Hugging Face TRL v1.13 Enables Training on 1M-Token Sequences

Hugging Face released TRL v1.13, enabling training on sequences of over 1 million tokens on a single 8-GPU H100 node, along with a full long-context guide addressing failures that emerge as sequences grow longer.

2026-09-13 ~ 2026-09-13 · 2 related posts

• HuggingFace TRL v1.13 ships long-context training beyond 1M tokens — SergioPaniego · 2026-09-13
• TRL v1.13 ships long-context training: 1M+ token sequences on a single 8-GPU H100 node — SergioPaniego · 2026-09-13