Stochastic Weight Averaging for steps instead of epochs #9861
Unanswered
MaveriQ
asked this question in
code help: NLP / ASR / TTS
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi
I am looking for guidance on how to adapt the SWA callback for a step based averaging and scheduler update. In its present form, both actions take place in the function
on_train_epoch_start
. Some of this will have to be moved into 'training_step' function.I will appreciate any pointers on how to go about that. Thanks
Beta Was this translation helpful? Give feedback.
All reactions