How to check the training accuracy in K fold validation

Question

I am using k fold validation in my model in which user scans the historical places and our app will show all the details of it. The technologies i am using are SIFT and MLP. However, I am unable to find the training accuracy in k fold and also one more thing that i am unable to use tensor board in it , because i found on internet that it'll be used in model.fit( ) function but in K fold I am not using Code is shown below .

def built_classifier():
    classifier = tf.keras.models.Sequential()
    classifier.add(tf.keras.layers.Dense(64, input_shape=(128,), activation='relu'))
    classifier.add(tf.keras.layers.Dense(3, activation='softmax'))
    classifier.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
    classifier.save('SuperClassPredictions.h5')
    return classifier


classifier = KerasClassifier(build_fn=built_classifier, epochs=10, batch_size=32, shuffle=True)
accuracies = cross_val_score(classifier, data, one_hot_train_labels, cv=10)
print("Data Accuracy", accuracies)