Skip to content

fix(docs): Update incorrect PPORLElement logprob tensor shape hint #377

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
Merged
merged 1 commit into from
Mar 17, 2023
Merged

fix(docs): Update incorrect PPORLElement logprob tensor shape hint #377

merged 1 commit into from
Mar 17, 2023

Conversation

jon-tow
Copy link
Collaborator

@jon-tow jon-tow commented Mar 17, 2023

Logits are collapsed along vocab dimension for logprobs resulting in tensor shape [..., response_size]

trlx/trlx/trainer/accelerate_ppo_trainer.py

Line 433 in 2f90ba0

logprobs = logprobs_of_labels(logits[:, :-1, :], all_tokens[:, 1:])

Related Issue: #371

maxreciprocate
maxreciprocate approved these changes Mar 17, 2023
View reviewed changes
Copy link
Collaborator

@maxreciprocate maxreciprocate left a comment

Choose a reason for hiding this comment

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

Thanks Jon!

@maxreciprocate maxreciprocate merged commit 79bfc6b into main Mar 17, 2023
@maxreciprocate maxreciprocate deleted the fix-shape-hint branch March 17, 2023 20:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@maxreciprocate maxreciprocate maxreciprocate approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@jon-tow @maxreciprocate