Expose metrics to choose the best model along a training run #455
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
Luthaf
reviewed
Jan 28, 2025
docs/src/architectures/nanopet.rst
Outdated
Comment on lines
114
to
116
| :param best_model_metric: specifies the validation set metric to use to select the best | ||
| model. The default is ``rmse_prod``, i.e., the product of the RMSEs for each target. | ||
| Other options are ``mae_prod`` and ``loss``. |
There was a problem hiding this comment.
Do we define a concept of "best model" somewhere? Saying that this is the model that will end up in the cwd, named xxx.pt, …?
I would then link from here to this best model definition. Otherwise I would add something here, like "i.e. the model you can find at xxx.pt at the end of a training run"
There was a problem hiding this comment.
This can change for different architectures, so I will add it here
Luthaf
approved these changes
Jan 28, 2025
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Outdated suggestions cannot be applied.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.
Very important to reproduce state-of-the-art results
Contributor (creator of pull-request) checklist
📚 Documentation preview 📚: https://metatrain--455.org.readthedocs.build/en/455/