Bugfix: handle case where 'losses' is a list of tensors

[TeodorChiaburu]

Description

This PR fixes an issue I came across when applying NHiTS and TFT on my use case, namely that losses can be tensors within a list. In that case, the function mask_losses will fail. It is just a one-liner in base_metrics.py.

[jdb78]

BTW: Would be great to have a test for this!