mliu48/telearms-yam-cube-v5-exp-random-1500
bimanual_yam • Updated • 15k episodes • 225
Final checkpoint: step 160,000.
StarVLA QwenOFT (Qwen2.5-VL-3B-Instruct backbone, full fine-tune
including the vision encoder) on mliu48/telearms-yam-cube-v5-exp-random-1500:
15,000 simulated bimanual YAM demonstrations (10 tasks x 1,500), 14,340,545 frames at 30 Hz, three 224x224
cameras (front, left wrist, right wrist), no domain randomization.
One of five StarVLA action heads trained on this data with the same backbone and the same 15.36M-sample budget as the pi0.5 and MolmoAct2 Random-1500 runs.
starVLA_dev @ 13d8ad4 plus a local examples/TelearmsYAM data config
(cameras front/left/right, mixture telearms_v5_random_1500, robot type telearms_yam_sim).dataset_statistics.json holds the statistics needed to
un-normalize predicted actions.pytorch_model.pt (StarVLA state dict), config.yaml / config.full.yaml (resolved training config).Base model
Qwen/Qwen2.5-VL-3B-Instruct