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

Modify listings::ch06::calc_loss_batch to include train param and update listings::ch06::calc_loss_loader to set train to false #218

Open
nerdai opened this issue Jan 5, 2025 · 0 comments
Open

Modify listings::ch06::calc_loss_batch to include train param and update listings::ch06::calc_loss_loader to set train to false #218

nerdai opened this issue Jan 5, 2025 · 0 comments

Comments

@nerdai
Copy link
Owner

nerdai commented Jan 5, 2025 •
edited
Loading

Similar to ch05, calc_loss_batch is used for both inference and training, so it should have a param to be able to control the model modes.

Accordingly, since calc_loss_loader is only used for inference, it should set train to false when it invokes calc_loss_batch.
@nerdai nerdai converted this from a draft issue Jan 5, 2025
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
llms-from-scratch
Status: Ready
Milestone
No milestone
Development

No branches or pull requests
1 participant
@nerdai