Skip to content

Track entropy at training time #178

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.

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

Merged
merged 1 commit into from
Jun 30, 2025
Merged

Track entropy at training time #178

merged 1 commit into from
Jun 30, 2025

Conversation

corbt
Copy link
Contributor

@corbt corbt commented Jun 30, 2025

It may be useful to see how entropy changes over time, since once entropy collapses the model is unlikely to learn much more.

Not sure whether this is the best way to do it; notably, when doing it this way we aren't able to track entropy on the val set, only at training.

This is a subset of my changes from the increase-entropy branch, where I tried to explicitly reward increased entropy. However that branch, while successfully maintaining higher entropy, didn't seem to help training, so I only copied over the reporting changes here.

It may be useful to see how entropy changes over time, since once entropy collapses the model is unlikely to learn much more.

Not sure whether this is the best way to do it; notably, when doing it this way we aren't able to track entropy on the val set, only at training.
@corbt corbt requested a review from bradhilton June 30, 2025 08:04
Copy link
Collaborator

@bradhilton bradhilton left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks great!

@bradhilton bradhilton merged commit 9ece8d1 into main Jun 30, 2025
1 check passed
@bradhilton bradhilton deleted the entropy-tracking branch June 30, 2025 19:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants