Evaluation for 70B model FAILED (tenyx/Llama3-TenyxChat-70B)

#719
by sarath-shekkizhar - opened

Hi,
The model evaluation FAILED for tenyx/Llama3-TenyxChat-70B (requests commit: c3a0bc5a0e1c65c3b011a691a386b30a5fc893f2 ). Looking into the discussion here, I noticed a few other 70B model variants reporting FAILED evaluation.
Is it possible to resubmit the TenyxChat model for evaluation?

Would also be happy to help if there is a known reason/error log for these failures.

Thank you

Open LLM Leaderboard org

Hi @sarath-shekkizhar !

According to logs, there was a network problem, so I resubmitted your model โ€“ feel free to write here if you encounter any other problems with this model

P.S. thanks to @Phil337 for searching for the request file ๐Ÿค

alozowski changed discussion status to closed

@alozowski Looks like the request FAILED again. Any chance the model could be resubmitted? Seems like the evaluation/status took 12+ hours before it ended up with failed -- anything we are missing here?

@alozowski -- any updates on this?

alozowski changed discussion status to open
Open LLM Leaderboard org
โ€ข
edited 27 days ago

Hi @sarath-shekkizhar ,

I checked the latest log file, it seems to be a network issue again as I can't detect any problems with the model itself. I've rescheduled your model, let's see how the evaluation process goes this time around

UPD: I checked the log after the reschedule, the evaluation is running, so let's wait for the results (I'm closing this question)

alozowski changed discussion status to closed

Sign up or log in to comment