YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

pi05_franka_pickplace checkpoint

  • openpi config: pi05_franka_pickplace (pi-0.5, warm-start gs://openpi-assets/checkpoints/pi05_droid)
  • dataset: Sumo00048/pi05_franka_teleop (24 train episodes; ep 24 held out for val)
  • training step: 40000
  • val loss (held-out ep, flow-matching): None
  • train loss (sample): 0.0034

Note: flow-matching val loss is a weak proxy for policy quality; final selection should be by closed-loop rollout success.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support