Hi, thanks for the great work.

When I fine-tune with acid.ckpt or re10k.ckpt：python3 -m src.main +experiment=custom checkpointing.load=checkpoints/re10k.ckpt mode=train data_loader.train.batch_size=4

an error occurs：KeyError: 'Trying to restore optimizer state but checkpoint contains only the model. This is probably due to ModelCheckpoint.save_weights_onlybeing set toTrue.'

Is my finetune command incorrect?