The fine tuning endpoint for OpenAI's API seems to be fairly new, and I can't find many examples of fine tuning datasets online.
I'm in charge of a voicebot, and I'm testing out the performance of GPT-3 for general open-conversation questions. I'd like to train the model on the "fixed" intent-response pairs we're currently using: this would probably end up performing better in terms of company voice and style.
I have ready a long JSON file of data extracted from our current conversational engine, which matches user input to intents and returns the specified response. I'd like to train a GPT-3 model on this data.
As of now, for some quick testing, I've set up my calls to the API just like they suggest. I have a "fixed" intro text in the form
<name> is <company>'s voicebot. he is kind and professional...
This is a conversation between <name> and a customer:
which is pre-pended to each query, and then a small python class which keeps track of the context which starts with
User: <request the user provides>
Bot:
then with each turn the api's response is appended, this way I'm keeping track of what is said. After a few questions, the query or prompt string i'm sending looks like this:
<name> is <company>'s voicebot. he is kind and professional...
This is a conversation between <name> and a user:
User: <request>
Bot: <response>
User: <request>
Bot: <response>
... and so on
Bot:
My question is, do i have to provide the same "format" for my training data? Is it advisable? The docs indicate that the training set should be in this format:
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
...
But does the prompt need to include my intro text (the description) each time or do i simply provide a series of user/bot exchanges with a Bot: in the end and in the completion the answer i'd expect?
What would be a best practice in this case?
My fear is that if i wanted to slightly change the intro prompt a month from now I'd have to retrain the whole thing again because each response was trained with that specific block of text prepended.
I contacted OpenAI's support and they were extremely helpful: I'll leave their answer here.
the prompt does not need the fixed intro every time. Instead, you'll just want to provide at least a few hundred prompt-completion pairs of user/bot exchanges. We have a sample of a chatbot fine-tuning dataset here.