Sxjdwang
commented
11 months ago The loss you describe is normal. In my training, the lip loss on the validation set is still larger than 200 after training with a batch size of 8.
Open luqianX opened 11 months ago
Sxjdwang
commented
11 months ago The loss you describe is normal. In my training, the lip loss on the validation set is still larger than 200 after training with a batch size of 8.
why my lip_loss is >90 even for gt videos? should not LabelSmoothedCrossEntropyCriterion in fairseq be near -log(1/n)?