The Definitive Guide toAI Data Centers
Ask the GuideAboutAccount
GuideGlossaryPost-training

Post-training

The fine-tuning and alignment stages (SFT, RLHF) after pretraining that shape a model's behavior and usefulness.

Current numbers

~80%of wall-clock spent on rollout generation in agentic/reasoning RL post-trainingas of 2026 · register ↗

← All terms