Hello there,
I am fine-tuning gpt-3.5-turbo model for information related to Covid-19.
I have a wonder that Should I use multiple prompts for only one answer to fine-tune the model.
The purpose of this is that I want users to be able to use a variety of questions with the same purpose and return the same results.
(I was not using role: system).
For axample,
{"messages": [{"role": "user","content": "When did Covid-19 start?"},{"role": "assistant","content": "COVID-19 first appeared on a small scale in November 2019 with the first large cluster appearing in Wuhan, China, in December 2019."}]}
{"messages": [{"role": "user","content": "Can you tell me what year and where Covid-19 started?"},{"role": "assistant","content": "COVID-19 first appeared on a small scale in November 2019 with the first large cluster appearing in Wuhan, China, in December 2019."}]}
{"messages": [{"role": "user","content": "Where did Covid-19 originate? When?"},{"role": "assistant","content": "COVID-19 first appeared on a small scale in November 2019 with the first large cluster appearing in Wuhan, China, in December 2019."}]}
Thankyou and looking forward to receive the answer!