How to handle stateful=True in hyperparameter tuning of a LSTM - machine-learning

Question

Hello I'm using RandomizedSearchCV for hyperparameter tuning of my LSTM. The code works fine with stateful=False. However I also want so try this with stateful on but I'm not sure how to.
I arranged my data in a sliding window with shape (211845 datapoints, 4 window size, 16 features).
Following function for creating the architecture of the model.
def create_lstm(dropout_rate=0.0, neurons=32, lr=1e-3):
lstm = Sequential()
lstm.add(InputLayer((4, 16)))
lstm.add(LSTM(neurons, return_sequences=True))
lstm.add(Dropout(dropout_rate))
lstm.add(LSTM(neurons)
lstm.add(Dropout(dropout_rate))
lstm.add(Dense(neurons/4, activation='relu'))
lstm.add(Dense(1))
lstm.compile(loss='mse',
optimizer=Adam(learning_rate=lr),
metrics=['mean_squared_error']
)
return lstm
I pass the function to the wrapper
lstm_estimator = KerasRegressor(build_fn=create_lstm, verbose=1)
The following code is for my param grid and RandomSearch
lstm_param_grid = {
'dropout_rate': [0, 0.2, 0.4],
'neurons': [32, 64, 128],
'batch_size': [100, 200, 400],
'epochs': [50, 100, 150],
'lr': [1e-3, 1e-4, 1e-5]
}
lstm_RandomGrid = RandomizedSearchCV(estimator = lstm_estimator,
param_distributions = lstm_param_grid,
n_iter = 10,
verbose = 10,
n_jobs = -1,
cv = 5
)
In my create_lstm function the input shape of my data is equal to the window size and the number of features. After the RandomSearch i pass the arguments epochs and batch size when I fit the model. However with stateful=True you have to define batch_input_shape=(x, y, z).
I'm really not sure what exactly to do now. How can I change my code so that the RandomSearch still tests multiple batch sizes? And what exactly are (x,y,z) in my example? I tried (batch_size=100, window size, num of features) but that didn't work out.