Spaces:
Restarting
on
CPU Upgrade
Restarting
on
CPU Upgrade
Are all metics in the table accuracy?
#28
by
zhiminy
- opened
I cannot find any specification of the demonstrated metrics...particularly for CommonGenv2 and TruthfulQA
zhiminy
changed discussion title from
Are all metics `accuracy`?
to Are all metics in the table accuracy?
Hello,
The metric for the TruthfulQA task is mc2. Other task metrics can be found under the "About" tab of this link: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard.
The metric for KoCommonGenV2 is acc_norm.
Regards.
zhiminy
changed discussion status to
closed
Hello,
The metric for the TruthfulQA task is mc2. Other task metrics can be found under the "About" tab of this link: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard.
The metric for KoCommonGenV2 is acc_norm.
Regards.
Thanks, but it is better to add this into the documentation :)