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

[core] Small refactor of forward pass #136

Merged
merged 9 commits into from
Feb 8, 2023
Merged

[core] Small refactor of forward pass #136

merged 9 commits into from
Feb 8, 2023

Conversation

younesbelkada
Copy link
Contributor

@younesbelkada younesbelkada commented Feb 7, 2023 •
edited
Loading

Let's address #133 step by step

This PR just refactors thetrain_mini_batch function, so that the loss function does not have to compute the logits internally - which makes the latest easier to test

Logs:

@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Feb 7, 2023 •
edited
Loading

The documentation is not available anymore as the PR was closed or merged.

@younesbelkada younesbelkada marked this pull request as ready for review February 7, 2023 13:54
@younesbelkada younesbelkada requested a review from lvwerra February 7, 2023 13:54
@younesbelkada
Copy link
Contributor Author

Final runs:
T5: https://wandb.ai/distill-bloom/trl/runs/7bxai1m5?workspace=user-younesbelkada
gpt2: https://wandb.ai/distill-bloom/trl/runs/2453mt4s?workspace=user-younesbelkada

@younesbelkada younesbelkada merged commit 11bb0a2 into huggingface:main Feb 8, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@lvwerra lvwerra lvwerra 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.
3 participants
@younesbelkada @HuggingFaceDocBuilderDev @lvwerra