NLNR

Hi, thank you for your excellent job. However, when I run the code using the default setting for pretraining on OAG_CS, the time taken for an epoch is much longer...

When running model vidore/colpali-v1.2 on full evaluation, it will occur RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:6 and cuda:0!