Fix early stopping code in dfencoder to use average loss of batches in validation set #908
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
hsin-c
added
bug
mdemoret-nv
requested changes
Apr 28, 2023
hsin-c
force-pushed
the
hsin-dfencoder-early-stopping-loss-fix
branch
from
38eb3a5
to
e865eb4
Compare
Added testing for early stopping. (Providing coverage for the early-stopping code in general, not testing the change in this PR specifically as it's a logic update on the data science side). |
mdemoret-nv
approved these changes
May 5, 2023
|
/merge |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR fixes the early stopping code in dfencoder to use the average loss of all batches in the validation set, instead of just the net loss of the last batch. This change will ensure that the early stopping criteria are more representative of the entire validation set, rather than relying on a potentially unrepresentative subset of the data.
closes #905
Checklist