| { | |
| "schema_version": 1, | |
| "dataset": "rt1", | |
| "status": "released_inference", | |
| "codec": "rt1/codec", | |
| "action_ranges": "rt1/preprocessing/action_ranges.pt", | |
| "action_tokens_per_step": 13, | |
| "text_conditioning": { | |
| "enabled": true, | |
| "repo_id": "google-t5/t5-base", | |
| "revision": "a9723ea7f1b39c1eae772870f3b547bf6ef7e6c1", | |
| "layers": [ | |
| 3, | |
| 7, | |
| 11 | |
| ], | |
| "inner": 256, | |
| "width": 768, | |
| "max_tokens": 64, | |
| "bundled": false | |
| }, | |
| "initial_observations": 2, | |
| "memory": { | |
| "anchor_states": 1, | |
| "recent_states": 6, | |
| "ground_truth_refresh": false | |
| }, | |
| "evaluation": { | |
| "strategy": "per_frame_beam", | |
| "beam_width": 4, | |
| "horizon": 32, | |
| "visual_tokens_per_frame": 80, | |
| "valid_visual_vocab": 4375 | |
| }, | |
| "variants": { | |
| "sft": { | |
| "path": "rt1/models/sft", | |
| "method": "SFT", | |
| "updates": 50000, | |
| "text": true | |
| }, | |
| "main": { | |
| "path": "rt1/models/main", | |
| "method": "GDBS with semantic and visual feedback", | |
| "updates": 500, | |
| "text": true | |
| } | |
| } | |
| } | |