Remark. Fine-tuning objectives and supervised instances [ftip-006R]
Remark. Fine-tuning objectives and supervised instances [ftip-006R]
Wei et al. train on instruction-expressed task mixtures in [wei2022finetuned, Section 2 and Figure 2]. Ouyang et al. fine-tune on labeler demonstrations in [ouyang2022training, Section 3.5 and Appendix C.1]. The proposed continued-optimization interface in Definition [ftip-006Q] includes these concrete supervised instances.
Neither cited source defines fine-tuning as one universal objective. A concrete run must state its records, loss and normalization, optimizer, stopping rule, and trainable parameters. Instruction tuning later specializes the records to instruction--response demonstrations.