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.

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

Switch from SGD optimizer to AdamW for patch classification tasks #690

Merged
merged 9 commits into from
Oct 18, 2024

Conversation

nkaenzig
Copy link
Collaborator

@nkaenzig nkaenzig commented Oct 18, 2024

  • For some models we have observed SGD to not converge (fast enough), without further tuning the learning rate
  • This PR standardises the batch size for patch classifiction tasks to 256

@nkaenzig nkaenzig self-assigned this Oct 18, 2024
@nkaenzig nkaenzig marked this pull request as ready for review October 18, 2024 13:08
@roman807
Copy link
Collaborator

Thanks, looks good! Do you want to already include the updated leaderboard plots in this PR or would this come in a later one?

@nkaenzig nkaenzig enabled auto-merge (squash) October 18, 2024 13:54
@nkaenzig nkaenzig merged commit c6af930 into main Oct 18, 2024
6 checks passed
@nkaenzig nkaenzig deleted the sgd-to-adam branch October 18, 2024 14:11
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