Loading dataset... Smith300DA3Dataset: loading 9 sessions dataset_20260512_161202: 123 frames loaded dataset_20260512_161418: 107 frames loaded dataset_20260512_161822: 123 frames loaded dataset_20260512_162057: 102 frames loaded dataset_20260512_162940: 138 frames loaded dataset_20260512_163220: 91 frames loaded dataset_20260512_163457: 97 frames loaded dataset_20260516_163657: 133 frames loaded extra_singleview_capture: 616 frames loaded Smith300DA3Dataset ready: 62 eps, 1530 frames, 1468 samples, rgb=4.66 GB, depth=1.55 GB Train: 1395 Val: 73 Building model... [INFO ] using MLP layer as FFN Loading weights from local directory Trainable: 25,932,928 Epoch 5: 53%|█████▎ | 93/174 [00:24<00:38, 2.13it/s, d=0.025, h=9.892, w_d=36, w_h=0.099] Epoch 0: val_h=11.1064 val_d=0.0534 val_pix=147.6px ✓ best (val_h=11.1064) Epoch 1: val_h=10.8256 val_d=0.0440 val_pix=94.0px ✓ best (val_h=10.8256) Epoch 2: val_h=10.5672 val_d=0.0431 val_pix=97.6px ✓ best (val_h=10.5672) Epoch 3: val_h=10.3489 val_d=0.0381 val_pix=102.2px ✓ best (val_h=10.3489) Epoch 4: val_h=10.1471 val_d=0.0375 val_pix=92.3px ✓ best (val_h=10.1471)