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

Generalize loss decay to > 1d #68

Open

matsen opened this issue Jun 26, 2020 · 1 comment

Assignees

Contributor

matsen commented Jun 26, 2020

The current loss decay setup assumes that the output is 1d.

matsen self-assigned this

Contributor Author

matsen commented Oct 27, 2020

@zorian15 -- your exponentiation should work fine with > 1d, right?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment