by Nevin1901 on 10/21/23, 9:23 PM with 5 comments
Working on a service which uses GPT-3.5 and was wondering how I would go about tracking the usefulness of it. Wondering what you guys have done, or if you guys even track your NLP models at all.
by PaulHoule on 10/21/23, 10:09 PM
Are you doing classification, regression, extraction or something different? How did you evaluate the model before it went into production?