Dataset Formatting

Also known as: training data format, SFT data format

Dataset formatting refers to the structure imposed on training examples before they are fed into a fine-tuning run — including how system messages, user turns, and assistant responses are arranged using the model family's chat template, how special tokens mark role boundaries, and how output fields are masked so the loss is computed only on tokens the model should learn to generate. Incorrect formatting is one of the most common causes of poor fine-tuning results because the model trains on the wrong supervision signal.