{"slug": "hugging-face-fixes-trl-cispo-default-that-shrank-gradients-fivefold-in-its", "title": "Hugging Face fixes TRL CISPO default that shrank gradients fivefold in its reproduction", "summary": "Hugging Face shipped TRL v1.18.0 on November 13th, 2026, raising the CISPO default for the 'epsilon_high' setting to 5.0 after an inherited 0.2 ceiling clipped every on-policy importance weight to 0.2 when users left the parameter unset, shrinking gradients fivefold in its reproduction. The fix corrects a reinforcement-learning loss default that had been silently capping on-policy weights near 1.", "body_md": "# Hugging Face fixes TRL CISPO default that shrank gradients fivefold in its reproduction\n\n**Hugging Face's TRL v1.18.0 sets the CISPO default to 5.0 after an inherited 0.2 ceiling clipped on-policy weights near 1.**\n\n        By [RuntimeWire Staff](https://runtimewire.com/author/runtimewire-staff)\n        · Published \n\nHugging Face, co-founded by Clement Delangue, has corrected a default in TRL's CISPO reinforcement-learning loss that clipped every on-policy importance weight to 0.2 when users left 'epsilon_high' unset. The fix shipped in TRL v1.18.0 on November 13th, 2026, and raises the CISPO default for that setting to 5.0.…", "url": "https://wpnews.pro/news/hugging-face-fixes-trl-cispo-default-that-shrank-gradients-fivefold-in-its", "canonical_source": "https://runtimewire.com/article/hugging-face-trl-cispo-default-gradient-fix", "published_at": "2026-11-14 12:15:12+00:00", "updated_at": "2026-11-14 12:20:19.641732+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "ai-tools", "developer-tools"], "entities": ["Hugging Face", "TRL", "CISPO", "Clement Delangue"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/hugging-face-fixes-trl-cispo-default-that-shrank-gradients-fivefold-in-its", "markdown": "https://wpnews.pro/news/hugging-face-fixes-trl-cispo-default-that-shrank-gradients-fivefold-in-its.md", "text": "https://wpnews.pro/news/hugging-face-fixes-trl-cispo-default-that-shrank-gradients-fivefold-in-its.txt", "jsonld": "https://wpnews.pro/news/hugging-face-fixes-trl-cispo-default-that-shrank-gradients-fivefold-in-its.jsonld"}}