-
Notifications
You must be signed in to change notification settings - Fork 472
start decay after resume without "-continue" #76
Comments
The learning rate is only updated at the end of an epoch. So it will complete epoch 6 first, then a first decay will be applied. |
well if I specify start_epoch 6 end_epoch 9 start_decay 5 decay_rate 0.5 |
Why are you not using I believe the current behavior is correct. For example if |
then to avoid confusion, if continue is not set and if you load from an existing model, I f would suggest we throw an error if start_decay_at if less or equal to start_epoch. |
Unless I'm missing something, that is reason we introduced the When you don't use |
ok best to discuss this on the forum. |
Here is the scenario.
first training:
5 epochs, lr 1.0, start decay 5 decay_rate 0.5
Then resume training with -"continue" works fine.
start_epoch 6 end_epoch 9 ==> lr of epoch 6 = 0.5
if I don't use "-continue"
lr of epoch 6 will start at 1 and not decay right away eventhough I am passing options.
I could always use -continue, but I guess one might want to change the decay rate after a resume.
clear ?
The text was updated successfully, but these errors were encountered: