Giter Site home page Giter Site logo

loss explode question about wavegrad HOT 7 CLOSED

ivanvovk avatar ivanvovk commented on July 28, 2024
loss explode question

from wavegrad.

Comments (7)

junkeon avatar junkeon commented on July 28, 2024 1

Thank you for your advice, i will try and report it!

from wavegrad.

ivanvovk avatar ivanvovk commented on July 28, 2024 1

Thank you for your feedback. And what was your batch size?

from wavegrad.

ivanvovk avatar ivanvovk commented on July 28, 2024 1

No-no, thank you very much, its enough information. I'm just trying to figure out why I had no loss explode problems with default setting on my server. However, I am glad that you managed to finish training, finally. Since the issue is solved, I'm closing it.

from wavegrad.

ivanvovk avatar ivanvovk commented on July 28, 2024

Hello, sure. Try decrease LR scheduler gamma a bit in the first place. From 0.95 to 0.9 with default initial LR (1e-3). I used 0.95 and it was kinda borderline between normal training and training with loss explosion. And please report if it helps or not.

from wavegrad.

ivanvovk avatar ivanvovk commented on July 28, 2024

Any updates, @junkeon ?

from wavegrad.

junkeon avatar junkeon commented on July 28, 2024

As your advice, i decreased gamma varies from 0.9 to 0.5 and there are all loss explode
But it seems okay with lr = 5e-4 and gamma = 0.9 on LJ speech data
In that setting, i got l1 loss slight above 0.1 and the synthesized quality is fine

from wavegrad.

junkeon avatar junkeon commented on July 28, 2024

sorry for late the previous feedback...
I can't remember the exact the number, it might be 48, the default setting
I can give you the number tomorrow (i am not allowed to access the server from outside), can't i?

from wavegrad.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.