Skip to content
jointTrainig-separateLosses
Francesco Giuliari's avatar
Francesco Giuliari
@Francesco.Giuliari
8f948bd7 · Joint trainig working (no more nan, validatin places loss diverges) · 
Joint training is working with no more NaN (lr has to be really low).

Losses are still separate, validation losses do not have a jont covergence (places loss increase)

IIT