def create_model(layer_1, layer_2, lrate, input_sh, act = 'relu'):
    model = models.Sequential()
    model.add(layers.LSTM(layer_1, activation = act, return_sequences=True, input_shape = input_sh))
    model.add(layers.LSTM(layer_2, activation = act))
    model.add(layers.Dense(24))

    adam_opt = optimizers.Adam(lr = lrate)
    model.compile(optimizer = adam_opt, loss = 'mse', metrics = ['mape'])
    model.summary()
    return model

tscv = TimeSeriesSplit(n_splits = 2)
for train_index, valid_index in tscv.split(features):
    print('Train_shape:', train_index.shape, 'Valid_shape:', valid_index.shape)
    train_X, valid_X = features[train_index], features[valid_index]
    train_y, valid_y = target[train_index], target[valid_index]

    model = create_model(lstm_layer_1, lstm_layer_2, learning_rate,
                    input_sh = (24, train_X.shape[-1]))

    history = model.fit(train_X, train_y, epochs = epochs,
                    batch_size=batch_size,
                   validation_data=(valid_X, valid_y))

TypeError                                 Traceback (most recent call last)
<ipython-input-22-0d80fb09704c> in <module>
 20     history = model.fit(train_X, train_y, epochs = epochs,
 21                         batch_size=batch_size,
---> 22                        validation_data=(valid_X, valid_y))
     23
     24     #Plot the figure

~/3005/lib/python3.7/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
  1037                                         initial_epoch=initial_epoch,
  1038                                         steps_per_epoch=steps_per_epoch,
-> 1039                                         validation_steps=validation_steps)
  1040
  1041     def evaluate(self, x=None, y=None,

~/3005/lib/python3.7/site-packages/keras/engine/training_arrays.py in fit_loop(model, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps)
   140             indices_for_conversion_to_dense.append(i)
   141
--> 142     for epoch in range(initial_epoch, epochs):
   143         # Reset stateful metrics
   144         for m in model.stateful_metric_functions:

TypeError: 'range' object cannot be interpreted as an integer