You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The LR scheduler in train.py is being used in the per step mode rather than per epoch, which means the warmup and decay are expressed in terms of numbers of steps rather than numbers of epochs (I train a lot on huge datasets and sometimes don't actually get through one epoch). You need to use a much slower warmup than you would if it were expressed in terms of epochs.
the code is calling sched.step() without epoch number, which causes the learning rate to increase rapidly essentially without warmup.
https://github.com/pytorch/pytorch/blob/master/torch/optim/lr_scheduler.py
The text was updated successfully, but these errors were encountered: