diff --git a/GITHUB_Deals_Prediction-Classification_TF.ipynb b/GITHUB_Deals_Prediction-Classification_TF.ipynb
new file mode 100644
index 0000000..9fd4f4f
--- /dev/null
+++ b/GITHUB_Deals_Prediction-Classification_TF.ipynb
@@ -0,0 +1,1840 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "id": "e4f27925-556d-4e44-b5c3-d1a1f78c34e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Dense, Dropout\n",
+    "from tensorflow.keras.callbacks import EarlyStopping\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import classification_report, confusion_matrix\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "plt.style.use('fivethirtyeight')\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "6fb173c7-b878-4ec8-8b58-6a21d3ab084d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 100 entries, 0 to 99\n",
+      "Data columns (total 6 columns):\n",
+      " #   Column         Non-Null Count  Dtype \n",
+      "---  ------         --------------  ----- \n",
+      " 0   OrderID        100 non-null    object\n",
+      " 1   OrderQuantity  100 non-null    int64 \n",
+      " 2   OrderValue     100 non-null    int64 \n",
+      " 3   Country        100 non-null    object\n",
+      " 4   Industry       100 non-null    object\n",
+      " 5   Deal Status    100 non-null    object\n",
+      "dtypes: int64(2), object(4)\n",
+      "memory usage: 4.8+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "deals= pd.read_csv('Sample_Data_Deals2.csv')\n",
+    "deals.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "1bfac3a3-045d-4eb3-8df5-91a728b99dfd",
+   "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>OrderID</th>\n",
+       "      <th>Country</th>\n",
+       "      <th>Industry</th>\n",
+       "      <th>Deal Status</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>100</td>\n",
+       "      <td>100</td>\n",
+       "      <td>100</td>\n",
+       "      <td>100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>unique</th>\n",
+       "      <td>5</td>\n",
+       "      <td>5</td>\n",
+       "      <td>7</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>top</th>\n",
+       "      <td>OD38231</td>\n",
+       "      <td>Germany</td>\n",
+       "      <td>Manufacturing</td>\n",
+       "      <td>Won</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>freq</th>\n",
+       "      <td>36</td>\n",
+       "      <td>36</td>\n",
+       "      <td>29</td>\n",
+       "      <td>54</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        OrderID  Country       Industry Deal Status\n",
+       "count       100      100            100         100\n",
+       "unique        5        5              7           2\n",
+       "top     OD38231  Germany  Manufacturing         Won\n",
+       "freq         36       36             29          54"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "deals.describe(include='O')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "id": "18e3e42c-e958-422b-8828-a7d0dbea7461",
+   "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>OrderQuantity</th>\n",
+       "      <th>OrderValue</th>\n",
+       "      <th>Country</th>\n",
+       "      <th>Industry</th>\n",
+       "      <th>Deal Status</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>371</td>\n",
+       "      <td>383</td>\n",
+       "      <td>Canada</td>\n",
+       "      <td>Technology</td>\n",
+       "      <td>Won</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>163</td>\n",
+       "      <td>121</td>\n",
+       "      <td>Canada</td>\n",
+       "      <td>Finance</td>\n",
+       "      <td>Won</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>191</td>\n",
+       "      <td>117</td>\n",
+       "      <td>Australia</td>\n",
+       "      <td>Manufacturing</td>\n",
+       "      <td>Lost</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>150</td>\n",
+       "      <td>143</td>\n",
+       "      <td>Australia</td>\n",
+       "      <td>Manufacturing</td>\n",
+       "      <td>Lost</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>165</td>\n",
+       "      <td>148</td>\n",
+       "      <td>Australia</td>\n",
+       "      <td>Manufacturing</td>\n",
+       "      <td>Lost</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   OrderQuantity  OrderValue    Country       Industry Deal Status\n",
+       "0            371         383     Canada     Technology         Won\n",
+       "1            163         121     Canada        Finance         Won\n",
+       "2            191         117  Australia  Manufacturing        Lost\n",
+       "3            150         143  Australia  Manufacturing        Lost\n",
+       "4            165         148  Australia  Manufacturing        Lost"
+      ]
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Drop Order ID\n",
+    "deals1 = pd.DataFrame(deals.iloc[:,1:])\n",
+    "deals1.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "544eb58f-ead7-4a15-8e91-8e8d0bcf199e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='Deal Status', ylabel='count'>"
+      ]
+     },
+     "execution_count": 64,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.countplot(x='Deal Status',data=deals1, hue='Deal Status', palette='flare') #Check if the dataset is well-balanced"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "id": "4b8f44ff-9f37-4f4d-8db0-90090a1a42fc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<seaborn.axisgrid.JointGrid at 0x1eaac1a5dd0>"
+      ]
+     },
+     "execution_count": 65,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 600x600 with 3 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.jointplot(x='OrderQuantity', y='OrderValue', data=deals1, hue='Deal Status', palette='flare')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "id": "e2624b25-f8dc-441f-8410-6cd1bf50ff8e",
+   "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>OrderQuantity</th>\n",
+       "      <th>OrderValue</th>\n",
+       "      <th>Country_Canada</th>\n",
+       "      <th>Country_China</th>\n",
+       "      <th>Country_France</th>\n",
+       "      <th>Country_Germany</th>\n",
+       "      <th>Industry_Finance</th>\n",
+       "      <th>Industry_Government</th>\n",
+       "      <th>Industry_Healthcare</th>\n",
+       "      <th>Industry_Manufacturing</th>\n",
+       "      <th>Industry_Retail</th>\n",
+       "      <th>Industry_Technology</th>\n",
+       "      <th>Deal Status_Won</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>371</td>\n",
+       "      <td>383</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>163</td>\n",
+       "      <td>121</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>191</td>\n",
+       "      <td>117</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>150</td>\n",
+       "      <td>143</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>165</td>\n",
+       "      <td>148</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   OrderQuantity  OrderValue  Country_Canada  Country_China  Country_France  \\\n",
+       "0            371         383               1              0               0   \n",
+       "1            163         121               1              0               0   \n",
+       "2            191         117               0              0               0   \n",
+       "3            150         143               0              0               0   \n",
+       "4            165         148               0              0               0   \n",
+       "\n",
+       "   Country_Germany  Industry_Finance  Industry_Government  \\\n",
+       "0                0                 0                    0   \n",
+       "1                0                 1                    0   \n",
+       "2                0                 0                    0   \n",
+       "3                0                 0                    0   \n",
+       "4                0                 0                    0   \n",
+       "\n",
+       "   Industry_Healthcare  Industry_Manufacturing  Industry_Retail  \\\n",
+       "0                    0                       0                0   \n",
+       "1                    0                       0                0   \n",
+       "2                    0                       1                0   \n",
+       "3                    0                       1                0   \n",
+       "4                    0                       1                0   \n",
+       "\n",
+       "   Industry_Technology  Deal Status_Won  \n",
+       "0                    1                1  \n",
+       "1                    0                1  \n",
+       "2                    0                0  \n",
+       "3                    0                0  \n",
+       "4                    0                0  "
+      ]
+     },
+     "execution_count": 66,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Encoding categorical data, drop orderID\n",
+    "deals3 = pd.get_dummies(deals1, columns=['Country', 'Industry','Deal Status'], drop_first=True,dtype=int)\n",
+    "deals3.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "id": "72c5d574-6c66-4777-8aa3-15b2b0e586ed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Create x and y datasets\n",
+    "X = deals3.drop('Deal Status_Won',axis=1).values\n",
+    "y = deals3['Deal Status_Won'].values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "e47a5176-e5b2-4e78-ac64-344102009124",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    " X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=101)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "id": "2c6ff97b-eeeb-4bb5-b456-e3922e641e1b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Transform your data\n",
+    "scaler=MinMaxScaler()\n",
+    "X_train = scaler.fit_transform(X_train)\n",
+    "X_test = scaler.transform(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 79,
+   "id": "0afcfaf4-73de-43f4-b35a-b02870e1f8ce",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(75, 12)"
+      ]
+     },
+     "execution_count": 79,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_train.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 80,
+   "id": "21faee33-c124-4c83-ab75-ebedaa4fb25d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(25, 12)"
+      ]
+     },
+     "execution_count": 80,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_test.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 102,
+   "id": "fa5f23a3-b393-46b9-b39c-4035479ea3d4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 101ms/step - loss: 0.6936 - val_loss: 0.7130\n",
+      "Epoch 2/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6840 - val_loss: 0.7122\n",
+      "Epoch 3/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.7032 - val_loss: 0.7115\n",
+      "Epoch 4/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.7038 - val_loss: 0.7111\n",
+      "Epoch 5/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 0.7037 - val_loss: 0.7104\n",
+      "Epoch 6/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.7046 - val_loss: 0.7097\n",
+      "Epoch 7/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.7403 - val_loss: 0.7097\n",
+      "Epoch 8/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6940 - val_loss: 0.7091\n",
+      "Epoch 9/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6923 - val_loss: 0.7077\n",
+      "Epoch 10/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6851 - val_loss: 0.7059\n",
+      "Epoch 11/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6998 - val_loss: 0.7040\n",
+      "Epoch 12/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.7004 - val_loss: 0.7019\n",
+      "Epoch 13/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6932 - val_loss: 0.6997\n",
+      "Epoch 14/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.7291 - val_loss: 0.6975\n",
+      "Epoch 15/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6800 - val_loss: 0.6957\n",
+      "Epoch 16/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6818 - val_loss: 0.6943\n",
+      "Epoch 17/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 0.6861 - val_loss: 0.6932\n",
+      "Epoch 18/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 0.6972 - val_loss: 0.6923\n",
+      "Epoch 19/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.7046 - val_loss: 0.6911\n",
+      "Epoch 20/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6960 - val_loss: 0.6898\n",
+      "Epoch 21/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6766 - val_loss: 0.6890\n",
+      "Epoch 22/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6714 - val_loss: 0.6883\n",
+      "Epoch 23/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.7171 - val_loss: 0.6881\n",
+      "Epoch 24/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.7015 - val_loss: 0.6876\n",
+      "Epoch 25/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 0.7077 - val_loss: 0.6875\n",
+      "Epoch 26/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6737 - val_loss: 0.6873\n",
+      "Epoch 27/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.7171 - val_loss: 0.6875\n",
+      "Epoch 28/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6840 - val_loss: 0.6877\n",
+      "Epoch 29/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.6807 - val_loss: 0.6876\n",
+      "Epoch 30/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6817 - val_loss: 0.6872\n",
+      "Epoch 31/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6628 - val_loss: 0.6866\n",
+      "Epoch 32/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6828 - val_loss: 0.6858\n",
+      "Epoch 33/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.6803 - val_loss: 0.6852\n",
+      "Epoch 34/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6875 - val_loss: 0.6845\n",
+      "Epoch 35/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.7004 - val_loss: 0.6842\n",
+      "Epoch 36/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6734 - val_loss: 0.6837\n",
+      "Epoch 37/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.6478 - val_loss: 0.6833\n",
+      "Epoch 38/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6729 - val_loss: 0.6827\n",
+      "Epoch 39/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6857 - val_loss: 0.6821\n",
+      "Epoch 40/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.6696 - val_loss: 0.6819\n",
+      "Epoch 41/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6905 - val_loss: 0.6820\n",
+      "Epoch 42/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6882 - val_loss: 0.6821\n",
+      "Epoch 43/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6646 - val_loss: 0.6822\n",
+      "Epoch 44/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6620 - val_loss: 0.6827\n",
+      "Epoch 45/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.7070 - val_loss: 0.6833\n",
+      "Epoch 46/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.7114 - val_loss: 0.6837\n",
+      "Epoch 47/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.6981 - val_loss: 0.6843\n",
+      "Epoch 48/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6738 - val_loss: 0.6849\n",
+      "Epoch 49/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6812 - val_loss: 0.6853\n",
+      "Epoch 50/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 0.6428 - val_loss: 0.6857\n",
+      "Epoch 51/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6975 - val_loss: 0.6859\n",
+      "Epoch 52/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6850 - val_loss: 0.6860\n",
+      "Epoch 53/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.6614 - val_loss: 0.6857\n",
+      "Epoch 54/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6523 - val_loss: 0.6856\n",
+      "Epoch 55/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6423 - val_loss: 0.6852\n",
+      "Epoch 56/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6701 - val_loss: 0.6850\n",
+      "Epoch 57/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6795 - val_loss: 0.6847\n",
+      "Epoch 58/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step - loss: 0.6546 - val_loss: 0.6845\n",
+      "Epoch 59/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6711 - val_loss: 0.6845\n",
+      "Epoch 60/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6635 - val_loss: 0.6849\n",
+      "Epoch 61/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6812 - val_loss: 0.6849\n",
+      "Epoch 62/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6816 - val_loss: 0.6848\n",
+      "Epoch 63/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.7026 - val_loss: 0.6846\n",
+      "Epoch 64/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6560 - val_loss: 0.6848\n",
+      "Epoch 65/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6565 - val_loss: 0.6849\n",
+      "Epoch 66/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6886 - val_loss: 0.6851\n",
+      "Epoch 67/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6915 - val_loss: 0.6854\n",
+      "Epoch 68/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6549 - val_loss: 0.6858\n",
+      "Epoch 69/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6445 - val_loss: 0.6860\n",
+      "Epoch 70/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6541 - val_loss: 0.6862\n",
+      "Epoch 71/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6755 - val_loss: 0.6864\n",
+      "Epoch 72/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6670 - val_loss: 0.6866\n",
+      "Epoch 73/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6900 - val_loss: 0.6869\n",
+      "Epoch 74/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.7008 - val_loss: 0.6872\n",
+      "Epoch 75/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6750 - val_loss: 0.6873\n",
+      "Epoch 76/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.7042 - val_loss: 0.6879\n",
+      "Epoch 77/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 0.6855 - val_loss: 0.6888\n",
+      "Epoch 78/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.6697 - val_loss: 0.6900\n",
+      "Epoch 79/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 0.6431 - val_loss: 0.6909\n",
+      "Epoch 80/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6687 - val_loss: 0.6914\n",
+      "Epoch 81/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6741 - val_loss: 0.6918\n",
+      "Epoch 82/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6571 - val_loss: 0.6920\n",
+      "Epoch 83/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6466 - val_loss: 0.6919\n",
+      "Epoch 84/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6678 - val_loss: 0.6915\n",
+      "Epoch 85/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 0.6682 - val_loss: 0.6912\n",
+      "Epoch 86/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6480 - val_loss: 0.6909\n",
+      "Epoch 87/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6802 - val_loss: 0.6908\n",
+      "Epoch 88/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 0.6637 - val_loss: 0.6906\n",
+      "Epoch 89/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - loss: 0.6691 - val_loss: 0.6901\n",
+      "Epoch 90/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6621 - val_loss: 0.6900\n",
+      "Epoch 91/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.6464 - val_loss: 0.6901\n",
+      "Epoch 92/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6648 - val_loss: 0.6904\n",
+      "Epoch 93/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6596 - val_loss: 0.6907\n",
+      "Epoch 94/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6655 - val_loss: 0.6908\n",
+      "Epoch 95/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 0.6712 - val_loss: 0.6909\n",
+      "Epoch 96/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6424 - val_loss: 0.6915\n",
+      "Epoch 97/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6562 - val_loss: 0.6921\n",
+      "Epoch 98/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6768 - val_loss: 0.6929\n",
+      "Epoch 99/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6274 - val_loss: 0.6934\n",
+      "Epoch 100/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6162 - val_loss: 0.6939\n",
+      "Epoch 101/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6571 - val_loss: 0.6944\n",
+      "Epoch 102/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 0.6637 - val_loss: 0.6944\n",
+      "Epoch 103/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.7007 - val_loss: 0.6946\n",
+      "Epoch 104/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.6239 - val_loss: 0.6947\n",
+      "Epoch 105/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.6586 - val_loss: 0.6946\n",
+      "Epoch 106/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6559 - val_loss: 0.6942\n",
+      "Epoch 107/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6361 - val_loss: 0.6942\n",
+      "Epoch 108/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 67ms/step - loss: 0.6277 - val_loss: 0.6940\n",
+      "Epoch 109/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6453 - val_loss: 0.6941\n",
+      "Epoch 110/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 0.6247 - val_loss: 0.6940\n",
+      "Epoch 111/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.6758 - val_loss: 0.6939\n",
+      "Epoch 112/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 0.6586 - val_loss: 0.6938\n",
+      "Epoch 113/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6672 - val_loss: 0.6935\n",
+      "Epoch 114/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6677 - val_loss: 0.6934\n",
+      "Epoch 115/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6402 - val_loss: 0.6934\n",
+      "Epoch 116/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6840 - val_loss: 0.6934\n",
+      "Epoch 117/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6654 - val_loss: 0.6935\n",
+      "Epoch 118/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.6694 - val_loss: 0.6939\n",
+      "Epoch 119/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6604 - val_loss: 0.6941\n",
+      "Epoch 120/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6407 - val_loss: 0.6941\n",
+      "Epoch 121/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.6688 - val_loss: 0.6942\n",
+      "Epoch 122/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 0.6446 - val_loss: 0.6944\n",
+      "Epoch 123/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.6684 - val_loss: 0.6940\n",
+      "Epoch 124/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6752 - val_loss: 0.6940\n",
+      "Epoch 125/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6570 - val_loss: 0.6939\n",
+      "Epoch 126/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6515 - val_loss: 0.6937\n",
+      "Epoch 127/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6625 - val_loss: 0.6939\n",
+      "Epoch 128/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6064 - val_loss: 0.6942\n",
+      "Epoch 129/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6294 - val_loss: 0.6945\n",
+      "Epoch 130/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 0.6538 - val_loss: 0.6949\n",
+      "Epoch 131/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6286 - val_loss: 0.6953\n",
+      "Epoch 132/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6564 - val_loss: 0.6956\n",
+      "Epoch 133/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6342 - val_loss: 0.6954\n",
+      "Epoch 134/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6415 - val_loss: 0.6953\n",
+      "Epoch 135/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 0.6466 - val_loss: 0.6954\n",
+      "Epoch 136/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.6211 - val_loss: 0.6961\n",
+      "Epoch 137/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6666 - val_loss: 0.6969\n",
+      "Epoch 138/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5987 - val_loss: 0.6977\n",
+      "Epoch 139/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5919 - val_loss: 0.6984\n",
+      "Epoch 140/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6546 - val_loss: 0.6988\n",
+      "Epoch 141/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - loss: 0.6107 - val_loss: 0.6991\n",
+      "Epoch 142/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.6230 - val_loss: 0.6993\n",
+      "Epoch 143/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6547 - val_loss: 0.6993\n",
+      "Epoch 144/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6564 - val_loss: 0.6986\n",
+      "Epoch 145/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6190 - val_loss: 0.6982\n",
+      "Epoch 146/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6035 - val_loss: 0.6985\n",
+      "Epoch 147/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6642 - val_loss: 0.6992\n",
+      "Epoch 148/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6075 - val_loss: 0.6999\n",
+      "Epoch 149/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 0.6150 - val_loss: 0.7011\n",
+      "Epoch 150/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6375 - val_loss: 0.7022\n",
+      "Epoch 151/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 0.6465 - val_loss: 0.7030\n",
+      "Epoch 152/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6058 - val_loss: 0.7036\n",
+      "Epoch 153/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6199 - val_loss: 0.7043\n",
+      "Epoch 154/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6084 - val_loss: 0.7052\n",
+      "Epoch 155/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6312 - val_loss: 0.7059\n",
+      "Epoch 156/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6122 - val_loss: 0.7067\n",
+      "Epoch 157/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6373 - val_loss: 0.7072\n",
+      "Epoch 158/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6555 - val_loss: 0.7078\n",
+      "Epoch 159/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6318 - val_loss: 0.7081\n",
+      "Epoch 160/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6155 - val_loss: 0.7087\n",
+      "Epoch 161/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.5988 - val_loss: 0.7090\n",
+      "Epoch 162/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.6786 - val_loss: 0.7090\n",
+      "Epoch 163/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6040 - val_loss: 0.7089\n",
+      "Epoch 164/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5921 - val_loss: 0.7091\n",
+      "Epoch 165/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6616 - val_loss: 0.7101\n",
+      "Epoch 166/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6562 - val_loss: 0.7109\n",
+      "Epoch 167/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6011 - val_loss: 0.7115\n",
+      "Epoch 168/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 0.6163 - val_loss: 0.7124\n",
+      "Epoch 169/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6103 - val_loss: 0.7138\n",
+      "Epoch 170/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6428 - val_loss: 0.7149\n",
+      "Epoch 171/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6313 - val_loss: 0.7168\n",
+      "Epoch 172/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6281 - val_loss: 0.7185\n",
+      "Epoch 173/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6160 - val_loss: 0.7202\n",
+      "Epoch 174/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.5736 - val_loss: 0.7217\n",
+      "Epoch 175/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.6144 - val_loss: 0.7231\n",
+      "Epoch 176/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.6237 - val_loss: 0.7239\n",
+      "Epoch 177/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6538 - val_loss: 0.7242\n",
+      "Epoch 178/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6207 - val_loss: 0.7243\n",
+      "Epoch 179/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5994 - val_loss: 0.7242\n",
+      "Epoch 180/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.6043 - val_loss: 0.7240\n",
+      "Epoch 181/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5829 - val_loss: 0.7234\n",
+      "Epoch 182/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6776 - val_loss: 0.7231\n",
+      "Epoch 183/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6268 - val_loss: 0.7230\n",
+      "Epoch 184/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6266 - val_loss: 0.7236\n",
+      "Epoch 185/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6344 - val_loss: 0.7244\n",
+      "Epoch 186/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.6277 - val_loss: 0.7254\n",
+      "Epoch 187/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6351 - val_loss: 0.7257\n",
+      "Epoch 188/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.6416 - val_loss: 0.7258\n",
+      "Epoch 189/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6591 - val_loss: 0.7259\n",
+      "Epoch 190/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6020 - val_loss: 0.7258\n",
+      "Epoch 191/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.6492 - val_loss: 0.7262\n",
+      "Epoch 192/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6095 - val_loss: 0.7263\n",
+      "Epoch 193/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6330 - val_loss: 0.7264\n",
+      "Epoch 194/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.5950 - val_loss: 0.7264\n",
+      "Epoch 195/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5766 - val_loss: 0.7266\n",
+      "Epoch 196/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.6531 - val_loss: 0.7269\n",
+      "Epoch 197/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.5883 - val_loss: 0.7281\n",
+      "Epoch 198/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6571 - val_loss: 0.7298\n",
+      "Epoch 199/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.6384 - val_loss: 0.7309\n",
+      "Epoch 200/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5798 - val_loss: 0.7320\n",
+      "Epoch 201/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.6156 - val_loss: 0.7332\n",
+      "Epoch 202/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.6052 - val_loss: 0.7342\n",
+      "Epoch 203/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 64ms/step - loss: 0.6063 - val_loss: 0.7350\n",
+      "Epoch 204/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.5937 - val_loss: 0.7362\n",
+      "Epoch 205/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5890 - val_loss: 0.7378\n",
+      "Epoch 206/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.6105 - val_loss: 0.7395\n",
+      "Epoch 207/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 68ms/step - loss: 0.6444 - val_loss: 0.7408\n",
+      "Epoch 208/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.6282 - val_loss: 0.7421\n",
+      "Epoch 209/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6339 - val_loss: 0.7429\n",
+      "Epoch 210/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.6050 - val_loss: 0.7437\n",
+      "Epoch 211/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 0.6155 - val_loss: 0.7449\n",
+      "Epoch 212/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6290 - val_loss: 0.7458\n",
+      "Epoch 213/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.5687 - val_loss: 0.7472\n",
+      "Epoch 214/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.5904 - val_loss: 0.7477\n",
+      "Epoch 215/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6519 - val_loss: 0.7474\n",
+      "Epoch 216/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.6136 - val_loss: 0.7479\n",
+      "Epoch 217/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 0.6096 - val_loss: 0.7486\n",
+      "Epoch 218/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5763 - val_loss: 0.7489\n",
+      "Epoch 219/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6171 - val_loss: 0.7496\n",
+      "Epoch 220/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6792 - val_loss: 0.7502\n",
+      "Epoch 221/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.5807 - val_loss: 0.7509\n",
+      "Epoch 222/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6323 - val_loss: 0.7514\n",
+      "Epoch 223/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 0.5773 - val_loss: 0.7509\n",
+      "Epoch 224/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.6303 - val_loss: 0.7505\n",
+      "Epoch 225/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.6315 - val_loss: 0.7504\n",
+      "Epoch 226/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6105 - val_loss: 0.7502\n",
+      "Epoch 227/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6104 - val_loss: 0.7487\n",
+      "Epoch 228/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.5937 - val_loss: 0.7483\n",
+      "Epoch 229/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6121 - val_loss: 0.7479\n",
+      "Epoch 230/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6079 - val_loss: 0.7482\n",
+      "Epoch 231/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.5900 - val_loss: 0.7486\n",
+      "Epoch 232/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 0.5634 - val_loss: 0.7488\n",
+      "Epoch 233/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.6345 - val_loss: 0.7489\n",
+      "Epoch 234/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 0.6454 - val_loss: 0.7493\n",
+      "Epoch 235/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5724 - val_loss: 0.7504\n",
+      "Epoch 236/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6244 - val_loss: 0.7520\n",
+      "Epoch 237/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 0.5890 - val_loss: 0.7536\n",
+      "Epoch 238/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 67ms/step - loss: 0.6264 - val_loss: 0.7551\n",
+      "Epoch 239/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.5998 - val_loss: 0.7572\n",
+      "Epoch 240/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 0.6040 - val_loss: 0.7601\n",
+      "Epoch 241/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 0.5819 - val_loss: 0.7628\n",
+      "Epoch 242/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 0.5980 - val_loss: 0.7653\n",
+      "Epoch 243/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.6082 - val_loss: 0.7674\n",
+      "Epoch 244/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - loss: 0.5388 - val_loss: 0.7690\n",
+      "Epoch 245/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - loss: 0.6049 - val_loss: 0.7703\n",
+      "Epoch 246/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.5778 - val_loss: 0.7720\n",
+      "Epoch 247/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.5892 - val_loss: 0.7728\n",
+      "Epoch 248/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.5804 - val_loss: 0.7736\n",
+      "Epoch 249/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 0.5601 - val_loss: 0.7747\n",
+      "Epoch 250/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 0.6022 - val_loss: 0.7759\n",
+      "Epoch 251/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.5693 - val_loss: 0.7782\n",
+      "Epoch 252/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 0.5858 - val_loss: 0.7800\n",
+      "Epoch 253/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 0.5563 - val_loss: 0.7809\n",
+      "Epoch 254/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.5708 - val_loss: 0.7819\n",
+      "Epoch 255/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 65ms/step - loss: 0.6014 - val_loss: 0.7826\n",
+      "Epoch 256/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 0.5747 - val_loss: 0.7841\n",
+      "Epoch 257/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.5825 - val_loss: 0.7863\n",
+      "Epoch 258/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.5729 - val_loss: 0.7881\n",
+      "Epoch 259/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 70ms/step - loss: 0.6337 - val_loss: 0.7895\n",
+      "Epoch 260/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5870 - val_loss: 0.7896\n",
+      "Epoch 261/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.6190 - val_loss: 0.7894\n",
+      "Epoch 262/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.5690 - val_loss: 0.7890\n",
+      "Epoch 263/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 67ms/step - loss: 0.6066 - val_loss: 0.7871\n",
+      "Epoch 264/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 0.5851 - val_loss: 0.7855\n",
+      "Epoch 265/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5783 - val_loss: 0.7844\n",
+      "Epoch 266/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 74ms/step - loss: 0.6019 - val_loss: 0.7834\n",
+      "Epoch 267/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.6063 - val_loss: 0.7822\n",
+      "Epoch 268/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5702 - val_loss: 0.7814\n",
+      "Epoch 269/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5861 - val_loss: 0.7812\n",
+      "Epoch 270/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.6104 - val_loss: 0.7819\n",
+      "Epoch 271/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step - loss: 0.5539 - val_loss: 0.7828\n",
+      "Epoch 272/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.5874 - val_loss: 0.7836\n",
+      "Epoch 273/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 70ms/step - loss: 0.5372 - val_loss: 0.7848\n",
+      "Epoch 274/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.5918 - val_loss: 0.7863\n",
+      "Epoch 275/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step - loss: 0.5958 - val_loss: 0.7877\n",
+      "Epoch 276/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6000 - val_loss: 0.7885\n",
+      "Epoch 277/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.5711 - val_loss: 0.7895\n",
+      "Epoch 278/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5570 - val_loss: 0.7910\n",
+      "Epoch 279/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.5632 - val_loss: 0.7926\n",
+      "Epoch 280/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5439 - val_loss: 0.7934\n",
+      "Epoch 281/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.5246 - val_loss: 0.7948\n",
+      "Epoch 282/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.5331 - val_loss: 0.7967\n",
+      "Epoch 283/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5227 - val_loss: 0.7985\n",
+      "Epoch 284/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5717 - val_loss: 0.8002\n",
+      "Epoch 285/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.5791 - val_loss: 0.8018\n",
+      "Epoch 286/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 0.5669 - val_loss: 0.8036\n",
+      "Epoch 287/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5714 - val_loss: 0.8041\n",
+      "Epoch 288/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 68ms/step - loss: 0.5695 - val_loss: 0.8061\n",
+      "Epoch 289/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.6090 - val_loss: 0.8088\n",
+      "Epoch 290/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.5506 - val_loss: 0.8117\n",
+      "Epoch 291/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.5842 - val_loss: 0.8140\n",
+      "Epoch 292/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.5567 - val_loss: 0.8162\n",
+      "Epoch 293/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5589 - val_loss: 0.8182\n",
+      "Epoch 294/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5689 - val_loss: 0.8194\n",
+      "Epoch 295/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.5727 - val_loss: 0.8197\n",
+      "Epoch 296/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.5903 - val_loss: 0.8212\n",
+      "Epoch 297/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.5697 - val_loss: 0.8225\n",
+      "Epoch 298/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5465 - val_loss: 0.8234\n",
+      "Epoch 299/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.5711 - val_loss: 0.8246\n",
+      "Epoch 300/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6177 - val_loss: 0.8252\n",
+      "Epoch 301/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5603 - val_loss: 0.8252\n",
+      "Epoch 302/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.5683 - val_loss: 0.8244\n",
+      "Epoch 303/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.5348 - val_loss: 0.8239\n",
+      "Epoch 304/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.6031 - val_loss: 0.8243\n",
+      "Epoch 305/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.5747 - val_loss: 0.8251\n",
+      "Epoch 306/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5440 - val_loss: 0.8261\n",
+      "Epoch 307/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5462 - val_loss: 0.8274\n",
+      "Epoch 308/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 64ms/step - loss: 0.5701 - val_loss: 0.8290\n",
+      "Epoch 309/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.6173 - val_loss: 0.8300\n",
+      "Epoch 310/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5768 - val_loss: 0.8303\n",
+      "Epoch 311/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.5406 - val_loss: 0.8310\n",
+      "Epoch 312/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5750 - val_loss: 0.8318\n",
+      "Epoch 313/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - loss: 0.5887 - val_loss: 0.8328\n",
+      "Epoch 314/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.5539 - val_loss: 0.8341\n",
+      "Epoch 315/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step - loss: 0.5702 - val_loss: 0.8353\n",
+      "Epoch 316/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5666 - val_loss: 0.8369\n",
+      "Epoch 317/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.5836 - val_loss: 0.8376\n",
+      "Epoch 318/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.5444 - val_loss: 0.8394\n",
+      "Epoch 319/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - loss: 0.5934 - val_loss: 0.8402\n",
+      "Epoch 320/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 78ms/step - loss: 0.5521 - val_loss: 0.8416\n",
+      "Epoch 321/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5435 - val_loss: 0.8432\n",
+      "Epoch 322/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.5560 - val_loss: 0.8446\n",
+      "Epoch 323/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 0.5570 - val_loss: 0.8464\n",
+      "Epoch 324/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 77ms/step - loss: 0.5638 - val_loss: 0.8474\n",
+      "Epoch 325/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.5650 - val_loss: 0.8492\n",
+      "Epoch 326/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.5741 - val_loss: 0.8512\n",
+      "Epoch 327/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - loss: 0.5459 - val_loss: 0.8535\n",
+      "Epoch 328/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 72ms/step - loss: 0.5985 - val_loss: 0.8560\n",
+      "Epoch 329/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.5342 - val_loss: 0.8591\n",
+      "Epoch 330/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5983 - val_loss: 0.8618\n",
+      "Epoch 331/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.5675 - val_loss: 0.8637\n",
+      "Epoch 332/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 65ms/step - loss: 0.5534 - val_loss: 0.8648\n",
+      "Epoch 333/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5268 - val_loss: 0.8663\n",
+      "Epoch 334/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.5759 - val_loss: 0.8682\n",
+      "Epoch 335/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5203 - val_loss: 0.8695\n",
+      "Epoch 336/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.5378 - val_loss: 0.8705\n",
+      "Epoch 337/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - loss: 0.5851 - val_loss: 0.8713\n",
+      "Epoch 338/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.5506 - val_loss: 0.8726\n",
+      "Epoch 339/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.6133 - val_loss: 0.8727\n",
+      "Epoch 340/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.5881 - val_loss: 0.8729\n",
+      "Epoch 341/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step - loss: 0.5538 - val_loss: 0.8721\n",
+      "Epoch 342/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.4951 - val_loss: 0.8704\n",
+      "Epoch 343/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 0.5144 - val_loss: 0.8686\n",
+      "Epoch 344/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.5428 - val_loss: 0.8689\n",
+      "Epoch 345/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.6023 - val_loss: 0.8704\n",
+      "Epoch 346/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - loss: 0.5811 - val_loss: 0.8715\n",
+      "Epoch 347/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 64ms/step - loss: 0.5588 - val_loss: 0.8738\n",
+      "Epoch 348/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.5945 - val_loss: 0.8754\n",
+      "Epoch 349/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.5626 - val_loss: 0.8771\n",
+      "Epoch 350/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 0.5534 - val_loss: 0.8787\n",
+      "Epoch 351/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5614 - val_loss: 0.8803\n",
+      "Epoch 352/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5314 - val_loss: 0.8816\n",
+      "Epoch 353/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5601 - val_loss: 0.8831\n",
+      "Epoch 354/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.5517 - val_loss: 0.8854\n",
+      "Epoch 355/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.5496 - val_loss: 0.8883\n",
+      "Epoch 356/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.4747 - val_loss: 0.8913\n",
+      "Epoch 357/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5385 - val_loss: 0.8942\n",
+      "Epoch 358/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.5082 - val_loss: 0.8969\n",
+      "Epoch 359/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - loss: 0.5112 - val_loss: 0.8996\n",
+      "Epoch 360/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - loss: 0.5074 - val_loss: 0.9013\n",
+      "Epoch 361/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - loss: 0.5335 - val_loss: 0.8995\n",
+      "Epoch 362/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 0.5315 - val_loss: 0.8971\n",
+      "Epoch 363/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - loss: 0.5786 - val_loss: 0.8953\n",
+      "Epoch 364/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - loss: 0.5244 - val_loss: 0.8947\n",
+      "Epoch 365/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step - loss: 0.5360 - val_loss: 0.8931\n",
+      "Epoch 366/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 0.5437 - val_loss: 0.8910\n",
+      "Epoch 367/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 0.5531 - val_loss: 0.8898\n",
+      "Epoch 368/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 70ms/step - loss: 0.5695 - val_loss: 0.8895\n",
+      "Epoch 369/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 0.5345 - val_loss: 0.8898\n",
+      "Epoch 370/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.5086 - val_loss: 0.8904\n",
+      "Epoch 371/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 0.5532 - val_loss: 0.8909\n",
+      "Epoch 372/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step - loss: 0.5663 - val_loss: 0.8909\n",
+      "Epoch 373/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 65ms/step - loss: 0.5312 - val_loss: 0.8923\n",
+      "Epoch 374/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.5902 - val_loss: 0.8924\n",
+      "Epoch 375/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - loss: 0.5536 - val_loss: 0.8914\n",
+      "Epoch 376/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - loss: 0.5538 - val_loss: 0.8904\n",
+      "Epoch 377/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.4994 - val_loss: 0.8906\n",
+      "Epoch 378/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 0.5493 - val_loss: 0.8912\n",
+      "Epoch 379/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.5464 - val_loss: 0.8931\n",
+      "Epoch 380/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.5178 - val_loss: 0.8956\n",
+      "Epoch 381/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 0.5566 - val_loss: 0.8981\n",
+      "Epoch 382/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5656 - val_loss: 0.9008\n",
+      "Epoch 383/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 72ms/step - loss: 0.5474 - val_loss: 0.9045\n",
+      "Epoch 384/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step - loss: 0.5056 - val_loss: 0.9097\n",
+      "Epoch 385/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 0.5369 - val_loss: 0.9144\n",
+      "Epoch 386/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.5471 - val_loss: 0.9181\n",
+      "Epoch 387/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 0.5517 - val_loss: 0.9207\n",
+      "Epoch 388/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 76ms/step - loss: 0.5050 - val_loss: 0.9232\n",
+      "Epoch 389/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 0.5221 - val_loss: 0.9268\n",
+      "Epoch 390/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - loss: 0.5823 - val_loss: 0.9300\n",
+      "Epoch 391/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - loss: 0.5136 - val_loss: 0.9340\n",
+      "Epoch 392/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 76ms/step - loss: 0.5422 - val_loss: 0.9386\n",
+      "Epoch 393/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 0.5365 - val_loss: 0.9440\n",
+      "Epoch 394/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.5558 - val_loss: 0.9480\n",
+      "Epoch 395/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.5554 - val_loss: 0.9505\n",
+      "Epoch 396/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step - loss: 0.4832 - val_loss: 0.9517\n",
+      "Epoch 397/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - loss: 0.5383 - val_loss: 0.9524\n",
+      "Epoch 398/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - loss: 0.5539 - val_loss: 0.9520\n",
+      "Epoch 399/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 0.5924 - val_loss: 0.9533\n",
+      "Epoch 400/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 70ms/step - loss: 0.5595 - val_loss: 0.9555\n",
+      "Epoch 401/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.5553 - val_loss: 0.9578\n",
+      "Epoch 402/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.5471 - val_loss: 0.9603\n",
+      "Epoch 403/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5433 - val_loss: 0.9619\n",
+      "Epoch 404/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.5032 - val_loss: 0.9618\n",
+      "Epoch 405/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - loss: 0.5251 - val_loss: 0.9636\n",
+      "Epoch 406/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.5520 - val_loss: 0.9657\n",
+      "Epoch 407/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.5153 - val_loss: 0.9688\n",
+      "Epoch 408/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.5235 - val_loss: 0.9711\n",
+      "Epoch 409/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 0.5226 - val_loss: 0.9724\n",
+      "Epoch 410/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - loss: 0.5587 - val_loss: 0.9726\n",
+      "Epoch 411/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 0.5330 - val_loss: 0.9723\n",
+      "Epoch 412/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.4812 - val_loss: 0.9728\n",
+      "Epoch 413/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.5076 - val_loss: 0.9742\n",
+      "Epoch 414/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.5490 - val_loss: 0.9762\n",
+      "Epoch 415/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step - loss: 0.5184 - val_loss: 0.9785\n",
+      "Epoch 416/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.5497 - val_loss: 0.9812\n",
+      "Epoch 417/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - loss: 0.4723 - val_loss: 0.9835\n",
+      "Epoch 418/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.5271 - val_loss: 0.9852\n",
+      "Epoch 419/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 72ms/step - loss: 0.5230 - val_loss: 0.9851\n",
+      "Epoch 420/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 78ms/step - loss: 0.5226 - val_loss: 0.9855\n",
+      "Epoch 421/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 0.5292 - val_loss: 0.9864\n",
+      "Epoch 422/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 72ms/step - loss: 0.5873 - val_loss: 0.9880\n",
+      "Epoch 423/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.4991 - val_loss: 0.9902\n",
+      "Epoch 424/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 0.5340 - val_loss: 0.9931\n",
+      "Epoch 425/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.5206 - val_loss: 0.9959\n",
+      "Epoch 426/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - loss: 0.4959 - val_loss: 0.9968\n",
+      "Epoch 427/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 73ms/step - loss: 0.5372 - val_loss: 0.9955\n",
+      "Epoch 428/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - loss: 0.4912 - val_loss: 0.9935\n",
+      "Epoch 429/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.5810 - val_loss: 0.9906\n",
+      "Epoch 430/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.5006 - val_loss: 0.9884\n",
+      "Epoch 431/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.4607 - val_loss: 0.9891\n",
+      "Epoch 432/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 0.5359 - val_loss: 0.9925\n",
+      "Epoch 433/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5215 - val_loss: 0.9955\n",
+      "Epoch 434/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5234 - val_loss: 0.9970\n",
+      "Epoch 435/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5299 - val_loss: 0.9987\n",
+      "Epoch 436/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.4678 - val_loss: 1.0018\n",
+      "Epoch 437/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.4941 - val_loss: 1.0044\n",
+      "Epoch 438/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5348 - val_loss: 1.0054\n",
+      "Epoch 439/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.4842 - val_loss: 1.0061\n",
+      "Epoch 440/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.4861 - val_loss: 1.0071\n",
+      "Epoch 441/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.5370 - val_loss: 1.0077\n",
+      "Epoch 442/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 0.5422 - val_loss: 1.0095\n",
+      "Epoch 443/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.4616 - val_loss: 1.0118\n",
+      "Epoch 444/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.5670 - val_loss: 1.0137\n",
+      "Epoch 445/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5471 - val_loss: 1.0155\n",
+      "Epoch 446/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 67ms/step - loss: 0.4937 - val_loss: 1.0172\n",
+      "Epoch 447/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 0.4902 - val_loss: 1.0196\n",
+      "Epoch 448/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5483 - val_loss: 1.0213\n",
+      "Epoch 449/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - loss: 0.5081 - val_loss: 1.0223\n",
+      "Epoch 450/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - loss: 0.5626 - val_loss: 1.0237\n",
+      "Epoch 451/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.4884 - val_loss: 1.0257\n",
+      "Epoch 452/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.5464 - val_loss: 1.0253\n",
+      "Epoch 453/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - loss: 0.4504 - val_loss: 1.0260\n",
+      "Epoch 454/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5163 - val_loss: 1.0272\n",
+      "Epoch 455/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.4797 - val_loss: 1.0290\n",
+      "Epoch 456/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.4973 - val_loss: 1.0317\n",
+      "Epoch 457/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5505 - val_loss: 1.0355\n",
+      "Epoch 458/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.5787 - val_loss: 1.0366\n",
+      "Epoch 459/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5288 - val_loss: 1.0374\n",
+      "Epoch 460/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.4451 - val_loss: 1.0392\n",
+      "Epoch 461/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.4802 - val_loss: 1.0408\n",
+      "Epoch 462/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.5111 - val_loss: 1.0413\n",
+      "Epoch 463/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.5093 - val_loss: 1.0422\n",
+      "Epoch 464/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 0.5845 - val_loss: 1.0421\n",
+      "Epoch 465/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5444 - val_loss: 1.0414\n",
+      "Epoch 466/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.4944 - val_loss: 1.0416\n",
+      "Epoch 467/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 0.5027 - val_loss: 1.0421\n",
+      "Epoch 468/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 68ms/step - loss: 0.5195 - val_loss: 1.0428\n",
+      "Epoch 469/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.4827 - val_loss: 1.0449\n",
+      "Epoch 470/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.4850 - val_loss: 1.0475\n",
+      "Epoch 471/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5028 - val_loss: 1.0502\n",
+      "Epoch 472/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step - loss: 0.5370 - val_loss: 1.0523\n",
+      "Epoch 473/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.5038 - val_loss: 1.0553\n",
+      "Epoch 474/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - loss: 0.5261 - val_loss: 1.0588\n",
+      "Epoch 475/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - loss: 0.4654 - val_loss: 1.0634\n",
+      "Epoch 476/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 0.5370 - val_loss: 1.0690\n",
+      "Epoch 477/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.5461 - val_loss: 1.0749\n",
+      "Epoch 478/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5044 - val_loss: 1.0811\n",
+      "Epoch 479/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5082 - val_loss: 1.0864\n",
+      "Epoch 480/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.5097 - val_loss: 1.0902\n",
+      "Epoch 481/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.4665 - val_loss: 1.0929\n",
+      "Epoch 482/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.4822 - val_loss: 1.0947\n",
+      "Epoch 483/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5269 - val_loss: 1.0968\n",
+      "Epoch 484/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 64ms/step - loss: 0.5638 - val_loss: 1.0970\n",
+      "Epoch 485/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5142 - val_loss: 1.0978\n",
+      "Epoch 486/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 0.4943 - val_loss: 1.0990\n",
+      "Epoch 487/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.4550 - val_loss: 1.1013\n",
+      "Epoch 488/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.5389 - val_loss: 1.1026\n",
+      "Epoch 489/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.4875 - val_loss: 1.1036\n",
+      "Epoch 490/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - loss: 0.5026 - val_loss: 1.1040\n",
+      "Epoch 491/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.4723 - val_loss: 1.1055\n",
+      "Epoch 492/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 0.4616 - val_loss: 1.1084\n",
+      "Epoch 493/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - loss: 0.5326 - val_loss: 1.1114\n",
+      "Epoch 494/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 0.4789 - val_loss: 1.1145\n",
+      "Epoch 495/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5342 - val_loss: 1.1166\n",
+      "Epoch 496/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 0.5232 - val_loss: 1.1185\n",
+      "Epoch 497/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - loss: 0.4841 - val_loss: 1.1197\n",
+      "Epoch 498/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - loss: 0.5530 - val_loss: 1.1190\n",
+      "Epoch 499/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.5412 - val_loss: 1.1192\n",
+      "Epoch 500/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 0.5082 - val_loss: 1.1214\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.src.callbacks.history.History at 0x1eab7c54390>"
+      ]
+     },
+     "execution_count": 102,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Define model\n",
+    "model=Sequential()\n",
+    "model.add(Dense(30,activation='relu'))\n",
+    "model.add(Dropout(0.5)) #prevents overfitting\n",
+    "model.add(Dense(15,activation='relu'))\n",
+    "model.add(Dropout(0.5))  #prevents overfitting\n",
+    "#BINARY CLASSIFICATION USES SIGMOID ACTIVATION FUNCTION FOR OUTPUT LAYER\n",
+    "model.add(Dense(1,activation='sigmoid'))  #output layer\n",
+    "#Compile\n",
+    "model.compile(loss='binary_crossentropy', optimizer='adam')\n",
+    "\n",
+    "#Model Fitting\n",
+    "model.fit(X_train, y_train, epochs=500, validation_data=(X_test,y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 103,
+   "id": "0915c338-37b6-4c1a-936f-38c7106df6bc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: >"
+      ]
+     },
+     "execution_count": 103,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "losses= pd.DataFrame(model.history.history)\n",
+    "losses.plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "id": "f49a18cd-7ef0-4cf5-a191-3a14b51d171d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Early stopping to prevent overfitting\n",
+    "early_stop = EarlyStopping(monitor='val_loss',mode='min',verbose=1,patience=25)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "id": "d5d4e73f-15ff-4567-bf82-0bbacae9dc42",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 82ms/step - loss: 0.5082 - val_loss: 1.1252\n",
+      "Epoch 2/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 0.5229 - val_loss: 1.1291\n",
+      "Epoch 3/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5226 - val_loss: 1.1325\n",
+      "Epoch 4/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 0.5404 - val_loss: 1.1343\n",
+      "Epoch 5/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.5426 - val_loss: 1.1365\n",
+      "Epoch 6/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5217 - val_loss: 1.1388\n",
+      "Epoch 7/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.4785 - val_loss: 1.1408\n",
+      "Epoch 8/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 0.5067 - val_loss: 1.1409\n",
+      "Epoch 9/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5035 - val_loss: 1.1405\n",
+      "Epoch 10/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.5422 - val_loss: 1.1389\n",
+      "Epoch 11/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step - loss: 0.4645 - val_loss: 1.1391\n",
+      "Epoch 12/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 68ms/step - loss: 0.5191 - val_loss: 1.1402\n",
+      "Epoch 13/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.4928 - val_loss: 1.1417\n",
+      "Epoch 14/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.4637 - val_loss: 1.1442\n",
+      "Epoch 15/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - loss: 0.4847 - val_loss: 1.1471\n",
+      "Epoch 16/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.4921 - val_loss: 1.1498\n",
+      "Epoch 17/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 0.5273 - val_loss: 1.1508\n",
+      "Epoch 18/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.4736 - val_loss: 1.1510\n",
+      "Epoch 19/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 0.5577 - val_loss: 1.1504\n",
+      "Epoch 20/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.4605 - val_loss: 1.1491\n",
+      "Epoch 21/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 0.4902 - val_loss: 1.1475\n",
+      "Epoch 22/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5107 - val_loss: 1.1482\n",
+      "Epoch 23/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step - loss: 0.4831 - val_loss: 1.1500\n",
+      "Epoch 24/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - loss: 0.5182 - val_loss: 1.1520\n",
+      "Epoch 25/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5136 - val_loss: 1.1547\n",
+      "Epoch 26/500\n",
+      "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 0.5138 - val_loss: 1.1584\n",
+      "Epoch 26: early stopping\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.src.callbacks.history.History at 0x1eab7ed9f50>"
+      ]
+     },
+     "execution_count": 105,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Model fit WITH callbacks\n",
+    "model.fit(X_train, y_train, epochs=500, validation_data=(X_test,y_test), callbacks=[early_stop])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "id": "8186078d-9fdf-400f-8321-ce16339938b3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: >"
+      ]
+     },
+     "execution_count": 106,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Check val loss\n",
+    "losses2= pd.DataFrame(model.history.history)\n",
+    "losses2.plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 113,
+   "id": "10d56f7c-fe3b-4a9c-a2c2-b8184f3b755d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step\n",
+      "[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "predictions = model.predict(X_test)\n",
+    "classes_x=np.argmax(predictions,axis=1)\n",
+    "print(classes_x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 114,
+   "id": "108c542c-cc9c-449f-bcdb-ee74faed5f66",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       0.44      1.00      0.61        11\n",
+      "           1       0.00      0.00      0.00        14\n",
+      "\n",
+      "    accuracy                           0.44        25\n",
+      "   macro avg       0.22      0.50      0.31        25\n",
+      "weighted avg       0.19      0.44      0.27        25\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\neogi\\Documents\\Python_venv\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
+      "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
+      "C:\\Users\\neogi\\Documents\\Python_venv\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
+      "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
+      "C:\\Users\\neogi\\Documents\\Python_venv\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
+      "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(classification_report(y_test,classes_x))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 115,
+   "id": "ceae6613-1f43-4360-a69c-45224a04018b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[11  0]\n",
+      " [14  0]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(confusion_matrix(y_test,classes_x))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/GITHUB_Deals_Prediction-Viz.ipynb b/GITHUB_Deals_Prediction-Viz.ipynb
new file mode 100644
index 0000000..ec262fc
--- /dev/null
+++ b/GITHUB_Deals_Prediction-Viz.ipynb
@@ -0,0 +1,429 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e4f27925-556d-4e44-b5c3-d1a1f78c34e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import seaborn as sns\n",
+    "%matplotlib inline\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "plt.style.use('ggplot')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6fb173c7-b878-4ec8-8b58-6a21d3ab084d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 100 entries, 0 to 99\n",
+      "Data columns (total 6 columns):\n",
+      " #   Column         Non-Null Count  Dtype \n",
+      "---  ------         --------------  ----- \n",
+      " 0   OrderID        100 non-null    object\n",
+      " 1   OrderQuantity  100 non-null    int64 \n",
+      " 2   OrderValue     100 non-null    int64 \n",
+      " 3   Country        100 non-null    object\n",
+      " 4   Industry       100 non-null    object\n",
+      " 5   Deal Status    100 non-null    object\n",
+      "dtypes: int64(2), object(4)\n",
+      "memory usage: 4.8+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "deals= pd.read_csv('Sample_Data_Deals2.csv')\n",
+    "deals.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "264cb739-a36e-475d-98c5-9fcc0b97394e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "OrderQuantity    185.16\n",
+       "OrderValue       178.50\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "deals.mean(numeric_only=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8bd3577a-09c2-4893-8fb5-6d3382100e62",
+   "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>OrderID</th>\n",
+       "      <th>Country</th>\n",
+       "      <th>Industry</th>\n",
+       "      <th>Deal Status</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>100</td>\n",
+       "      <td>100</td>\n",
+       "      <td>100</td>\n",
+       "      <td>100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>unique</th>\n",
+       "      <td>5</td>\n",
+       "      <td>5</td>\n",
+       "      <td>7</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>top</th>\n",
+       "      <td>OD38231</td>\n",
+       "      <td>Germany</td>\n",
+       "      <td>Manufacturing</td>\n",
+       "      <td>Won</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>freq</th>\n",
+       "      <td>36</td>\n",
+       "      <td>36</td>\n",
+       "      <td>29</td>\n",
+       "      <td>54</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        OrderID  Country       Industry Deal Status\n",
+       "count       100      100            100         100\n",
+       "unique        5        5              7           2\n",
+       "top     OD38231  Germany  Manufacturing         Won\n",
+       "freq         36       36             29          54"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "deals.describe(include='O')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "b35ff8b0-f80b-4200-b43a-8e8c43648b4f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='Deal Status'>"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Count the total number of deals in each stage, horizontal bar plot\n",
+    "deals['Deal Status'].value_counts().sort_index(ascending=False).plot(kind='bar', colormap='flare', alpha=0.6)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "ea47103d-99b4-4b6a-850b-fa9b00334a18",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Group deals by Country and OrderValue\n",
+    "gbo2=deals.groupby('Country')['OrderValue']\n",
+    "df2=gbo2.sum()\n",
+    "colors = [\"#355070\", \"#6d597a\", \"#b56576\", \"#e56b6f\", \"#eaac8b\"]\n",
+    "labels = ['Canada', 'Australia', 'China', 'France','Germany']\n",
+    "\n",
+    "plt.pie(df2,labels=labels,colors=colors, explode=(0,0.1,0,0,0.1),autopct='%1.0f%%')\n",
+    "plt.title('Total Deals by Country and Order Value')\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "a1c7f78e-960c-491d-95bc-dab551567014",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Count the number of deals in each Stage by Country\n",
+    "#In which country did the company win the most number of deals? Answer: Germany.\n",
+    "fig=plt.figure(figsize=(10,5))\n",
+    "ax=sns.countplot(x='Country', data=deals, hue='Deal Status', palette='rocket', alpha=0.8)\n",
+    "#ax.bar_label(ax.containers[0:2], fontsize=10);\n",
+    "plt.legend(fontsize='small', loc='upper right', bbox_to_anchor=(1.2, 1))\n",
+    "plt.title('Deals by Country, Deal Status and Number of Orders')\n",
+    "plt.tight_layout()\n",
+    "for container in ax.containers:\n",
+    "    ax.bar_label(container)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 113,
+   "id": "35dfa1f6-85a8-43a3-96d1-9db7e2eaeeef",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Deals worth how much were lost in Germany?\n",
+    "fig=plt.figure(figsize=(10,5))\n",
+    "r=sns.barplot(x='Deal Status',y='OrderValue',data=deals, \n",
+    "            hue='Country', palette='rocket', alpha=0.7, errorbar=None)\n",
+    "for container in r.containers:\n",
+    "    r.bar_label(container)\n",
+    "plt.legend(fontsize='small', loc='upper right', bbox_to_anchor=(1.2, 1))\n",
+    "plt.title('Deals by Country, Deal Status and Order Value')\n",
+    "plt.tight_layout()  # Adjust layout to prevent label cutoff#\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "67b01a86-0695-4630-b3f4-56ec9841e893",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Figure size 1700x700 with 0 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Most of the high quantity deals (greater than 300) were lost in which country?\n",
+    "plt.figure(figsize=(17,7))\n",
+    "plt.style.use('ggplot')\n",
+    "plt.tight_layout()  # Adjust layout to prevent label cutoff\n",
+    "g=sns.catplot(\n",
+    "    data=deals, kind=\"swarm\",\n",
+    "    x=\"Country\", y=\"OrderQuantity\", \n",
+    "    hue='Country',col=\"Deal Status\", palette=\"rocket\", size=10, legend=False\n",
+    ")\n",
+    "# set rotation\n",
+    "g.set_xticklabels(rotation=30) \n",
+    "plt.show()\n",
+    "#plt.legend(fontsize='small', loc='upper right', bbox_to_anchor=(1.2, 1))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 116,
+   "id": "5194b7e4-7977-4b28-8d17-8d052d176594",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1113.88x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Box plot with outliers\n",
+    "sns.catplot(\n",
+    "    data=deals, kind=\"boxen\",\n",
+    "    y=\"OrderQuantity\",\n",
+    "    hue='Country',col=\"Deal Status\", palette=\"flare\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "id": "97059838-a1eb-47bb-893c-676dff8f6408",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Group deals by Industry and OrderValue\n",
+    "gbo=deals.groupby('Industry')['OrderValue']\n",
+    "df=gbo.sum()\n",
+    "colors = [\"#355070\", \"#6d597a\", \"#b56576\", \"#e56b6f\", \"#eaac8b\",\"#ffa26b\",\"#a5bedc\"]\n",
+    "labels = ['Energy', 'Finance', 'Government', 'Healthcare','Manufacturing', 'Retail', 'Technology']\n",
+    "\n",
+    "plt.pie(df,labels=labels,colors=colors, explode=(0,0,0,0,0.1,0,0),autopct='%1.0f%%')\n",
+    "plt.title('Total Deals by Industry and Order Value')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 115,
+   "id": "7319a3b7-f413-4209-b6d3-a2b7afd8c5a0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Figure size 1300x500 with 0 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1150.88x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Deals are most likely to be won in which Country-Industry combination? Answer: Canada-Technology\n",
+    "fig=plt.figure(figsize=(13,5))\n",
+    "ax=sns.catplot(x='Country',y='OrderValue',data=deals, kind='bar', \n",
+    "            hue='Industry', col=\"Deal Status\",palette='rocket', alpha=0.7, errorbar=None)\n",
+    "sns.move_legend(ax, \"upper right\")\n",
+    "plt.tight_layout()  # Adjust layout to prevent label cutoff#\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}