This message was deleted.

Hi @Phil! This is a great idea. The

core

methods are using the

TimeSeriesDataModule

to create the loaders, and it currently assumes that the dataset (collection of time series) is the same for both training and validation sets. I will modify the module to allow for different datasets, and then you will be able to pass a

valid_df

in

core

methods.

Awesome! thank you @Cristian (Nixtla)! Let me just say how great the community you've all created is. I'm excited by your efforts