Sort outputs by variant id during extraction #122
Merged
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
|
It turns out that the quality of trained LR and VINC models depends sensitively on the shuffling of the prompts--I haven't yet totally figured out what's going on but I have verified that the only difference between the two cases was the data ordering. |
|
This sensitivity turns out to be explained by the bug fixed in #127 |
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Outdated suggestions cannot be applied.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.
This enables all the hiddens in a particular "row" (index into the
num_variantsaxis) to be of the same variant when using all available templates.Note that when
num_variantsis less than the number of available templates, it will continue to be the case that different subsets of the templates will be used for each example.