[Solved] Where Does Loss Calculation Begin When Multiple `response_template` Exist in Training Data Using SFTTrainer?
Last Updated on 2024-02-25 by Clay
Problem
SFTTrainer is a LLM fine-tuning tool provided by HuggingFace team, that can easily adjust many hyper-parameters and config at the fine-tuning task. In the process, response_template is the special string template we need to pass into the tool, any response right by it will be computed the loss.