Yifang Chen

icon indicating a website link https://cloudwaysx.github.io/

icon company University of Washington icon location PhD student in UW CSE interested in active learning, bandits and representation learning

Results 1 comments of Yifang Chen

[BUG] Tensors are on different devices when model.step()

I have the same issue here when running the following script. https://github.com/allenai/open-instruct/blob/main/scripts/dpo_train_with_accelerate.sh. I notice that version 0.14.0 does not have this issue.