      "Epoch 00299: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5452 - mean_squared_error: 0.5452 - val_loss: 0.7877 - val_mean_squared_error: 0.7877\n",
      "Epoch 300/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5429 - mean_squared_error: 0.5429\n",
      "Epoch 00300: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5446 - mean_squared_error: 0.5446 - val_loss: 0.7877 - val_mean_squared_error: 0.7877\n",
      "Epoch 301/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5410 - mean_squared_error: 0.5410\n",
      "Epoch 00301: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5420 - mean_squared_error: 0.5420 - val_loss: 0.7882 - val_mean_squared_error: 0.7882\n",
      "Epoch 302/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5524 - mean_squared_error: 0.5524\n",
      "Epoch 00302: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5541 - mean_squared_error: 0.5541 - val_loss: 0.7880 - val_mean_squared_error: 0.7880\n",
      "Epoch 303/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5462 - mean_squared_error: 0.5462\n",
      "Epoch 00303: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5504 - mean_squared_error: 0.5504 - val_loss: 0.7874 - val_mean_squared_error: 0.7874\n",
      "Epoch 304/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5521 - mean_squared_error: 0.5521\n",
      "Epoch 00304: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5517 - mean_squared_error: 0.5517 - val_loss: 0.7879 - val_mean_squared_error: 0.7879\n",
      "Epoch 305/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5549 - mean_squared_error: 0.5549\n",
      "Epoch 00305: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5525 - mean_squared_error: 0.5525 - val_loss: 0.7882 - val_mean_squared_error: 0.7882\n",
      "Epoch 306/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5455 - mean_squared_error: 0.5455\n",
      "Epoch 00306: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5464 - mean_squared_error: 0.5464 - val_loss: 0.7880 - val_mean_squared_error: 0.7880\n",
      "Epoch 307/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5530 - mean_squared_error: 0.5530\n",
      "Epoch 00307: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5523 - mean_squared_error: 0.5523 - val_loss: 0.7882 - val_mean_squared_error: 0.7882\n",
      "Epoch 308/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5424 - mean_squared_error: 0.5424\n",
      "Epoch 00308: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5421 - mean_squared_error: 0.5421 - val_loss: 0.7880 - val_mean_squared_error: 0.7880\n",
      "Epoch 309/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5376 - mean_squared_error: 0.5376\n",
      "Epoch 00309: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5390 - mean_squared_error: 0.5390 - val_loss: 0.7873 - val_mean_squared_error: 0.7873\n",
      "Epoch 310/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5487 - mean_squared_error: 0.5487\n",
      "Epoch 00310: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5491 - mean_squared_error: 0.5491 - val_loss: 0.7870 - val_mean_squared_error: 0.7870\n",
      "Epoch 311/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5454 - mean_squared_error: 0.5454\n",
      "Epoch 00311: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5470 - mean_squared_error: 0.5470 - val_loss: 0.7872 - val_mean_squared_error: 0.7872\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 312/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5520 - mean_squared_error: 0.5520\n",
      "Epoch 00312: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5507 - mean_squared_error: 0.5507 - val_loss: 0.7872 - val_mean_squared_error: 0.7872\n",
      "Epoch 313/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5529 - mean_squared_error: 0.5529\n",
      "Epoch 00313: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5522 - mean_squared_error: 0.5522 - val_loss: 0.7873 - val_mean_squared_error: 0.7873\n",
      "Epoch 314/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5631 - mean_squared_error: 0.5631\n",
      "Epoch 00314: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5598 - mean_squared_error: 0.5598 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 315/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5420 - mean_squared_error: 0.5420\n",
      "Epoch 00315: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5424 - mean_squared_error: 0.5424 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 316/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5421 - mean_squared_error: 0.5421\n",
      "Epoch 00316: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5422 - mean_squared_error: 0.5422 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 317/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5428 - mean_squared_error: 0.5428\n",
      "Epoch 00317: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5417 - mean_squared_error: 0.5417 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 318/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5444 - mean_squared_error: 0.5444\n",
      "Epoch 00318: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5462 - mean_squared_error: 0.5462 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 319/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5553 - mean_squared_error: 0.5553\n",
      "Epoch 00319: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5538 - mean_squared_error: 0.5538 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 320/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5541 - mean_squared_error: 0.5541\n",
      "Epoch 00320: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5513 - mean_squared_error: 0.5513 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 321/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5400 - mean_squared_error: 0.5400\n",
      "Epoch 00321: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5430 - mean_squared_error: 0.5430 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 322/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5418 - mean_squared_error: 0.5418\n",
      "Epoch 00322: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5416 - mean_squared_error: 0.5416 - val_loss: 0.7866 - val_mean_squared_error: 0.7866\n",
      "Epoch 323/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5512 - mean_squared_error: 0.5512\n",
      "Epoch 00323: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5542 - mean_squared_error: 0.5542 - val_loss: 0.7868 - val_mean_squared_error: 0.7868\n",
      "Epoch 324/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5554 - mean_squared_error: 0.5554\n",
      "Epoch 00324: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5557 - mean_squared_error: 0.5557 - val_loss: 0.7868 - val_mean_squared_error: 0.7868\n",
      "Epoch 325/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5517 - mean_squared_error: 0.5517\n",
      "Epoch 00325: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5517 - mean_squared_error: 0.5517 - val_loss: 0.7867 - val_mean_squared_error: 0.7867\n",
      "Epoch 326/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5539 - mean_squared_error: 0.5539\n",
      "Epoch 00326: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5527 - mean_squared_error: 0.5527 - val_loss: 0.7870 - val_mean_squared_error: 0.7870\n",
      "Epoch 327/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5535 - mean_squared_error: 0.5535\n",
      "Epoch 00327: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5505 - mean_squared_error: 0.5505 - val_loss: 0.7868 - val_mean_squared_error: 0.7868\n",
      "Epoch 328/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5484 - mean_squared_error: 0.5484\n",
      "Epoch 00328: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5472 - mean_squared_error: 0.5472 - val_loss: 0.7866 - val_mean_squared_error: 0.7866\n",
      "Epoch 329/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5411 - mean_squared_error: 0.5411\n",
      "Epoch 00329: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5411 - mean_squared_error: 0.5411 - val_loss: 0.7872 - val_mean_squared_error: 0.7872\n",
      "Epoch 330/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5359 - mean_squared_error: 0.5359\n",
      "Epoch 00330: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5361 - mean_squared_error: 0.5361 - val_loss: 0.7874 - val_mean_squared_error: 0.7874\n",
      "Epoch 331/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5433 - mean_squared_error: 0.5433\n",
      "Epoch 00331: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.5443 - mean_squared_error: 0.5443 - val_loss: 0.7877 - val_mean_squared_error: 0.7877\n",
      "Epoch 332/500\n",
      "5000/5513 [==========================>...] - ETA: 1s - loss: 0.5461 - mean_squared_error: 0.5461\n",
      "Epoch 00332: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.5482 - mean_squared_error: 0.5482 - val_loss: 0.7875 - val_mean_squared_error: 0.7875\n",
      "Epoch 333/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5458 - mean_squared_error: 0.5458\n",
      "Epoch 00333: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.5447 - mean_squared_error: 0.5447 - val_loss: 0.7875 - val_mean_squared_error: 0.7875\n",
      "Epoch 334/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5499 - mean_squared_error: 0.5499\n",
      "Epoch 00334: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5525 - mean_squared_error: 0.5525 - val_loss: 0.7867 - val_mean_squared_error: 0.7867\n",
      "Epoch 335/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5453 - mean_squared_error: 0.5453\n",
      "Epoch 00335: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.5456 - mean_squared_error: 0.5456 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 336/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5472 - mean_squared_error: 0.5472\n",
      "Epoch 00336: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.5466 - mean_squared_error: 0.5466 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 337/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5462 - mean_squared_error: 0.5462\n",
      "Epoch 00337: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.5486 - mean_squared_error: 0.5486 - val_loss: 0.7858 - val_mean_squared_error: 0.7858\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 338/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5501 - mean_squared_error: 0.5501\n",
      "Epoch 00338: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.5480 - mean_squared_error: 0.5480 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 339/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5504 - mean_squared_error: 0.5504\n",
      "Epoch 00339: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.5513 - mean_squared_error: 0.5513 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 340/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5541 - mean_squared_error: 0.5541\n",
      "Epoch 00340: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5546 - mean_squared_error: 0.5546 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 341/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5475 - mean_squared_error: 0.5475\n",
      "Epoch 00341: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5481 - mean_squared_error: 0.5481 - val_loss: 0.7858 - val_mean_squared_error: 0.7858\n",
      "Epoch 342/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5486 - mean_squared_error: 0.5486\n",
      "Epoch 00342: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5483 - mean_squared_error: 0.5483 - val_loss: 0.7867 - val_mean_squared_error: 0.7867\n",
      "Epoch 343/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5518 - mean_squared_error: 0.5518\n",
      "Epoch 00343: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5514 - mean_squared_error: 0.5514 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 344/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5518 - mean_squared_error: 0.5518\n",
      "Epoch 00344: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5502 - mean_squared_error: 0.5502 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 345/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5581 - mean_squared_error: 0.5581\n",
      "Epoch 00345: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5572 - mean_squared_error: 0.5572 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 346/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5566 - mean_squared_error: 0.5566\n",
      "Epoch 00346: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5559 - mean_squared_error: 0.5559 - val_loss: 0.7865 - val_mean_squared_error: 0.7865\n",
      "Epoch 347/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5549 - mean_squared_error: 0.5549\n",
      "Epoch 00347: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5501 - mean_squared_error: 0.5501 - val_loss: 0.7869 - val_mean_squared_error: 0.7869\n",
      "Epoch 348/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5466 - mean_squared_error: 0.5466\n",
      "Epoch 00348: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5501 - mean_squared_error: 0.5501 - val_loss: 0.7868 - val_mean_squared_error: 0.7868\n",
      "Epoch 349/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5481 - mean_squared_error: 0.5481\n",
      "Epoch 00349: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5500 - mean_squared_error: 0.5500 - val_loss: 0.7865 - val_mean_squared_error: 0.7865\n",
      "Epoch 350/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5516 - mean_squared_error: 0.5516\n",
      "Epoch 00350: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5500 - mean_squared_error: 0.5500 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 351/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5534 - mean_squared_error: 0.5534\n",
      "Epoch 00351: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5546 - mean_squared_error: 0.5546 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 352/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5527 - mean_squared_error: 0.5527\n",
      "Epoch 00352: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5521 - mean_squared_error: 0.5521 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 353/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5427 - mean_squared_error: 0.5427\n",
      "Epoch 00353: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5441 - mean_squared_error: 0.5441 - val_loss: 0.7854 - val_mean_squared_error: 0.7854\n",
      "Epoch 354/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5500 - mean_squared_error: 0.5500\n",
      "Epoch 00354: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5484 - mean_squared_error: 0.5484 - val_loss: 0.7857 - val_mean_squared_error: 0.7857\n",
      "Epoch 355/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5503 - mean_squared_error: 0.5503\n",
      "Epoch 00355: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5481 - mean_squared_error: 0.5481 - val_loss: 0.7857 - val_mean_squared_error: 0.7857\n",
      "Epoch 356/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5384 - mean_squared_error: 0.5384\n",
      "Epoch 00356: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5399 - mean_squared_error: 0.5399 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 357/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5484 - mean_squared_error: 0.5484\n",
      "Epoch 00357: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5487 - mean_squared_error: 0.5487 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 358/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5554 - mean_squared_error: 0.5554\n",
      "Epoch 00358: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5594 - mean_squared_error: 0.5594 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 359/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5579 - mean_squared_error: 0.5579\n",
      "Epoch 00359: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5564 - mean_squared_error: 0.5564 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 360/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5373 - mean_squared_error: 0.5373\n",
      "Epoch 00360: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5404 - mean_squared_error: 0.5404 - val_loss: 0.7866 - val_mean_squared_error: 0.7866\n",
      "Epoch 361/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5473 - mean_squared_error: 0.5473\n",
      "Epoch 00361: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5445 - mean_squared_error: 0.5445 - val_loss: 0.7871 - val_mean_squared_error: 0.7871\n",
      "Epoch 362/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5507 - mean_squared_error: 0.5507\n",
      "Epoch 00362: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5488 - mean_squared_error: 0.5488 - val_loss: 0.7877 - val_mean_squared_error: 0.7877\n",
      "Epoch 363/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5584 - mean_squared_error: 0.5584\n",
      "Epoch 00363: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5566 - mean_squared_error: 0.5566 - val_loss: 0.7872 - val_mean_squared_error: 0.7872\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 364/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5457 - mean_squared_error: 0.5457\n",
      "Epoch 00364: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5455 - mean_squared_error: 0.5455 - val_loss: 0.7876 - val_mean_squared_error: 0.7876\n",
      "Epoch 365/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5573 - mean_squared_error: 0.5573\n",
      "Epoch 00365: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5551 - mean_squared_error: 0.5551 - val_loss: 0.7875 - val_mean_squared_error: 0.7875\n",
      "Epoch 366/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5454 - mean_squared_error: 0.5454\n",
      "Epoch 00366: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5449 - mean_squared_error: 0.5449 - val_loss: 0.7873 - val_mean_squared_error: 0.7873\n",
      "Epoch 367/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5430 - mean_squared_error: 0.5430\n",
      "Epoch 00367: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5426 - mean_squared_error: 0.5426 - val_loss: 0.7878 - val_mean_squared_error: 0.7878\n",
      "Epoch 368/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5487 - mean_squared_error: 0.5487\n",
      "Epoch 00368: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5489 - mean_squared_error: 0.5489 - val_loss: 0.7874 - val_mean_squared_error: 0.7874\n",
      "Epoch 369/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5424 - mean_squared_error: 0.5424\n",
      "Epoch 00369: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5451 - mean_squared_error: 0.5451 - val_loss: 0.7877 - val_mean_squared_error: 0.7877\n",
      "Epoch 370/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5452 - mean_squared_error: 0.5452\n",
      "Epoch 00370: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5455 - mean_squared_error: 0.5455 - val_loss: 0.7883 - val_mean_squared_error: 0.7883\n",
      "Epoch 371/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5501 - mean_squared_error: 0.5501\n",
      "Epoch 00371: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5481 - mean_squared_error: 0.5481 - val_loss: 0.7882 - val_mean_squared_error: 0.7882\n",
      "Epoch 372/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5482 - mean_squared_error: 0.5482\n",
      "Epoch 00372: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5496 - mean_squared_error: 0.5496 - val_loss: 0.7882 - val_mean_squared_error: 0.7882\n",
      "Epoch 373/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5505 - mean_squared_error: 0.5505\n",
      "Epoch 00373: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5502 - mean_squared_error: 0.5502 - val_loss: 0.7877 - val_mean_squared_error: 0.7877\n",
      "Epoch 374/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5438 - mean_squared_error: 0.5438\n",
      "Epoch 00374: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5418 - mean_squared_error: 0.5418 - val_loss: 0.7876 - val_mean_squared_error: 0.7876\n",
      "Epoch 375/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5507 - mean_squared_error: 0.5507\n",
      "Epoch 00375: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 11s 2ms/sample - loss: 0.5501 - mean_squared_error: 0.5501 - val_loss: 0.7874 - val_mean_squared_error: 0.7874\n",
      "Epoch 376/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5555 - mean_squared_error: 0.5555\n",
      "Epoch 00376: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5562 - mean_squared_error: 0.5562 - val_loss: 0.7872 - val_mean_squared_error: 0.7872\n",
      "Epoch 377/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5498 - mean_squared_error: 0.5498\n",
      "Epoch 00377: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5497 - mean_squared_error: 0.5497 - val_loss: 0.7873 - val_mean_squared_error: 0.7873\n",
      "Epoch 378/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5508 - mean_squared_error: 0.5508\n",
      "Epoch 00378: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5494 - mean_squared_error: 0.5494 - val_loss: 0.7870 - val_mean_squared_error: 0.7870\n",
      "Epoch 379/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5446 - mean_squared_error: 0.5446\n",
      "Epoch 00379: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5438 - mean_squared_error: 0.5438 - val_loss: 0.7871 - val_mean_squared_error: 0.7871\n",
      "Epoch 380/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5559 - mean_squared_error: 0.5559\n",
      "Epoch 00380: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5554 - mean_squared_error: 0.5554 - val_loss: 0.7869 - val_mean_squared_error: 0.7869\n",
      "Epoch 381/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5565 - mean_squared_error: 0.5565\n",
      "Epoch 00381: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5571 - mean_squared_error: 0.5571 - val_loss: 0.7868 - val_mean_squared_error: 0.7868\n",
      "Epoch 382/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5499 - mean_squared_error: 0.5499\n",
      "Epoch 00382: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5503 - mean_squared_error: 0.5503 - val_loss: 0.7868 - val_mean_squared_error: 0.7868\n",
      "Epoch 383/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5465 - mean_squared_error: 0.5465\n",
      "Epoch 00383: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5460 - mean_squared_error: 0.5460 - val_loss: 0.7866 - val_mean_squared_error: 0.7866\n",
      "Epoch 384/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5468 - mean_squared_error: 0.5468\n",
      "Epoch 00384: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5504 - mean_squared_error: 0.5504 - val_loss: 0.7870 - val_mean_squared_error: 0.7870\n",
      "Epoch 385/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5507 - mean_squared_error: 0.5507\n",
      "Epoch 00385: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5494 - mean_squared_error: 0.5494 - val_loss: 0.7868 - val_mean_squared_error: 0.7868\n",
      "Epoch 386/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5515 - mean_squared_error: 0.5515\n",
      "Epoch 00386: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5499 - mean_squared_error: 0.5499 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 387/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5436 - mean_squared_error: 0.5436\n",
      "Epoch 00387: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5466 - mean_squared_error: 0.5466 - val_loss: 0.7855 - val_mean_squared_error: 0.7855\n",
      "Epoch 388/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5455 - mean_squared_error: 0.5455\n",
      "Epoch 00388: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5493 - mean_squared_error: 0.5493 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 389/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5564 - mean_squared_error: 0.5564\n",
      "Epoch 00389: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5534 - mean_squared_error: 0.5534 - val_loss: 0.7865 - val_mean_squared_error: 0.7865\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 390/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5420 - mean_squared_error: 0.5420\n",
      "Epoch 00390: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5416 - mean_squared_error: 0.5416 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 391/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5454 - mean_squared_error: 0.5454\n",
      "Epoch 00391: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5474 - mean_squared_error: 0.5474 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 392/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5507 - mean_squared_error: 0.5507\n",
      "Epoch 00392: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5489 - mean_squared_error: 0.5489 - val_loss: 0.7857 - val_mean_squared_error: 0.7857\n",
      "Epoch 393/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5527 - mean_squared_error: 0.5527\n",
      "Epoch 00393: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5514 - mean_squared_error: 0.5514 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 394/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5513 - mean_squared_error: 0.5513\n",
      "Epoch 00394: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5525 - mean_squared_error: 0.5525 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 395/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5501 - mean_squared_error: 0.5501\n",
      "Epoch 00395: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5509 - mean_squared_error: 0.5509 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 396/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5509 - mean_squared_error: 0.5509\n",
      "Epoch 00396: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5549 - mean_squared_error: 0.5549 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 397/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5476 - mean_squared_error: 0.5476\n",
      "Epoch 00397: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5473 - mean_squared_error: 0.5473 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 398/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5475 - mean_squared_error: 0.5475\n",
      "Epoch 00398: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5475 - mean_squared_error: 0.5475 - val_loss: 0.7857 - val_mean_squared_error: 0.7857\n",
      "Epoch 399/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5404 - mean_squared_error: 0.5404\n",
      "Epoch 00399: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5417 - mean_squared_error: 0.5417 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 400/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5457 - mean_squared_error: 0.5457\n",
      "Epoch 00400: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5455 - mean_squared_error: 0.5455 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 401/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5418 - mean_squared_error: 0.5418\n",
      "Epoch 00401: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5429 - mean_squared_error: 0.5429 - val_loss: 0.7857 - val_mean_squared_error: 0.7857\n",
      "Epoch 402/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5546 - mean_squared_error: 0.5546\n",
      "Epoch 00402: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5540 - mean_squared_error: 0.5540 - val_loss: 0.7867 - val_mean_squared_error: 0.7867\n",
      "Epoch 403/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5535 - mean_squared_error: 0.5535\n",
      "Epoch 00403: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5511 - mean_squared_error: 0.5511 - val_loss: 0.7866 - val_mean_squared_error: 0.7866\n",
      "Epoch 404/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5543 - mean_squared_error: 0.5543\n",
      "Epoch 00404: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5521 - mean_squared_error: 0.5521 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 405/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5536 - mean_squared_error: 0.5536\n",
      "Epoch 00405: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5536 - mean_squared_error: 0.5536 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 406/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5498 - mean_squared_error: 0.5498\n",
      "Epoch 00406: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5505 - mean_squared_error: 0.5505 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 407/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5437 - mean_squared_error: 0.5437\n",
      "Epoch 00407: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5443 - mean_squared_error: 0.5443 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 408/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5468 - mean_squared_error: 0.5468\n",
      "Epoch 00408: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5478 - mean_squared_error: 0.5478 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 409/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5441 - mean_squared_error: 0.5441\n",
      "Epoch 00409: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5436 - mean_squared_error: 0.5436 - val_loss: 0.7849 - val_mean_squared_error: 0.7849\n",
      "Epoch 410/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5416 - mean_squared_error: 0.5416\n",
      "Epoch 00410: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5418 - mean_squared_error: 0.5418 - val_loss: 0.7842 - val_mean_squared_error: 0.7842\n",
      "Epoch 411/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5462 - mean_squared_error: 0.5462\n",
      "Epoch 00411: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5467 - mean_squared_error: 0.5467 - val_loss: 0.7845 - val_mean_squared_error: 0.7845\n",
      "Epoch 412/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5430 - mean_squared_error: 0.5430\n",
      "Epoch 00412: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5438 - mean_squared_error: 0.5438 - val_loss: 0.7851 - val_mean_squared_error: 0.7851\n",
      "Epoch 413/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5522 - mean_squared_error: 0.5522\n",
      "Epoch 00413: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5527 - mean_squared_error: 0.5527 - val_loss: 0.7852 - val_mean_squared_error: 0.7852\n",
      "Epoch 414/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5428 - mean_squared_error: 0.5428\n",
      "Epoch 00414: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5463 - mean_squared_error: 0.5463 - val_loss: 0.7850 - val_mean_squared_error: 0.7850\n",
      "Epoch 415/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5461 - mean_squared_error: 0.5461\n",
      "Epoch 00415: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5450 - mean_squared_error: 0.5450 - val_loss: 0.7853 - val_mean_squared_error: 0.7853\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 416/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5469 - mean_squared_error: 0.5469\n",
      "Epoch 00416: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5480 - mean_squared_error: 0.5480 - val_loss: 0.7852 - val_mean_squared_error: 0.7852\n",
      "Epoch 417/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5524 - mean_squared_error: 0.5524\n",
      "Epoch 00417: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5503 - mean_squared_error: 0.5503 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 418/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5515 - mean_squared_error: 0.5515\n",
      "Epoch 00418: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5510 - mean_squared_error: 0.5510 - val_loss: 0.7852 - val_mean_squared_error: 0.7852\n",
      "Epoch 419/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5416 - mean_squared_error: 0.5416\n",
      "Epoch 00419: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5405 - mean_squared_error: 0.5405 - val_loss: 0.7858 - val_mean_squared_error: 0.7858\n",
      "Epoch 420/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5443 - mean_squared_error: 0.5443\n",
      "Epoch 00420: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5438 - mean_squared_error: 0.5438 - val_loss: 0.7852 - val_mean_squared_error: 0.7852\n",
      "Epoch 421/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5448 - mean_squared_error: 0.5448\n",
      "Epoch 00421: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5458 - mean_squared_error: 0.5458 - val_loss: 0.7851 - val_mean_squared_error: 0.7851\n",
      "Epoch 422/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5573 - mean_squared_error: 0.5573\n",
      "Epoch 00422: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5562 - mean_squared_error: 0.5562 - val_loss: 0.7849 - val_mean_squared_error: 0.7849\n",
      "Epoch 423/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5419 - mean_squared_error: 0.5419\n",
      "Epoch 00423: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5430 - mean_squared_error: 0.5430 - val_loss: 0.7846 - val_mean_squared_error: 0.7846\n",
      "Epoch 424/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5535 - mean_squared_error: 0.5535\n",
      "Epoch 00424: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5508 - mean_squared_error: 0.5508 - val_loss: 0.7851 - val_mean_squared_error: 0.7851\n",
      "Epoch 425/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5394 - mean_squared_error: 0.5394\n",
      "Epoch 00425: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5388 - mean_squared_error: 0.5388 - val_loss: 0.7854 - val_mean_squared_error: 0.7854\n",
      "Epoch 426/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5382 - mean_squared_error: 0.5382\n",
      "Epoch 00426: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5379 - mean_squared_error: 0.5379 - val_loss: 0.7853 - val_mean_squared_error: 0.7853\n",
      "Epoch 427/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5578 - mean_squared_error: 0.5578\n",
      "Epoch 00427: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5566 - mean_squared_error: 0.5566 - val_loss: 0.7855 - val_mean_squared_error: 0.7855\n",
      "Epoch 428/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5480 - mean_squared_error: 0.5480\n",
      "Epoch 00428: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5474 - mean_squared_error: 0.5474 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 429/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5504 - mean_squared_error: 0.5504\n",
      "Epoch 00429: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5476 - mean_squared_error: 0.5476 - val_loss: 0.7854 - val_mean_squared_error: 0.7854\n",
      "Epoch 430/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5552 - mean_squared_error: 0.5552\n",
      "Epoch 00430: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5540 - mean_squared_error: 0.5540 - val_loss: 0.7851 - val_mean_squared_error: 0.7851\n",
      "Epoch 431/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5528 - mean_squared_error: 0.5528\n",
      "Epoch 00431: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5546 - mean_squared_error: 0.5546 - val_loss: 0.7852 - val_mean_squared_error: 0.7852\n",
      "Epoch 432/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5571 - mean_squared_error: 0.5571\n",
      "Epoch 00432: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5567 - mean_squared_error: 0.5567 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 433/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5487 - mean_squared_error: 0.5487\n",
      "Epoch 00433: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5483 - mean_squared_error: 0.5483 - val_loss: 0.7865 - val_mean_squared_error: 0.7865\n",
      "Epoch 434/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5514 - mean_squared_error: 0.5514\n",
      "Epoch 00434: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5499 - mean_squared_error: 0.5499 - val_loss: 0.7857 - val_mean_squared_error: 0.7857\n",
      "Epoch 435/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5549 - mean_squared_error: 0.5549\n",
      "Epoch 00435: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5575 - mean_squared_error: 0.5575 - val_loss: 0.7850 - val_mean_squared_error: 0.7850\n",
      "Epoch 436/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5426 - mean_squared_error: 0.5426\n",
      "Epoch 00436: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5433 - mean_squared_error: 0.5433 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 437/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5548 - mean_squared_error: 0.5548\n",
      "Epoch 00437: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5535 - mean_squared_error: 0.5535 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 438/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5486 - mean_squared_error: 0.5486\n",
      "Epoch 00438: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5506 - mean_squared_error: 0.5506 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 439/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5522 - mean_squared_error: 0.5522\n",
      "Epoch 00439: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5557 - mean_squared_error: 0.5557 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 440/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5481 - mean_squared_error: 0.5481\n",
      "Epoch 00440: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5502 - mean_squared_error: 0.5502 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 441/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5428 - mean_squared_error: 0.5428\n",
      "Epoch 00441: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5415 - mean_squared_error: 0.5415 - val_loss: 0.7869 - val_mean_squared_error: 0.7869\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 442/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5517 - mean_squared_error: 0.5517\n",
      "Epoch 00442: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5515 - mean_squared_error: 0.5515 - val_loss: 0.7866 - val_mean_squared_error: 0.7866\n",
      "Epoch 443/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5468 - mean_squared_error: 0.5468\n",
      "Epoch 00443: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5473 - mean_squared_error: 0.5473 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 444/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5512 - mean_squared_error: 0.5512\n",
      "Epoch 00444: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5511 - mean_squared_error: 0.5511 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 445/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5539 - mean_squared_error: 0.5539\n",
      "Epoch 00445: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5520 - mean_squared_error: 0.5520 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 446/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5506 - mean_squared_error: 0.5506\n",
      "Epoch 00446: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5475 - mean_squared_error: 0.5475 - val_loss: 0.7869 - val_mean_squared_error: 0.7869\n",
      "Epoch 447/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5462 - mean_squared_error: 0.5462\n",
      "Epoch 00447: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5449 - mean_squared_error: 0.5449 - val_loss: 0.7871 - val_mean_squared_error: 0.7871\n",
      "Epoch 448/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5466 - mean_squared_error: 0.5466\n",
      "Epoch 00448: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5487 - mean_squared_error: 0.5487 - val_loss: 0.7869 - val_mean_squared_error: 0.7869\n",
      "Epoch 449/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5572 - mean_squared_error: 0.5572\n",
      "Epoch 00449: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5552 - mean_squared_error: 0.5552 - val_loss: 0.7868 - val_mean_squared_error: 0.7868\n",
      "Epoch 450/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5322 - mean_squared_error: 0.5322\n",
      "Epoch 00450: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5320 - mean_squared_error: 0.5320 - val_loss: 0.7863 - val_mean_squared_error: 0.7863\n",
      "Epoch 451/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5421 - mean_squared_error: 0.5421\n",
      "Epoch 00451: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5432 - mean_squared_error: 0.5432 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 452/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5553 - mean_squared_error: 0.5553\n",
      "Epoch 00452: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5552 - mean_squared_error: 0.5552 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 453/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5468 - mean_squared_error: 0.5468\n",
      "Epoch 00453: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5489 - mean_squared_error: 0.5489 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 454/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5469 - mean_squared_error: 0.5469\n",
      "Epoch 00454: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5489 - mean_squared_error: 0.5489 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 455/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5470 - mean_squared_error: 0.5470\n",
      "Epoch 00455: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5462 - mean_squared_error: 0.5462 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 456/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5448 - mean_squared_error: 0.5448\n",
      "Epoch 00456: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5452 - mean_squared_error: 0.5452 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 457/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5439 - mean_squared_error: 0.5439\n",
      "Epoch 00457: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5427 - mean_squared_error: 0.5427 - val_loss: 0.7858 - val_mean_squared_error: 0.7858\n",
      "Epoch 458/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5468 - mean_squared_error: 0.5468\n",
      "Epoch 00458: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5439 - mean_squared_error: 0.5439 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 459/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5527 - mean_squared_error: 0.5527\n",
      "Epoch 00459: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5553 - mean_squared_error: 0.5553 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 460/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5445 - mean_squared_error: 0.5445\n",
      "Epoch 00460: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5452 - mean_squared_error: 0.5452 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 461/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5637 - mean_squared_error: 0.5637\n",
      "Epoch 00461: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5620 - mean_squared_error: 0.5620 - val_loss: 0.7849 - val_mean_squared_error: 0.7849\n",
      "Epoch 462/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5541 - mean_squared_error: 0.5541\n",
      "Epoch 00462: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5559 - mean_squared_error: 0.5559 - val_loss: 0.7851 - val_mean_squared_error: 0.7851\n",
      "Epoch 463/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5454 - mean_squared_error: 0.5454\n",
      "Epoch 00463: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5420 - mean_squared_error: 0.5420 - val_loss: 0.7846 - val_mean_squared_error: 0.7846\n",
      "Epoch 464/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5522 - mean_squared_error: 0.5522\n",
      "Epoch 00464: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5522 - mean_squared_error: 0.5522 - val_loss: 0.7846 - val_mean_squared_error: 0.7846\n",
      "Epoch 465/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5507 - mean_squared_error: 0.5507\n",
      "Epoch 00465: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5473 - mean_squared_error: 0.5473 - val_loss: 0.7847 - val_mean_squared_error: 0.7847\n",
      "Epoch 466/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5487 - mean_squared_error: 0.5487\n",
      "Epoch 00466: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5498 - mean_squared_error: 0.5498 - val_loss: 0.7845 - val_mean_squared_error: 0.7845\n",
      "Epoch 467/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5418 - mean_squared_error: 0.5418\n",
      "Epoch 00467: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5432 - mean_squared_error: 0.5432 - val_loss: 0.7849 - val_mean_squared_error: 0.7849\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 468/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5454 - mean_squared_error: 0.5454\n",
      "Epoch 00468: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5456 - mean_squared_error: 0.5456 - val_loss: 0.7847 - val_mean_squared_error: 0.7847\n",
      "Epoch 469/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5446 - mean_squared_error: 0.5446\n",
      "Epoch 00469: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5459 - mean_squared_error: 0.5459 - val_loss: 0.7853 - val_mean_squared_error: 0.7853\n",
      "Epoch 470/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5508 - mean_squared_error: 0.5508\n",
      "Epoch 00470: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5501 - mean_squared_error: 0.5501 - val_loss: 0.7849 - val_mean_squared_error: 0.7849\n",
      "Epoch 471/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5437 - mean_squared_error: 0.5437\n",
      "Epoch 00471: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5437 - mean_squared_error: 0.5437 - val_loss: 0.7847 - val_mean_squared_error: 0.7847\n",
      "Epoch 472/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5485 - mean_squared_error: 0.5485\n",
      "Epoch 00472: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5508 - mean_squared_error: 0.5508 - val_loss: 0.7850 - val_mean_squared_error: 0.7850\n",
      "Epoch 473/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5485 - mean_squared_error: 0.5485\n",
      "Epoch 00473: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5500 - mean_squared_error: 0.5500 - val_loss: 0.7846 - val_mean_squared_error: 0.7846\n",
      "Epoch 474/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5413 - mean_squared_error: 0.5413\n",
      "Epoch 00474: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5407 - mean_squared_error: 0.5407 - val_loss: 0.7847 - val_mean_squared_error: 0.7847\n",
      "Epoch 475/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5470 - mean_squared_error: 0.5470\n",
      "Epoch 00475: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5461 - mean_squared_error: 0.5461 - val_loss: 0.7847 - val_mean_squared_error: 0.7847\n",
      "Epoch 476/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5404 - mean_squared_error: 0.5404\n",
      "Epoch 00476: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5407 - mean_squared_error: 0.5407 - val_loss: 0.7847 - val_mean_squared_error: 0.7847\n",
      "Epoch 477/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5501 - mean_squared_error: 0.5501\n",
      "Epoch 00477: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5497 - mean_squared_error: 0.5497 - val_loss: 0.7845 - val_mean_squared_error: 0.7845\n",
      "Epoch 478/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5496 - mean_squared_error: 0.5496\n",
      "Epoch 00478: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5465 - mean_squared_error: 0.5465 - val_loss: 0.7845 - val_mean_squared_error: 0.7845\n",
      "Epoch 479/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5532 - mean_squared_error: 0.5532\n",
      "Epoch 00479: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5539 - mean_squared_error: 0.5539 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 480/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5526 - mean_squared_error: 0.5526\n",
      "Epoch 00480: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5516 - mean_squared_error: 0.5516 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 481/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5523 - mean_squared_error: 0.5523\n",
      "Epoch 00481: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5531 - mean_squared_error: 0.5531 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 482/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5482 - mean_squared_error: 0.5482\n",
      "Epoch 00482: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5468 - mean_squared_error: 0.5468 - val_loss: 0.7851 - val_mean_squared_error: 0.7851\n",
      "Epoch 483/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5460 - mean_squared_error: 0.5460\n",
      "Epoch 00483: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5495 - mean_squared_error: 0.5495 - val_loss: 0.7841 - val_mean_squared_error: 0.7841\n",
      "Epoch 484/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5471 - mean_squared_error: 0.5471\n",
      "Epoch 00484: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5482 - mean_squared_error: 0.5482 - val_loss: 0.7844 - val_mean_squared_error: 0.7844\n",
      "Epoch 485/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5461 - mean_squared_error: 0.5461\n",
      "Epoch 00485: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5466 - mean_squared_error: 0.5466 - val_loss: 0.7854 - val_mean_squared_error: 0.7854\n",
      "Epoch 486/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5460 - mean_squared_error: 0.5460\n",
      "Epoch 00486: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5478 - mean_squared_error: 0.5478 - val_loss: 0.7856 - val_mean_squared_error: 0.7856\n",
      "Epoch 487/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5507 - mean_squared_error: 0.5507\n",
      "Epoch 00487: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5521 - mean_squared_error: 0.5521 - val_loss: 0.7859 - val_mean_squared_error: 0.7859\n",
      "Epoch 488/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5509 - mean_squared_error: 0.5509\n",
      "Epoch 00488: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5540 - mean_squared_error: 0.5540 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 489/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5490 - mean_squared_error: 0.5490\n",
      "Epoch 00489: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5504 - mean_squared_error: 0.5504 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 490/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5514 - mean_squared_error: 0.5514\n",
      "Epoch 00490: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5499 - mean_squared_error: 0.5499 - val_loss: 0.7861 - val_mean_squared_error: 0.7861\n",
      "Epoch 491/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5463 - mean_squared_error: 0.5463\n",
      "Epoch 00491: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5462 - mean_squared_error: 0.5462 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n",
      "Epoch 492/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5429 - mean_squared_error: 0.5429\n",
      "Epoch 00492: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5459 - mean_squared_error: 0.5459 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 493/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5414 - mean_squared_error: 0.5414\n",
      "Epoch 00493: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5419 - mean_squared_error: 0.5419 - val_loss: 0.7860 - val_mean_squared_error: 0.7860\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 494/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5465 - mean_squared_error: 0.5465\n",
      "Epoch 00494: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5497 - mean_squared_error: 0.5497 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 495/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5474 - mean_squared_error: 0.5474\n",
      "Epoch 00495: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5481 - mean_squared_error: 0.5481 - val_loss: 0.7862 - val_mean_squared_error: 0.7862\n",
      "Epoch 496/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5420 - mean_squared_error: 0.5420\n",
      "Epoch 00496: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5430 - mean_squared_error: 0.5430 - val_loss: 0.7866 - val_mean_squared_error: 0.7866\n",
      "Epoch 497/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5441 - mean_squared_error: 0.5441\n",
      "Epoch 00497: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5451 - mean_squared_error: 0.5451 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 498/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5477 - mean_squared_error: 0.5477\n",
      "Epoch 00498: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 9s 2ms/sample - loss: 0.5479 - mean_squared_error: 0.5479 - val_loss: 0.7869 - val_mean_squared_error: 0.7869\n",
      "Epoch 499/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5427 - mean_squared_error: 0.5427\n",
      "Epoch 00499: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5453 - mean_squared_error: 0.5453 - val_loss: 0.7864 - val_mean_squared_error: 0.7864\n",
      "Epoch 500/500\n",
      "5000/5513 [==========================>...] - ETA: 0s - loss: 0.5450 - mean_squared_error: 0.5450\n",
      "Epoch 00500: val_loss did not improve from 0.18841\n",
      "5513/5513 [==============================] - 10s 2ms/sample - loss: 0.5443 - mean_squared_error: 0.5443 - val_loss: 0.7867 - val_mean_squared_error: 0.7867\n"
     ]
    }
   ],
   "source": [
    "history = model.fit(x_train, y_train, epochs=epochs , callbacks=callbacks_list_model,\n",
    "          validation_data=(x_val, y_val),batch_size=batch_size) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dict_keys(['loss', 'mean_squared_error', 'val_loss', 'val_mean_squared_error', 'lr'])\n"
     ]
    }
   ],
   "source": [
    "print(history.history.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.title(\"Loss (MSE)\")\n",
    "plt.plot(history.history['loss'],color = 'blue',label=\"train_loss\")\n",
    "plt.plot(history.history['val_loss'],color = 'red',label=\"val_loss\")\n",
    "plt.xlabel(\"epochs\")\n",
    "plt.ylabel(\"loss\")\n",
    "plt.legend()\n",
    "plt.savefig('loss_support_sync_data.png')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train_pred = model.predict(x_train)\n",
    "y_val_pred = model.predict(x_val)\n",
    "y_test_pred = model.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "#fix!\n",
    "def plot_compare(x, event_col):\n",
    "#     Col = {'Open':0, 'High':1, 'Low':2, 'Close':3}\n",
    "    Col = dict()\n",
    "    count = 0\n",
    "    for i, col in enumerate(event_col):\n",
    "        Col[col] = i\n",
    "    ft = Col[x]\n",
    "    plt.figure(figsize=(15, 5))\n",
    "    plt.subplot(1, 2, 1)\n",
    "\n",
    "    plt.plot(np.arange(y_train.shape[0]), y_train[:, ft], color='blue', label='train target')\n",
    "\n",
    "    plt.plot(np.arange(y_train.shape[0], y_train.shape[0] + y_val.shape[0]), y_val[:, ft], \n",
    "             color='gray', label='val target')\n",
    "    plt.plot(np.arange(y_train.shape[0] + y_val.shape[0], y_train.shape[0] + y_val.shape[0] + y_test.shape[0]),\n",
    "            y_test[:, ft], color='black', label='test target')\n",
    "    plt.plot(np.arange(y_train_pred.shape[0]), y_train_pred[:, ft],\n",
    "            color='red', label='train prediction') \n",
    "    plt.plot(np.arange(y_train_pred.shape[0], y_train_pred.shape[0] + y_val_pred.shape[0]),\n",
    "            y_val_pred[:, ft], color='orange', label='val prediction')\n",
    "    plt.plot(np.arange(y_train_pred.shape[0] + y_val_pred.shape[0],\n",
    "            y_train_pred.shape[0] + y_val_pred.shape[0] + y_test_pred.shape[0]),\n",
    "            y_test_pred[:, ft], color ='green', label='test prediction')\n",
    "    plt.title('past and future stock price :' + x)\n",
    "    plt.xlabel('Time [Days]')\n",
    "    plt.ylabel('Normalized price')\n",
    "    plt.legend(loc='best')\n",
    "\n",
    "    plt.subplot(1, 2, 2)\n",
    "    plt.plot(np.arange(y_train.shape[0], y_train.shape[0] + y_test.shape[0]),\n",
    "            y_test[:, ft], color='black', label='test target')\n",
    "    plt.plot(np.arange(y_train.shape[0], y_train.shape[0] + y_test_pred.shape[0]),\n",
    "            y_test_pred[:, ft], color='green', label='test prediction')\n",
    "    plt.title('future stock prices :' + x)\n",
    "    plt.xlabel('Time [Days]')\n",
    "    plt.ylabel('Normalized price')\n",
    "    plt.legend(loc='best')\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_compare('Close(Nikkei)', event_col)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "689/689 [==============================] - 0s 480us/sample - loss: 12.3951 - mean_squared_error: 12.3951\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[12.395078650752762, 12.395079]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.evaluate(x_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "689/689 [==============================] - 0s 545us/sample - loss: 0.7867 - mean_squared_error: 0.7867\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.7866958777686508, 0.78669584]"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.evaluate(x_val,y_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5513/5513 [==============================] - 3s 480us/sample - loss: 0.0806 - mean_squared_error: 0.0806\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.08058590460862608, 0.080585875]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.evaluate(x_train,y_train)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}