hendrycks / test

Measuring Massive Multitask Language Understanding | ICLR 2021

Home Page:https://arxiv.org/abs/2009.03300

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Seems that setting logprobs=100 is not useful now.

KL4805 opened this issue · comments

Hello authors,

I am really impressed with your efforts in creating this benchmark!

One small thing I notice is that OpenAI seems to limit the 'logprobs' argument to at most 5 (https://platform.openai.com/docs/api-reference/completions/create), while you set to 100. In this case, will your results be affected?

Wondering the same thing here. I'm guessing should have at least some effect.