Views
No views yet
fold_tea_towel).| Base model | nvidia/GR00T-N1.7-3B |
| Dataset | villekuosmanen/armnetbench_fold_tea_towel |
| Task | fold_tea_towel |
| Training | Isambard-AI GH200, batch 64, action horizon 16 |
| W&B project | groot1.7_fold_tea_towel |
| W&B run | qp91sjl0 |
| Step | Loss | Path |
|---|---|---|
| 6,000 | 0.0262 | checkpoints/6000/pretrained_model/ |
| 4,000 | 0.0432 | checkpoints/4000/pretrained_model/ |
1from pathlib import Path
2# Use checkpoints/<step>/pretrained_model/ with the GR00T inference stack
3ckpt = "pravsels/groot1.7_fold_tea_towel/checkpoints/6000/pretrained_model"