TabularS3L

TabularS3L copied to clipboard

Train loss is negative

1

Hi, When doing first phase training over DAE and VIME (using unlabeled data), I got negative CrossEntropyLoss for the categorical features which resulted in a negative training and validation loss....

akhila-s-rao

How should I set different learning rate and optimization functions in the Second Phase Learning of SwitchTab?

1

In First Phase, we have: `config = SwitchTabConfig()` ` pl_switchtab = SwitchTabLightning(config)` So, in second phase: ` pl_switchtab.set_second_phase()` How should I set different learning rate and optimization functions in the...

znqaq