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

why is the warmup_iters set 2000? #552

Open
luxunxiansheng opened this issue Sep 5, 2024 · 0 comments
Open

why is the warmup_iters set 2000? #552

luxunxiansheng opened this issue Sep 5, 2024 · 0 comments

Comments

@luxunxiansheng
Copy link

The total batch size( in token ) is 0.5M in one iteration ,which follows the GPT3 paper. With the same logic, since the GPT3's warmup is 375M tokens, why is the warmup_iters not set to 375/0.5 = 750 but 2000? Is there any further consideration?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@luxunxiansheng