Our model(s) failed - Can we get the logs?

#675
by paloalma - opened

Hi,

We submitted 2 models but they failed:

It worked on our side using transformers so we were expecting these models to go through.

Can you investigate? Or can we have some logs?

thanks HF team :)

Open LLM Leaderboard org

Hi @paloalma !

Thanks for providing requests files!

I checked the logs, looks like it was a network issue. I have resubmitted both of your models, let's check the results.

If the status is FAILED again, I will investigate the error further

Hi @paloalma !

Thanks for providing requests files!

I checked the logs, looks like it was a network issue. I have resubmitted both of your models, let's check the results.

If the status is FAILED again, I will investigate the error further

Thanks for the fast response! Hope it gets through

Open LLM Leaderboard org

Closing since it's been solved, but feel free to reopen if there is a further problem!

clefourrier changed discussion status to closed
This comment has been hidden

Hi again !

I checked, and it seems that 2 other model encountered the same issue while being submitted :

https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/paloalma/ECE-TW3-JRGL-V1_eval_request_False_float16_Original.json
and
https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/paloalma/ECE-TW3-JRGL-V2_eval_request_False_bfloat16_Original.json

ECE-TW3-JRGL-V1 was also successfully tested on our side.

Thanks, HF team ;)

alozowski changed discussion status to open
Open LLM Leaderboard org

Hi @paloalma !

I checked the two files, it looks like it's the same network issue, so I've rescheduled the evaluation for those models too.

I'm closing this issue again, if you encounter the same problems with the models above, please, reopen it :)

alozowski changed discussion status to closed

Sign up or log in to comment