Closed GenjiB closed 1 year ago
Can you point to me where .21
is seen?
This is correct -
In the original paper, we use the 25th epoch pretrain checkpoint but later found the 21st would be good enough (because the lr scheduler cuts off every 5 epochs, 21st epoch is right after the cut). The cav-mae scale ++ model was trained after the paper got published, so there is a minor difference.
But this is a minor thing, I recommend to use the 21st because it saves pretraining cost, but 25th leads to very similar result.
-Yuan
Btw, the public link we provided for cav-mae scale++ is 21st epoch checkpoint. There's no other model released.
thanks so much for the clarification
Hi,
I just noticed that the script you provided use
audio_model.21
. Does that mean you use the model at 21th epoch?Because you pre-train the model with epochs, it would be a little bit confusing to me.
Thank you