如何在ktrain中使用交叉验证？

import ktrain
from ktrain import text

(x_train, y_train), (x_test, y_test), preproc = text.texts_from_folder('path/to/folder', 
                                                                       maxlen=500, 
                                                                       preprocess_mode='bert',
                                                                       train_test_names=['train', 'test'])

model = text.text_classifier('bert', train_data=(x_train, y_train))

learner = ktrain.get_learner(model, train_data=(x_train, y_train), val_data=(x_test, y_test))
learner.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

learner.autofit(lr=2e-5, epochs=5, batch_size=32, reduce_on_plateau=10, callbacks=[early_stopping], 
                monitor='val_loss', verbose=1, nfold=5)

predictor = ktrain.get_predictor(learner.model, preproc)
y_pred = predictor.predict(x_test)
learner.validate(val_data=(x_test, y_test), class_names=preproc.get_classes())