# Hugging Face fixes TRL CISPO default that shrank gradients fivefold in its reproduction

> Source: <https://runtimewire.com/article/hugging-face-trl-cispo-default-gradient-fix>
> Published: 2026-11-14 12:15:12+00:00

# Hugging Face fixes TRL CISPO default that shrank gradients fivefold in its reproduction

**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.**

        By [RuntimeWire Staff](https://runtimewire.com/author/runtimewire-staff)
        · Published 

Hugging 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.…