Metrics support #55
Merged
Metrics support #55
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
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
|
Waiting on the instruction tuning PR. Once #40 merges with main successfully, merging this branch will be easier. |
Merged
martinjaggi
approved these changes
Sep 6, 2023
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Outdated suggestions cannot be applied.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.
Added support to calculate custom metrics during evaluation (e.g. accuracy).
--metrics. When set, it should be accompanied by one or more names of metric functions. For now onlyperplexity,accuracy,count_loss_mask(number of nonzero elements per sample in the loss_mask),count_instruct_mask(same as before, but this setting doesn't count the extra tokens that surrounds the messages in the instruction tuning setting, i.e. the<|im_begin|>and<|im_end|>),instruct_accuracy.Thanks to @andreaskoepf and his fork for serving as inspiration to this implementation.