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

Flatten cache and add flashattention #2676

Merged
merged 12 commits into from
Nov 8, 2024

Conversation

grimoire
Copy link
Collaborator

No description provided.

@grimoire grimoire marked this pull request as draft November 5, 2024 03:34
@grimoire grimoire marked this pull request as ready for review November 5, 2024 05:36
Copy link
Collaborator

@RunningLeon RunningLeon left a comment

Choose a reason for hiding this comment

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

something wrong as shown in oc results on model internlm2_5-7b-chat

branch dataset version metric mode internlm2.5-7b-chat-pytorch
This PR race-high bd3f33 accuracy gen 14.38
main race-high bd3f33 accuracy gen 87.36
This PR gsm8k a58960 accuracy gen 84.31
main gsm8k a58960 accuracy gen 86.43

Copy link
Collaborator

@RunningLeon RunningLeon left a comment

Choose a reason for hiding this comment

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

Looks normal after fix commit ef24e85

dataset version metric mode internlm2.5-7b-chat-pytorch
race-high bd3f33 accuracy gen 87.34
gsm8k a58960 accuracy gen 85.44

Copy link
Collaborator

@RunningLeon RunningLeon left a comment

Choose a reason for hiding this comment

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

LGTM

@lvhan028 lvhan028 merged commit 2bed018 into InternLM:main Nov 8, 2024
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants