Mistral-Large-4
Mistral AIassistant_only_loss=True,
implementation detail · filed under post-training
Restricts supervised fine-tuning loss to assistant-generated content.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See supervised fine-tuning for the methods filed beside it.
Also called assistant_only_loss=True, cross-entropy loss on the assistant turns.
2 quotes from 2 sources, one card per model, each opening with its strongest.
assistant_only_loss=True,
SFT of Kolibri proceeds after the long-context training stage with cross-entropy loss on the assistant turns