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

Explanation about "data" log parameter #25

Closed
SushantGautam opened this issue Jun 12, 2023 · 3 comments
Closed

Explanation about "data" log parameter #25

SushantGautam opened this issue Jun 12, 2023 · 3 comments

Comments

@SushantGautam
Copy link
Contributor

image
The values in the data are always zero. What does it represent?
@SushantGautam
Copy link
Contributor Author

SushantGautam commented Jun 12, 2023 •
edited

Ah! Looks like "the time taken for data loading or preprocessing for the current iteration".
Maybe we can change the formatting to display some significant info rather than just zeros.

@SushantGautam
Copy link
Contributor Author

image
I tried to train: videollama_stage1_pretrain with just cc_sbu_align dataset. But the loss doesn't settle well. It is oscillating around 2.5-3. Do you know if this is normal?

@hangzhang-nlp
Copy link
Collaborator

Yes, it is normal.

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
2 participants
@SushantGautam @hangzhang-nlp