Setting	Value
Dataset	`taewonkoo/push_cube_v2_rlds`
Optimizer step	10,000 / 20,000
Per-device batch size	4
Gradient accumulation	4
Effective batch size	16
Learning rate	1e-4
Scheduler	Cosine with 2,000 warmup steps
LoRA rank	32
Input images	2 (`front`, `top`)
Proprioception	Enabled, 6 dimensions
Action dimension	6
Action chunk length	8
Precision	BF16 on an RTX 3090

The RLDS dataset contains 50 trajectories and 13,679 transitions. Actions and proprioceptive states follow the six-motor SO-101 representation.

Checkpoint contents

model.safetensors: VLA model with the LoRA weights merged
lora_adapter/: trainable LoRA adapter
action_head--10000_checkpoint.pt: continuous action head
proprio_projector--10000_checkpoint.pt: proprioception projector
vla_extras--10000_checkpoint.pt: trainable VLA extras such as action queries
training_state--10000_checkpoint.pt: optimizer, scheduler, scaler, and RNG state
processor, tokenizer, configuration, and dataset statistics

The separate action head and proprio projector are required for the SO-101 continuous-control policy. The merged model.safetensors alone is not the complete policy.

Code

Use the SO-101-compatible training and inference code from:

https://github.com/TaewonKoo/VLA-Adapter-SO101

This is an intermediate training checkpoint, not the final 20,000-step model. Review the base model, dataset, and code licenses before redistribution or deployment. Validate the policy in simulation or a controlled robot workspace before operating physical hardware.

taewonkoo/VLA-Adapter-SO101-push-cube-step-10000

VLA-Adapter SO-101 Push Cube — Step 10,000

Training configuration

Checkpoint contents

Code

taewonkoo/
VLA-Adapter-SO101-push-cube-step-10000