curriculum learning and test them, solve reproduce issue
Closed this issue · 5 comments
All cases are trained on fixed learning rate and steps. Adopt decaying learning rate on convergence point
Commented on #10
When I found that bug, it was already over to train first best model. So I decided to check out in double.
So, when I test above issue to reproduce exam, I saw that loss curve seems same like uploaded best checkpoint file. At this moment, it should be contained audioset files to reproduce that result. (It's under training)
I checked downloaded audioset files, and these are correct that contains 18055 files and volume normalized 22.05k. I will check continuously overall process.
Test samples are almost same. After training model, it will be reported.
-
Simple PESQ Report : #9 (comment)
-
WSDR Losses (valid on 200k steps)
- with audioset : -0.907
- without audioset : -0.938
Model is trained without audioset, it seems overfitting on voice bank dataset. (on testset)
- PR Plan
- First I will upload 200k result (with audioset)
- (WIP) It is training after 200k steps with decayed learning rate. After training model, it will be uploaded.
#15 pushed middle of result
remain
- check process codes of audioset
- get more training model with decayed learning rate
Handle another issue to get better result. close it