You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is there a way to control how many examples are used to evaluate the models? Also, how are the evaluations currently set up? Are all benchmarks (ARC, MMLU, HellaSwag) running in a zero-shot fashion? If not, what is the configuration used?
The text was updated successfully, but these errors were encountered:
Hello!
Is there a way to control how many examples are used to evaluate the models? Also, how are the evaluations currently set up? Are all benchmarks (ARC, MMLU, HellaSwag) running in a zero-shot fashion? If not, what is the configuration used?
The text was updated successfully, but these errors were encountered: