We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent ab2133b commit aa29050Copy full SHA for aa29050
swift/trainers/rlhf_trainer/ppo_trainer.py
@@ -39,7 +39,7 @@ def __init__(self, model: PreTrainedModel, ref_model: PreTrainedModel, *_args, *
39
new_kwargs = {
40
k: v
41
for k, v in kwargs.items()
42
- if k in ['train_dataset', 'data_collator', 'reward_model', 'value_model', 'eval_dataset']
+ if k in ['train_dataset', 'data_collator', 'reward_model', 'value_model', 'eval_dataset', 'callbacks']
43
}
44
parameters = inspect.signature(ppo_trainer_init).parameters
45
if 'config' in parameters:
0 commit comments