feat(evals): return partial results when llm function is interrupted #1755
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
mikeldking
commented
Nov 15, 2023
| return pd.DataFrame( | ||
| data={ | ||
| "label": labels, | ||
| **({"explanation": explanations} if provide_explanation else {}), | ||
| **({"explanation": cast(List[str], explanations)} if provide_explanation else {}), |
There was a problem hiding this comment.
not sure if mypy shifted but just casting for now as it should be pretty guaranteed. Can add fallbacks above too instead
There was a problem hiding this comment.
it worked for me without the cast (even after hatch env remove type)
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
mikeldking
force-pushed
the
1748-error-tolerence
branch
from
cd150be to
086697d
Compare
mikeldking
commented
Nov 16, 2023
RogerHYang
reviewed
Nov 16, 2023
| return pd.DataFrame( | ||
| data={ | ||
| "label": labels, | ||
| **({"explanation": explanations} if provide_explanation else {}), | ||
| **({"explanation": cast(List[str], explanations)} if provide_explanation else {}), |
There was a problem hiding this comment.
it worked for me without the cast (even after hatch env remove type)
| rails=["relevant", "irrelevant"], | ||
| ) | ||
|
|
||
| assert classification_df is not None |
There was a problem hiding this comment.
could be more specific
Suggested change
| assert classification_df is not None | |
| assert classification_df.isna().sum() == 2 |
There was a problem hiding this comment.
I was foreshadowing the async submission change. Gonna leave it less specific to future proof
RogerHYang
approved these changes
Nov 16, 2023
Co-authored-by: Roger Yang <[email protected]>
Co-authored-by: Roger Yang <[email protected]>
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.
resolves #1748
Adds a try / catch block around the generation step of the llm functions so that the partial results can be outputted. This is important since we don't want the user to lose the progress they make - notably because it costs money.