mmlu eval and mmlu-branch eval failing on RHEL AI 1.3

Solution In Progress - Updated -

Issue

  • With RHEL AI 1.3 MMLU eval failing on granite-8b-starter model with erroro : 500 Server Error
  • Run MMLU eval on the granite-8b-starter model

    $ ilab model evaluate --model /var/mnt/instg1/instructlab/models/granite-8b-starter/ --benchmark mmlu --gpus 8 --enable-serving-output
    
  • It fails with a 500 Internal Server error

    Requesting API:   0%|▏                                                                                                                                                                            | 
    WARNING 2024-12-09 05:44:05,620 lm-eval:347: API request failed with error message: Internal Server Error. Retrying...
    WARNING 2024-12-09 05:44:06,786 lm-eval:347: API request failed with error message: Internal Server Error. Retrying...
    WARNING 2024-12-09 05:44:07,959 lm-eval:347: API request failed with error message: Internal Server Error. Retrying...
    ...
    requests.exceptions.HTTPError: 500 Server Error: Internal Server Error for url: http://127.0.0.1:49301/v1/completions
    

Environment

  • RHEL AI 1.3
  • granite-8b-starter

Subscriber exclusive content

A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.

Current Customers and Partners

Log in for full access

Log In

New to Red Hat?

Learn more about Red Hat subscriptions

Using a Red Hat product through a public cloud?

How to access this content