I have 96 samples and i set val_size=10 then I have this: "RuntimeError: No best trial found for the given metric: loss. This means that no trial has reported this metric, or all values reported for this metric are NaN. To not ignore NaN values, you can set the

filter_nan_and_inf

arg to False."

Hi @virgilio espina. Can you also show the

nhits_config

please? Have you tried setting

val_size=12

(at least one horizon)?