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.

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

Standardize training_args #2082

Merged
merged 2 commits into from
Sep 19, 2024
Merged

Standardize training_args #2082

merged 2 commits into from
Sep 19, 2024

Conversation

qgallouedec
Copy link
Member

@qgallouedec qgallouedec commented Sep 19, 2024

What does this PR do?

Let's use training_args for all instances of TrainingArguments

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a GitHub issue? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines.
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@qgallouedec qgallouedec marked this pull request as ready for review September 19, 2024 10:26
Copy link
Member

@lewtun lewtun left a comment

Choose a reason for hiding this comment

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

Nice refactor! LGTM


assert train_dataset[0]["input_ids"][-1] != tokenizer.eos_token_id, "The last token should not be an EOS token"
################
# Training
################
trainer = PPOv2Trainer(
config=config,
config=training_args,
Copy link
Member

Choose a reason for hiding this comment

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

Not for this PR, but is there a reason the PPO/RLOO configs have a config attribute instead of the default args one?

Copy link
Member Author

Choose a reason for hiding this comment

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

I don't think so. I think we just didn't considered consistency when it was implemented.

@qgallouedec qgallouedec merged commit 10c2f63 into main Sep 19, 2024
10 checks passed
@qgallouedec qgallouedec deleted the standard-training-args branch September 19, 2024 13:03
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants