Open Models Almanac
Methodstraining objectiveauxiliary loss

single mention · training objective

Reference-policy KL penalty using the k2 estimator

Applies a reference-policy KL penalty estimated with the k2 estimator for selected data sources.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See auxiliary loss for the methods filed beside it.

Filed under training objective › auxiliary loss