-
Notifications
You must be signed in to change notification settings - Fork 1.2k
test: revamp eval related integration tests #1433
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
"role": "user", | ||
"content": judge_input_msg, | ||
} | ||
UserMessage( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
bug uncovered from unit tests :)
prompt_template=sample_judge_prompt_template, | ||
judge_score_regexes=[r"Score: (\d+)"], | ||
|
||
scoring_fn = scoring_fns_list[0] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
why the first one?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We test 1 scoring function per provider, as braintrust
has 10+ scoring functions (each having multiple LLM calls), and its slow to loop over all.
Will look into having mocks for scoring as well s.t. running can be within reasonable time.
What does this PR do?
Test Plan
dataset
scoring
eval