core.trainers.grpo.trainer

core.trainers.grpo.trainer

Axolotl GRPO trainers (with and without context parallelism handling)

Classes

Name	Description
AxolotlAsyncGRPOTrainer	Extend AsyncGRPOTrainer with axolotl helpers
AxolotlGRPOContextParallelTrainer	Extend the base GRPOTrainer for context parallelism handling
AxolotlGRPOTrainer	Extend the base GRPOTrainer for axolotl helpers

AxolotlAsyncGRPOTrainer

core.trainers.grpo.trainer.AxolotlAsyncGRPOTrainer(*args, **kwargs)

Extend AsyncGRPOTrainer with axolotl helpers

AxolotlGRPOContextParallelTrainer

core.trainers.grpo.trainer.AxolotlGRPOContextParallelTrainer(
    model,
    reward_funcs,
    args=None,
    train_dataset=None,
    eval_dataset=None,
    processing_class=None,
    reward_processing_classes=None,
    callbacks=None,
    optimizers=(None, None),
    peft_config=None,
    optimizer_cls_and_kwargs=None,
)

Extend the base GRPOTrainer for context parallelism handling

Methods

Name	Description
get_train_dataloader	Get dataloader for training

get_train_dataloader

core.trainers.grpo.trainer.AxolotlGRPOContextParallelTrainer.get_train_dataloader(
)

Get dataloader for training

AxolotlGRPOTrainer

core.trainers.grpo.trainer.AxolotlGRPOTrainer(
    *args,
    data_collator=None,
    **kwargs,
)

Extend the base GRPOTrainer for axolotl helpers