Leaderboard stuck?

#754
by DreamGenX - opened

Hey there, really appreciate you offering this as a community service!

FYI, the same 15 models seem to be stuck in "running evaluation" state, and some models are in "pending" state for >1day, e.g. https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/failspy/Llama-3-70B-Instruct-abliterated-v3_eval_request_False_float16_Original.json

Open LLM Leaderboard org

Hi @DreamGenX ,

Unfortunately, our research cluster is full and the evaluation can take more time than usual. If a particular model fails, please open a new discussion and we will resubmit it

alozowski changed discussion status to closed

Sign up or log in to comment