OpenPond
Back to Docs/Training methods

Training methods

Choose SFT, preference learning, or RL only after evidence and evaluation.

Training methods

Training changes model weights; Harness and Skill refinement change the behavior around a model. Start with the smaller, reversible change when the evidence supports it.

MethodBest fitRequires
SFTClear input/output demonstrationsCurated demonstrations and a holdout evaluation
Preference trainingRelative quality judgmentsComparable candidate outputs and reliable preference data
RL / GRPOMeasurable outcomes over multi-step rolloutsA bounded environment, reward/grader, budgets, and checkpoints

Every method needs approved data, a candidate evaluation, a budget, and an explicit activation decision. Training is not implied by a Refiner proposal.

Next: Evaluation before choosing a training run.