Add optional logging of text output to EvalOutputLogging #1283
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
sjawhar
commented
Jun 14, 2024
|
@maxisawesome can you please take a look? CC: @dakinggg |
|
|
|
Looks great other than the one comment I left! Thanks for fixing this for non-generative evals. |
|
@sjawhar if you can fix lint + unit tests (the CPU ones) that would be awesome! then we can merge |
sjawhar
commented
Jun 19, 2024
|
Anything else I can do to help get this merged? |
|
@sjawhar sorry about that, will take a look this week! |
dakinggg
reviewed
Jun 25, 2024
dakinggg
approved these changes
Jun 30, 2024
sjawhar
changed the title
Done |
|
@sjawhar looks like the tests failed with the recent change |
dakinggg
reviewed
Jun 30, 2024
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Outdated suggestions cannot be applied.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.
Adds the ability to log text output using
EvalOutputLoggingin non-metrics/ICL use cases. This appears as a newoutputskey in the logged dictionary, which is set tostats.outpusand de-tokenized when the model is aHuggingFaceModeland the dataset has a tokenizer.