WoWjx/so101-stack3-pi05-baseline

SO-101 Stack3 π0.5 baseline checkpoints

This public repository contains five deployment snapshots from one Stack3 fine-tuning run. Checkpoints are stored by optimizer step:

• checkpoints/002000
• checkpoints/004000
• checkpoints/006000
• checkpoints/008000
• checkpoints/010000

Each checkpoint directory contains the model weights, model configuration, tokenizer, and matching observation/action pre- and post-processors. The optimizer and training-resume state are not included in these deployment snapshots.

Training setup

• Robot: SO-101, single arm; front and wrist RGB cameras
• Observation state: 6 dimensions
• Action: 6 dimensions; first five arm-relative, gripper absolute
• Chunk size: 50; execution horizon: 10 actions
• Precision: BF16; batch size: 64
• Initialization: Stack2 π0.5 checkpoint 004228, followed by Stack3 full-chain fine-tuning
• Dataset: 64 Stack3 full-chain episodes (60,481 frames), all used for training; no held-out validation split
• Fine-tune learning rate: peak 1.25e-5, cosine decay to 1.25e-6, 1,000-step warmup
• Training completed: 10,000 optimizer updates

These are deployment candidates, not a claim of successful three-block stacking. The checkpoints have not been validated on the physical robot. Training loss does not establish real-world task success.

The Stack2 initialization was SO-101 Stack2 π0.5, checkpoint 004228. No OCBench, FurnitureBench, or OGBench trajectories were used. The Stack3 dataset and training environment are private and are not included in this repository.