actual param name for lr

src/peft/optimizers/loraplus.py

@@ -43,8 +43,8 @@ def create_loraplus_optimizer(
         model (`torch.nn.Module`): The model to be optimized.
         optimizer_cls (`torch.optim.Optimizer`): The optimizer class to be used.
         loraplus_lr_ratio (`float`):
-            The ratio of learning ηB/ηA where ηA is passed in as the optimizer learning rate. Should be ≥1. Should be
-            set in tandem with the optimizer learning rate (ηA); should be larger when the task is more difficult and
+            The ratio of learning ηB/ηA where ηA (lr) is passed in as the optimizer learning rate. Should be ≥1. Should be
+            set in tandem with the optimizer learning rate (lr); should be larger when the task is more difficult and
             the model needs to update its features to learn well. In this case, it helps to make the learning rate
             slightly smaller (e.g., by a factor of 2) than typical vanilla LoRA learning rates
         loraplus_lr_embedding (optional `float`):