chatGPT Fine-Tuning

파인프로세스 (At a high level, fine-tuning involves the following steps)

1. 데이터 준비(Prepare and upload training data)
2. 모델생성(Train a new fine-tuned model)
3. 모델활용(use your fine-tuned model)

학습데이터는 다음과 같은 형식으로 만들어져야 하고, 모델( Davinci, Curie, Babbage, Ada )

{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}
{"prompt": "<prompt text>", "completion": "<ideal generated text>"}

{"prompt":"Company: BHFF insurance\nProduct: allround insurance\nAd:One stop shop for all your insurance needs!\nSupported:", "completion":" yes"}
{"prompt":"Company: Loft conversion specialists\nProduct: -\nAd:Straight teeth in weeks!\nSupported:", "completion":" no"}

 작업을 완료시 fine-tune 작업ID를 얻을수있음. ft-XXXXXXXXXXXXXXXXXX

작업완료시 epoch 진행상황과 Fine-tune succeeded, uploaded model과 결과를 확인가능하다.