Best approach for JSON generation

[hermeticJay]

Relatively new to OpenAI.

I’d like to be able to provide a prompt (e.g. “George Washington”) and receive a JSON object back with various details (e.g. {“firstName”: “George”, “lastName”: “Washington”, “yearOfBirth”: 1732, “yearOfDeath”: 1799, “bio”: “First President of the United States”}).

ChatGPT seems to handle this well. I’ve tried fine-tuning GPT-3 to mixed results. Thinking this might be better suited for Codex but unaware of how to fine-tune that model. Curious as to what would be some best practices for this use case.

Thanks

[udm17]

I’ve been trying to do the same using GPT-3 and prompting with a sample has helped a lot. The return from the API is a string format, which can easily be read as a JSON using json.loads if you’re using python.

[hermeticJay]

Not sure how large your JSON objects are, but how many samples are you squeezing into the prompt? Which model are you prompting against?

[udm17]

I just using a single sample in the prompt, with around 7 key-value pairs. Prompting da-vinci-003

[ruby_coder]

@hermeticJay

Thinking this might be better suited for Codex but unaware of how to fine-tune that model.

This is easy to do with the davinci base model. You cannot fine-tune any codex models at this time.

@hermeticJay

Curious as to what would be some best practices for this use case.

I releases a tutorial / lab experiment on how to fine-tune a single-line JSONL training file using the n_epochs parameter yesterday. You might find the results useful.

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 …

Hope this helps.

[earthsendangered]

Can you provide sample training data? I’m trying to figure out how to train my model with sample json and the api doesn’t seem to like json as a property inside of the overall jsonL file.

[udm17]

I don’t provide them as a part of the jsonL file, but more so as a part of the prompt message.

[hermeticJay]

Yeah, exactly. Include a reference JSON object in your prompt (or as many as you can fit) and it should conform to that. It might forget after a while, so you may need to periodically refresh context.