Finetuning with no completion

[y7x3]

Does anybody know if this method of finetuning GPT-3 without a specific task still works?

Finetune model on context without using prompt and completion

I want to Finetune model using my knowledge base as context. So it can answer from that context without sending them all the time but i don’t have “prompt” and “completion” to finetune.

If so, what is going on under the hood / what actual training is occurring through this method. Thanks!