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

Encoder-Decoder models support #93

Merged
merged 22 commits into from
Jan 23, 2023
Merged

Encoder-Decoder models support #93

merged 22 commits into from
Jan 23, 2023

Conversation

younesbelkada
Copy link
Contributor

@younesbelkada younesbelkada commented Jan 18, 2023 •
edited
Loading

Just a draft PR to check the changes between the 2 branches

EDT: Final PR to support enc-dec models on trl

This PR also:

  • refactors testing suite

@younesbelkada younesbelkada changed the title Fix enc dec wip [Do not merge] Draft PR for Enc-Dec Jan 18, 2023
@lvwerra lvwerra marked this pull request as ready for review January 20, 2023 12:03
@lvwerra lvwerra changed the title [Do not merge] Draft PR for Enc-Dec PR for Enc-Dec Jan 20, 2023
@lvwerra lvwerra changed the title PR for Enc-Dec Encoder-Decoder model support Jan 20, 2023
@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Jan 20, 2023 •
edited
Loading

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

lvwerra
lvwerra reviewed Jan 20, 2023
View reviewed changes
Copy link
Member

@lvwerra lvwerra left a comment

Choose a reason for hiding this comment

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

A few small comments to improve the script

This was referenced Jan 20, 2023
Closed
Closed
@younesbelkada
Copy link
Contributor Author

younesbelkada commented Jan 20, 2023 •
edited
Loading

Final Run on 2xNvidia T4 for t5-imdb: https://wandb.ai/distill-bloom/trl/runs/z4sm1ppv?workspace=user-younesbelkada
and the wandb logs of the ppo-sentiment with GPT on 4xA100: https://wandb.ai/distill-bloom/trl/runs/1eapyuim?workspace=user-younesbelkada
apart from the spike on step 2 for the first run, the generations seems nice and the reward curve converging smoothly ! 🔥

@younesbelkada younesbelkada changed the title Encoder-Decoder model support Encoder-Decoder models support Jan 20, 2023
@younesbelkada younesbelkada mentioned this pull request Jan 21, 2023
Closed
26 tasks
lvwerra
lvwerra approved these changes Jan 23, 2023
View reviewed changes
Copy link
Member

@lvwerra lvwerra left a comment

Choose a reason for hiding this comment

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

One small change in the example, otherwise good to go! 🚀

@younesbelkada @lvwerra
Apply suggestions from code review
6bd15cc 
Co-authored-by: Leandro von Werra <[email protected]>
@younesbelkada younesbelkada merged commit 8c9a39b into main Jan 23, 2023
@younesbelkada younesbelkada deleted the fix-enc-dec-wip branch January 23, 2023 10:00
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.
4 participants
@younesbelkada @HuggingFaceDocBuilderDev @lvwerra @SSamDav