Views
No views yet
place_empty_cup (50 ep, single instruction)place_empty_cup task from RoboTwin 2.0 (demo_clean config), starting from the lerobot/smolvla_robotwin base checkpoint.arrow-hf/smolvla-robotwin-place-empty-cup-300ep (300-ep, 90% success). Trained with the same hyperparameters as the other 50-ep tasks in this benchmark for fair comparison.| Config | Value |
|---|---|
| Base checkpoint | lerobot/smolvla_robotwin |
| Training data | 50 RoboTwin demonstrations (subset of 300ep_A), single instruction |
| Batch size | 32 |
| Steps | 6000 |
| Optimizer | AdamW, lr=1e-4 |
| Scheduler | Cosine, warmup=300, decay=6000 |
| Chunk size | 50 |
| Final train loss | 0.005 |
demo_clean), 10 episodes, max_steps=400, action_chunk_exec=50, instruction "place the empty cup".| Variant | Data | Success rate |
|---|---|---|
| 50ep single (this model) | 50 | 70% |
| 50ep multi | 50 | 80% ⭐ |
| 300ep single | 300 | 90% |
place_object_basket).1from lerobot.policies.smolvla import SmolVLAPolicy
2policy = SmolVLAPolicy.from_pretrained("arrow-hf/smolvla-robotwin-place-empty-cup-50ep")action_chunk_exec=50 (full chunk).