Print initial validation loss + final validation loss #1228
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
carmocca
reviewed
Apr 2, 2024
rasbt
changed the title
|
I greatly simplified this @carmocca . Let me know if that's ok now. It should introduce any changes to the defaults. |
carmocca
approved these changes
Apr 25, 2024
rasbt
commented
Apr 25, 2024
I originally had that but others found it was misleading because it's calculated only on 2 batches and is not reliable. I then replaced it with the full loss calculation but then this was too slow. So the new argument is a compromise so that I can enable it for me but it doesn't slow it down for everyone. |
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Outdated suggestions cannot be applied.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.
EDIT: After Adrian already added the final validation, I greatly simplified this PR. So this only adds the initial validation. Since there was not that much enthusiasm from others, I made it optional and disabled it by default. I think it's a super useful feature to be able to know what the initial val_loss of the model is so that one can compare it to the final one and be able to tell if/how much things improved after training.