| { | |
| "checked": { | |
| "dev": 300, | |
| "test": 1000, | |
| "train": 20480 | |
| }, | |
| "duplicate_prompts": 0, | |
| "families": { | |
| "dev": { | |
| "abstention:contact": 12, | |
| "abstention:label": 12, | |
| "abstention:location": 12, | |
| "abstention:quantity": 12, | |
| "abstention:time": 12, | |
| "constraints:0": 8, | |
| "constraints:1": 8, | |
| "constraints:2": 8, | |
| "constraints:3": 8, | |
| "constraints:4": 7, | |
| "constraints:5": 7, | |
| "constraints:6": 7, | |
| "constraints:7": 7, | |
| "dialogue:contact": 12, | |
| "dialogue:label": 12, | |
| "dialogue:location": 12, | |
| "dialogue:quantity": 12, | |
| "dialogue:time": 12, | |
| "grounded:contact": 12, | |
| "grounded:label": 12, | |
| "grounded:location": 12, | |
| "grounded:quantity": 12, | |
| "grounded:time": 12, | |
| "reasoning:0": 10, | |
| "reasoning:1": 10, | |
| "reasoning:2": 10, | |
| "reasoning:3": 10, | |
| "reasoning:4": 10, | |
| "reasoning:5": 10 | |
| }, | |
| "test": { | |
| "abstention:contact": 40, | |
| "abstention:label": 40, | |
| "abstention:location": 40, | |
| "abstention:quantity": 40, | |
| "abstention:time": 40, | |
| "constraints:0": 25, | |
| "constraints:1": 25, | |
| "constraints:2": 25, | |
| "constraints:3": 25, | |
| "constraints:4": 25, | |
| "constraints:5": 25, | |
| "constraints:6": 25, | |
| "constraints:7": 25, | |
| "dialogue:contact": 40, | |
| "dialogue:label": 40, | |
| "dialogue:location": 40, | |
| "dialogue:quantity": 40, | |
| "dialogue:time": 40, | |
| "grounded:contact": 40, | |
| "grounded:label": 40, | |
| "grounded:location": 40, | |
| "grounded:quantity": 40, | |
| "grounded:time": 40, | |
| "reasoning:0": 34, | |
| "reasoning:1": 34, | |
| "reasoning:2": 33, | |
| "reasoning:3": 33, | |
| "reasoning:4": 33, | |
| "reasoning:5": 33 | |
| }, | |
| "train": { | |
| "abstention:contact": 817, | |
| "abstention:label": 834, | |
| "abstention:location": 806, | |
| "abstention:quantity": 819, | |
| "abstention:time": 820, | |
| "constraints:0": 519, | |
| "constraints:1": 508, | |
| "constraints:2": 525, | |
| "constraints:3": 495, | |
| "constraints:4": 522, | |
| "constraints:5": 507, | |
| "constraints:6": 519, | |
| "constraints:7": 501, | |
| "dialogue:contact": 817, | |
| "dialogue:label": 834, | |
| "dialogue:location": 806, | |
| "dialogue:quantity": 819, | |
| "dialogue:time": 820, | |
| "grounded:contact": 817, | |
| "grounded:label": 834, | |
| "grounded:location": 806, | |
| "grounded:quantity": 819, | |
| "grounded:time": 820, | |
| "reasoning:0": 727, | |
| "reasoning:1": 538, | |
| "reasoning:2": 728, | |
| "reasoning:3": 738, | |
| "reasoning:4": 630, | |
| "reasoning:5": 735 | |
| } | |
| }, | |
| "text_only": true, | |
| "wrong_targets": 0 | |
| } | |