Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

About Hyperparmeter "predictor_grad" #89

Open
HAN-oQo opened this issue Mar 13, 2023 · 2 comments
Open

About Hyperparmeter "predictor_grad" #89

HAN-oQo opened this issue Mar 13, 2023 · 2 comments

Comments

@HAN-oQo
Copy link

HAN-oQo commented Mar 13, 2023

Hi,
Thank you for the awesome project!

I wonder why the hparam "predictor_grad" is required.
Can you explain the reason please?

Best regards,
Hankyu
@MoonInTheRiver
Copy link
Owner

Adjust the weight of subtasks during multi-task training.

@HAN-oQo
Copy link
Author

HAN-oQo commented Mar 13, 2023 •
edited

Thank you for answer! @MoonInTheRiver

But, im still confusin about this term.
dur_input.detach() + hparams['predictor_grad'] * (dur_input - dur_input.detach())

Can you explain this why it can adjust the weights in detail please?

Thank you so much for answer

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@MoonInTheRiver @HAN-oQo