Spaces:
Running
on
CPU Upgrade
70B models FAILED
Hi @alozowski
My running models have failed. Since they were successful previously, I am guessing it's the resources issue?
Many thanks
Hi @MaziyarPanahi ,
Thanks for providing the requests files! Yes, the cluster is full atm and that caused the models to fail โ I've re-submitted them, it should be fine now ๐
Please, ping me here if you encounter any issues with these models again
Many thanks @alozowski
I am not familiar with the new system, do these 2 models go to running automatically, or they go back to the PENDING queue?
The system didn't change, all the submitted models go to PENDING
first
Thanks @alozowski - was just wondering whether it should be voted again or it goes to running automatically.
Hi @alozowski
Sorry to bother you, these models are in RUNNING state but I can't see them in the running queue:
- https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2_eval_request_False_bfloat16_Original.json
- https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4_eval_request_False_bfloat16_Original.json
- https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/MaziyarPanahi/Qwen2-72B-Instruct-v0.1_eval_request_False_bfloat16_Original.json
Hi @MaziyarPanahi ,
Don't worry, I checked your models โ the first two jobs got preempted because of some exciting team experiments, but no worries though, they bounced back on its own shortly and you can see all the results on the Leaderboard now! ๐ค
You are all the best! ๐ค