Skip to content

Simplify and update trl examples #38772

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

Open
wants to merge 5 commits into
base: main
Choose a base branch
from

Conversation

qgallouedec
Copy link
Member

What does this PR do?

Fixes # (issue)

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 or the forum? 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, and
    here are tips on formatting docstrings.
  • 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.

optim="galore_adamw",
optim_target_modules=[r".*.attn.*", r".*.mlp.*"],
optim_args="rank=64, update_proj_gap=100, scale=0.10",
gradient_checkpointing=True,
Copy link
Member Author

Choose a reason for hiding this comment

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

soon default, but for now we need this to avoid oom

@@ -392,15 +392,15 @@ training_args = TrainingArguments(

[Gradient Low-Rank Projection (GaLore)](https://hf.co/papers/2403.03507) significantly reduces memory usage when training large language models (LLMs). One of GaLores key benefits is *full-parameter* learning, unlike low-rank adaptation methods like [LoRA](https://hf.co/papers/2106.09685), which produces better model performance.

Install the [GaLore](https://github.com/jiaweizzhao/GaLore) library, [TRL](https://hf.co/docs/trl/index), and [Datasets](https://hf.co/docs/datasets/index).
Install the [GaLore](https://github.com/jiaweizzhao/GaLore) library, [TRL](https://hf.co/docs/trl/index).
Copy link
Member Author

@qgallouedec qgallouedec Jun 11, 2025

Choose a reason for hiding this comment

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

datasets is a dep of trl

@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 requested a review from stevhliu June 12, 2025 09:44
Copy link
Member

@stevhliu stevhliu left a comment

Choose a reason for hiding this comment

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

Wow thanks for simplifying :)

@@ -392,15 +392,15 @@ training_args = TrainingArguments(

[Gradient Low-Rank Projection (GaLore)](https://hf.co/papers/2403.03507) significantly reduces memory usage when training large language models (LLMs). One of GaLores key benefits is *full-parameter* learning, unlike low-rank adaptation methods like [LoRA](https://hf.co/papers/2106.09685), which produces better model performance.

Install the [GaLore](https://github.com/jiaweizzhao/GaLore) library, [TRL](https://hf.co/docs/trl/index), and [Datasets](https://hf.co/docs/datasets/index).
Install the [GaLore](https://github.com/jiaweizzhao/GaLore) library, [TRL](https://hf.co/docs/trl/index).
Copy link
Member

Choose a reason for hiding this comment

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

Suggested change
Install the [GaLore](https://github.com/jiaweizzhao/GaLore) library, [TRL](https://hf.co/docs/trl/index).
Install the [GaLore](https://github.com/jiaweizzhao/GaLore) and [TRL](https://hf.co/docs/trl/index) libraries.

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