diff --git a/trl/trainer/ppov2_config.py b/trl/trainer/ppov2_config.py index 1761d16e304..3cb33d0e5c6 100644 --- a/trl/trainer/ppov2_config.py +++ b/trl/trainer/ppov2_config.py @@ -12,7 +12,7 @@ @dataclass -class PPOv2Config(TrainingArguments, OnpolicyRuntimeConfig): +class PPOv2Config(OnpolicyRuntimeConfig, TrainingArguments): # common config exp_name: str = os.path.basename(__file__)[: -len(".py")] """the name of this experiment""" diff --git a/trl/trainer/rloo_config.py b/trl/trainer/rloo_config.py index 20e353a33fc..dd1039c3f47 100644 --- a/trl/trainer/rloo_config.py +++ b/trl/trainer/rloo_config.py @@ -13,7 +13,7 @@ @dataclass -class RLOOConfig(TrainingArguments, OnpolicyRuntimeConfig): +class RLOOConfig(OnpolicyRuntimeConfig, TrainingArguments): # common config exp_name: str = os.path.basename(__file__)[: -len(".py")] """the name of this experiment"""