~ portfolio

Satvik Sawhney

software engineer

loading000%
notes1 note

Notes.

Short, atomic things — TILs, half-formed thoughts, citations to remember.

TIL: GRPO will silently collapse if your SFT policy is too confident

May 25, 2026

Training the SlotKeeper manager, GRPO from my SFT checkpoint flatlined to 0.0167.

The cause was upstream: the SFT eval-loss had dropped to 0.0525, leaving the policy near-deterministic. GRPO's advantage estimate needs variance across sampled completions — if every sample is basically identical, the gradient is ~0 and nothing learns.

Low loss is not the goal. A policy you intend to RL on needs entropy left in it.

What recovered the score: a DPO + Best-of-N path on preference pairs mined from the teacher. Next time I'd rejection-sample against teacher trajectories first, then SFT on that higher-entropy distribution before touching RL.