π0.5 finetuning ablations: 1 clean hour beats 17 hours of raw data scaling

DominiqueCAPaul · x · 2026-09-24

Two months of ablations on π0.5 finetunes for a real manufacturing task, reaching 98% success with all results, data and runs published. Key findings: 5x data only lifted 63%→76%; spreading 4h across five scenes beat 4h in the eval scene by 30pp; one clean, slower hour on top of 21h took 76%→90%; and just 1.7h total (1h clean data + 240 human-intervention rollouts) jumped 28%→88%. Quality and diversity beat pure scale.

Related event: π0.5 Fine-Tuning Study: 1 Hour of Clean Data Beats 17 Hours of Scale(6 posts)→

Original post →

More from Embodied

Embodied channel →