zkzhou126
Results
2
comments of
zkzhou126
> > when I use the original loss（without loss mask），I get the following result > > ``` > > ----------------------------- > > | decoder_nll | 1.27e-05 | > > |...
> I am running the experiments of QQP and I have changed the computation of loss in the training code. when I create dataset, I add 'loss_mask' > > ```python...