2.3 Train the model

results = model.fit(
    X_train, y_train,
    epochs= training_epochs,
    batch_size = 32,
    validation_data = (X_test, y_test),
    verbose = 2
)

Train on 60000 samples, validate on 10000 samples
Epoch 1/5
60000/60000 - 55s - loss: 0.1004 - accuracy: 0.9700 - val_loss: 0.0667 - val_accuracy: 0.9796
Epoch 2/5
60000/60000 - 37s - loss: 0.0445 - accuracy: 0.9866 - val_loss: 0.0610 - val_accuracy: 0.9839
Epoch 3/5
60000/60000 - 30s - loss: 0.0352 - accuracy: 0.9889 - val_loss: 0.0484 - val_accuracy: 0.9854
Epoch 4/5
60000/60000 - 30s - loss: 0.0267 - accuracy: 0.9915 - val_loss: 0.0552 - val_accuracy: 0.9852
Epoch 5/5
60000/60000 - 30s - loss: 0.0208 - accuracy: 0.9932 - val_loss: 0.0572 - val_accuracy: 0.9852