#Fine-Tuning Fine-Tuned Model

4 messages · Page 1 of 1 (latest)

proper kettle
#

Hi everyone; so my team is working to train the API model to read long government contracts and spit back out necessary/significant information so we would be able to read such contracts efficiently. I created a fine-tuned model off of ~10 data-points but I was looking to see if I could somehow train my model to work more accurately through the OpenAI playground?

By this, I'm asking if I can adjust/evaluate the completions in the playground to further train/adjust my fine-tuning through trial in error; or am I going to have to continue importing training data? Thank you!

glad mountain
#

I don't think fine tuning is the way to go if you're looking to do question answering from documents or from a corpus of knowledge

#

Look into embeddings and extractive question answering

cerulean bramble