AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Fine-tuning GPT-OSS-20B for multilingual reasoning on Amazon SageMaker HyperPod

AWS Artificial Intelligence Blog · article · Oct 20, 2026 · UTC

Learn how we fine-tuned GPT-OSS-20B for multilingual reasoning on Amazon SageMaker HyperPod, and how to decide between supervised fine-tuning (SFT) and reinforcement learning with GRPO. SFT took reasoning-language accuracy from 22% to 100%, and GRPO added measurable gains where headroom existed.

Read original source ↗ Open in workspace

recordType
article
region
Global

Evidence & attribution

First collected: 2026-10-20T23:32:06.004Z. This is not the publication date.