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

deprecated fa2 and use flex attention #166

Merged
merged 7 commits into from
Dec 10, 2024
Merged

deprecated fa2 and use flex attention #166

merged 7 commits into from
Dec 10, 2024

Conversation

samsja
Copy link
Collaborator

@samsja samsja commented Dec 3, 2024 •
edited
Loading

Screenshot from 2024-12-09 20-09-09.

Eval of a 1b train on 1000 steps

Tasks Version Filter n-shot Metric Value Stderr
hellaswag 1 none 10 acc ↑ 0.2784 ± 0.0045
none 10 acc_norm ↑ 0.2924 ± 0.0045

seems that everything is fine

@JohannesHa JohannesHa marked this pull request as draft December 8, 2024 00:51
@samsja samsja marked this pull request as ready for review December 10, 2024 02:41
Jackmin801
Jackmin801 approved these changes Dec 10, 2024
View reviewed changes
Copy link
Member

@Jackmin801 Jackmin801 left a comment

Choose a reason for hiding this comment

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

nice! lfgtm!

@samsja samsja merged commit a116ef1 into main Dec 10, 2024
2 checks passed
@samsja samsja deleted the add-flex-attn branch December 10, 2024 18:50
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Jackmin801 Jackmin801 Jackmin801 approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@samsja @Jackmin801