You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The ORPOTrainer fails when training using attn_implementation="flash_attention_2", since the cache is being used, and falls back to the default configuration i.e. padding_side="right" for the tokenizer in this case.
Bug in code
Missing use_cache=False to prevent the model from using the cache, to avoid issues with Flash Attention 2.
Description
The
ORPOTrainer
fails when training usingattn_implementation="flash_attention_2"
, since the cache is being used, and falls back to the default configuration i.e.padding_side="right"
for the tokenizer in this case.Bug in code
Missing
use_cache=False
to prevent the model from using the cache, to avoid issues with Flash Attention 2.trl/trl/trainer/orpo_trainer.py
Lines 685 to 689 in 2ce8e45
The text was updated successfully, but these errors were encountered: