I’m new to neural networks and a bit confused on why the loss is continually getting worse. Here is what I have right now:

!pip install tensorflow

from sklearn.preprocessing import StandardScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from sklearn.model_selection import train_test_split
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import EarlyStopping



X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=42)



scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)



model = Sequential([
    Dense(128, activation='relu', input_shape=(X_train.shape[1],)),
    Dropout(0.5),
    Dense(64, activation='relu'),
    Dense(32, activation='relu'),
    Dense(16, activation='relu'),
    Dense(1, activation='sigmoid')
])



optimizer = Adam(learning_rate=0.001)
model.compile(optimizer=optimizer, loss='MeanSquaredError', metrics=['accuracy'])



early_stopping = EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True)



history = model.fit(X_train_scaled, y_train, epochs=100, batch_size=32,
                    validation_split=0.2, callbacks=[early_stopping])


model.fit(X_train_scaled, y_train, epochs=50, batch_size=32, validation_split=0.2)


loss, accuracy = model.evaluate(X_test_scaled, y_test)
print(f'Test Accuracy: {accuracy}')

I was hoping that over the epochs the accuracy would improve and that would be reflected in the loss function, but I think I must be missing an important statement or parameter.