Is lm-eval-harness stuck again or just taking a while?

#611
by nisten - opened

Wondering if the models in queue are too big or the eval runtime is just stuck again.

Cheers,
Nisten

Open LLM Leaderboard org

Hi!
We run on the spare cycles of the science cluster of HF - if there is a model training going on, our evaluations will be slower, in order to share the ressources fairly between the different research teams.

clefourrier changed discussion status to closed

Sign up or log in to comment