Open source Developer tools Infrastructure & hardware

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

AWS Machine Learning Mijanur Palash

Publication summary. The terms of AWS Machine Learning do not allow reproduction of the full article: read the complete text on the original website.

Source summary (English)

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 the full article

aws.amazon.com

View on AWS Machine Learning (new tab)

Topics

Share

X (new tab) LinkedIn (new tab) Facebook (new tab) Email

Related articles