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

How to adjust the best training efficiency #84

Open
Feedstar opened this issue Mar 17, 2025 · 0 comments
Open

How to adjust the best training efficiency #84

Feedstar opened this issue Mar 17, 2025 · 0 comments

Comments

@Feedstar
Copy link

In the paper, I saw that the number of steps is best kept around 100k or 200k. Is this the most important indicator affecting training efficiency? When training on GPU hardware with different performance, should I change the number of num_envs to keep the number of steps around 100k or 200k, or change other parameters?If anyone knows, I look forward to your reply.
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
@Feedstar