[WIP] add option to use MultipleNegativesRankingLoss
#152
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
PhilipMay
force-pushed
the
add_MultipleNegativesRankingLoss_training
branch
from
7ca1200
to
87740d5
Compare
PhilipMay
changed the title
MultipleNegativesRankingLossMultipleNegativesRankingLoss
PhilipMay
force-pushed
the
add_MultipleNegativesRankingLoss_training
branch
from
1655b36
to
2f3fdb6
Compare
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Outdated suggestions cannot be applied.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 is an experiment - work still in progress
The idea is: if we have more (or equal) classes than batch size we are able to create batches of sentence pairs
where each class is represented not more than once. If that is the case we can use MultipleNegativesRankingLoss.
related to #144
Todo