Skip to content

[FIX] Inverse scaling with MASE loss#1447

Merged
marcopeix merged 2 commits intomainfrom
fix/inv_norm_val_step
Feb 11, 2026
Merged

[FIX] Inverse scaling with MASE loss#1447
marcopeix merged 2 commits intomainfrom
fix/inv_norm_val_step

Conversation

@marcopeix
Copy link
Contributor

If MASE was used a validation loss, insample_y was in normalized scale while outsample_y and y_hat were in original scale.

With the fix, all values passed to MASE should be in the same original scale.

@marcopeix marcopeix marked this pull request as ready for review February 11, 2026 18:40
@nasaul nasaul self-requested a review February 11, 2026 18:50
Copy link
Collaborator

@nasaul nasaul left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@marcopeix marcopeix merged commit 14ac0c5 into main Feb 11, 2026
21 checks passed
@marcopeix marcopeix deleted the fix/inv_norm_val_step branch February 11, 2026 20:33
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants