How do you fine-tune a model to understand how much cheese a customer wants on a pizza?

[ruby_coder]

@Pasquale

but to me it is still unclear how it would be possible to train an ada model, f

I understand @Pasquale

Rough explaining and handwaving instructions which are just “wild guesses” are not going to get you to your end goal. Code matters. Testing matters.

Did you read my lab-tutorial on fine tuning?

Fine-Tuning In a Nutshell with a Single Line JSONL File and n_epochs

Those who frequent this community easily notice that developers struggle to get good fine-tunings results. In this multi-part tutorial, I’m going to use the davinci base model and fine-tune it multiple times with the same single-line prompt using different values for n_epochs. I will take a completion with each of these models, and demonstrate that if you set your n_epochs value high enough, you can get excellent results fine-tuning with a single-line prompt! Before we get started, I would …

Do you want me to fine-tune a single example for you, @Pasquale ? I’m into real-world examples and testing, not guessing.

If so, reply with your prompt-completion pair(s) and I will take a look and test for you.

But first, please go though the lab-based tutorial above and spend some quality time understanding fine-tuning from that tutorial.