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
Training waterbirds dataset out-of-the-box gives 0 worst group accuracy. Digging deeper, I noticed that all the predictions immediately become the 0 label. Any advice would be helpful. Thanks in advance.
The text was updated successfully, but these errors were encountered:
Digging deeper, it seems that setting lr=1e-3 and wd=1e-4 is necessary to get reasonable results (i.e. non-degenerate solutions). It seems these are the hyperparameters recommended by most papers using this dataset (e.g,. https://arxiv.org/pdf/2210.11369.pdf). Perhaps the default values of these hyperparameters should be changed?
Training waterbirds dataset out-of-the-box gives 0 worst group accuracy. Digging deeper, I noticed that all the predictions immediately become the 0 label. Any advice would be helpful. Thanks in advance.
The text was updated successfully, but these errors were encountered: