Class AsyncRLGRPOTrainer

rft/trainer/arl.py:70–983

Trainer for the Group Relative Policy Optimization (GRPO) method. This algorithm was initially proposed in the paper [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). Example: ```python from datasets

RewardFunc = Union[str, PreTrainedModel, Callable[[list, list], list[float]]]

class AsyncRLGRPOTrainer(Trainer):
    """
    Trainer for the Group Relative Policy Optimization (GRPO) method. This algorithm was initially proposed in the
    paper [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

    Example:

    ```python
    from datasets import load_dataset
    from trl import GRPOTrainer

    dataset = load_dataset("trl-lib/tldr", split="train")

    trainer = GRPOTrainer(
        model="Qwen/Qwen2-0.5B-Instruct",
        reward_funcs="weqweasdas/RM-Gemma-2B",
        train_dataset=dataset,
    )

    trainer.train()
    ```

    Args:
        model (`Union[str, PreTrainedModel]`):
            Model to be trained. Can be either:

            - A string, being the *model id* of a pretrained model hosted inside a model repo on huggingface.co, or
              a path to a *directory* containing model weights saved using
              [`~transformers.PreTrainedModel.save_pretrained`], e.g., `'./my_model_directory/'`. The model is
              loaded using [`~transformers.AutoModelForCausalLM.from_pretrained`] with the keywork arguments
              in `args.model_init_kwargs`.
            - A [`~transformers.PreTrainedModel`] object. Only causal language models are supported.
        reward_funcs (`Union[RewardFunc, list[RewardFunc]]`):
            Reward functions to be used for computing the rewards. To compute the rewards, we call all the reward
            functions with the prompts and completions and sum the rewards. Can be either:

            - A single reward function, such as:
                - A string: The *model ID* of a pretrained model hosted inside a model repo on huggingface.co, or a
                path to a *directory* containing model weights saved using
                [`~transformers.PreTrainedModel.save_pretrained`], e.g., `'./my_model_directory/'`. The model is loaded
                using [`~transformers.AutoModelForSequenceClassification.from_pretrained`] with `num_labels=1` and the
                keyword arguments in `args.model_init_kwargs`.
                - A [`~transformers.PreTrainedModel`] object: Only sequence classification models are supported.
                - A custom reward function: The function is provided with the prompts and the generated completions,
                  plus any additional columns in the dataset. It should return a list of rewards. For more details, see
                  [Using a custom reward function](#using-a-custom-reward-function).
            - A list of reward functions, where each item can independently be any of the above types. Mixing different
            types within the list (e.g., a string model ID and a custom reward function) is allowed.
        args ([`GRPOConfig`], *optional*, defaults to `None`):
            Configuration for this trainer. If `None`, a default configuration is used.
        train_dataset ([`~datasets.Dataset`] or [`~datasets.IterableDataset`]):
            Dataset to use for training. It must include a column `"prompt"`. Any additional columns in the dataset is
            ignored. The format of the samples can be either:

            - [Standard](dataset_formats#standard): Each sample contains plain text.
            - [Conversational](dataset_formats#conversational): Each sample contains structured messages (e.g., role
              and content).
        eval_dataset ([`~datasets.Dataset`], [`~datasets.IterableDataset`] or `dict[str, Union[Dataset, IterableDataset]]`):