👎 [GRPO] Adds option to disable dropout #3234
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
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. |
lewtun
approved these changes
Apr 4, 2025
trl/trainer/grpo_trainer.py
Outdated
| @@ -359,6 +366,10 @@ def __init__( | |||
| reward_funcs[i] = AutoModelForSequenceClassification.from_pretrained( | |||
| reward_func, num_labels=1, **model_init_kwargs | |||
| ) | |||
| if args.disable_dropout: | |||
| if isinstance(reward_funcs[i], nn.Module): | |||
There was a problem hiding this comment.
I think AutoModelForSequenceClassification is loaded in eval model by default, so technically we don't need this here (happy to keep it though if we want to be safe)
There was a problem hiding this comment.
Indeed!
>>> from transformers import AutoModelForSequenceClassification
>>> model = AutoModelForSequenceClassification.from_pretrained("trl-lib/Qwen2-0.5B-Reward", num_labels=1)
>>> model.training
False
qgallouedec
reviewed
Apr 4, 2025
trl/trainer/grpo_config.py
Outdated
| @@ -101,6 +101,9 @@ class GRPOConfig(TrainingArguments): | |||
| speed, but may be numerically unstable for long training runs. | |||
| num_iterations (`int`, *optional*, defaults to `1`): | |||
| Number of iterations per batch (denoted as μ in the algorithm). | |||
| disable_dropout (`bool`, *optional*, defaults to `False`): | |||
There was a problem hiding this comment.
In the other trainers this is set to True, maybe we should do the same here?
qgallouedec
reviewed
Apr 4, 2025
trl/trainer/grpo_trainer.py
Outdated
Comment on lines
351
to
356
| if args.disable_dropout: | ||
| if isinstance(model, nn.Module): | ||
| disable_dropout_in_model(model) | ||
| if self.ref_model is not None and isinstance(self.ref_model, nn.Module): | ||
| disable_dropout_in_model(self.ref_model) | ||
|
|
There was a problem hiding this comment.
we only support PreTrainedModel, which are nn.Module (what else could it be?)
Suggested change
| if args.disable_dropout: | |
| if isinstance(model, nn.Module): | |
| disable_dropout_in_model(model) | |
| if self.ref_model is not None and isinstance(self.ref_model, nn.Module): | |
| disable_dropout_in_model(self.ref_model) | |
| if args.disable_dropout: | |
| disable_dropout_in_model(model) | |
| if self.ref_model is not None: | |
| disable_dropout_in_model(self.ref_model) | |
qgallouedec
approved these changes
Apr 9, 2025
yxliu-TAMU
pushed a commit
to mincheolseong/ECEN743-GRPO-Project-Proposal
that referenced
this pull request
Apr 20, 2025
Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com> Co-authored-by: Quentin Gallouédec <gallouedec.quentin@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Adds an option to disable dropout.
The RLOOTrainer disables dropout in policy, ref_model and reward model. This PR adds the option to disable dropout to the GRPOTrainer, which may improve training stability.
The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization
Provides more insight about why this option may improve training stability: