Identical GRPO recipe gives three small LLMs three different outcomes
One builder post-trained three from-scratch models — 353M, 316M, and 672M — with an identical SFT-then-GRPO recipe and got three different behaviors. Size didn't predict the outcome: the 353M partly recovered, the 316M lost ground on four of six tasks, and scaling to 672M didn't fix the fragility. None gained meaningfully on GSM8K, so the arithmetic reward didn't transfer to word-problem reasoning.