| { |
| "model": "decider-4b-v2.1-tr-lora", |
| "path": "/workspace/laya/decider_run/model", |
| "revision": "eb5fbdfc9448473ec25e399882912863afbdb70e", |
| "fp8_layers": 0, |
| "limit": 0, |
| "skipped": {}, |
| "seconds": 3595, |
| "report": { |
| "all": { |
| "n": 101716, |
| "accuracy": 0.7962, |
| "brier": 0.2653, |
| "nll": 0.53, |
| "ece": 0.0203 |
| }, |
| "source/bev_tr": { |
| "n": 46320, |
| "accuracy": 0.8382, |
| "brier": 0.2215, |
| "nll": 0.3964, |
| "ece": 0.0092 |
| }, |
| "source/bev_tr/choice": { |
| "n": 18808, |
| "accuracy": 0.8465, |
| "brier": 0.214, |
| "nll": 0.3982, |
| "ece": 0.009 |
| }, |
| "source/bev_tr/noul": { |
| "n": 17572, |
| "accuracy": 0.9029, |
| "brier": 0.1396, |
| "nll": 0.2281, |
| "ece": 0.0099 |
| }, |
| "source/bev_tr/score": { |
| "n": 9940, |
| "accuracy": 0.708, |
| "brier": 0.3805, |
| "nll": 0.6904, |
| "ece": 0.018 |
| }, |
| "source/bev_tr_en": { |
| "n": 5766, |
| "accuracy": 0.7542, |
| "brier": 0.3138, |
| "nll": 0.5674, |
| "ece": 0.0126 |
| }, |
| "source/bev_tr_en/choice": { |
| "n": 2386, |
| "accuracy": 0.7812, |
| "brier": 0.3036, |
| "nll": 0.5762, |
| "ece": 0.0289 |
| }, |
| "source/bev_tr_en/noul": { |
| "n": 2117, |
| "accuracy": 0.8734, |
| "brier": 0.1665, |
| "nll": 0.2696, |
| "ece": 0.0262 |
| }, |
| "source/bev_tr_en/score": { |
| "n": 1263, |
| "accuracy": 0.5036, |
| "brier": 0.5799, |
| "nll": 1.0501, |
| "ece": 0.0373 |
| }, |
| "source/beyazperde_tr": { |
| "n": 5000, |
| "accuracy": 0.6336, |
| "brier": 0.4769, |
| "nll": 0.8667, |
| "ece": 0.0402 |
| }, |
| "source/beyazperde_tr/score": { |
| "n": 5000, |
| "accuracy": 0.6336, |
| "brier": 0.4769, |
| "nll": 0.8667, |
| "ece": 0.0402 |
| }, |
| "source/jev_bench_tr": { |
| "n": 22773, |
| "accuracy": 0.7078, |
| "brier": 0.3407, |
| "nll": 0.821, |
| "ece": 0.051 |
| }, |
| "source/jev_bench_tr/choice": { |
| "n": 9599, |
| "accuracy": 0.7316, |
| "brier": 0.2873, |
| "nll": 0.9497, |
| "ece": 0.0593 |
| }, |
| "source/jev_bench_tr/noul": { |
| "n": 7174, |
| "accuracy": 0.8246, |
| "brier": 0.2226, |
| "nll": 0.4021, |
| "ece": 0.0458 |
| }, |
| "source/jev_bench_tr/score": { |
| "n": 6000, |
| "accuracy": 0.5298, |
| "brier": 0.5675, |
| "nll": 1.1159, |
| "ece": 0.0453 |
| }, |
| "source/jev_bench_tr_en": { |
| "n": 2000, |
| "accuracy": 0.7705, |
| "brier": 0.2689, |
| "nll": 0.6936, |
| "ece": 0.0351 |
| }, |
| "source/jev_bench_tr_en/choice": { |
| "n": 839, |
| "accuracy": 0.7926, |
| "brier": 0.2156, |
| "nll": 0.8206, |
| "ece": 0.0399 |
| }, |
| "source/jev_bench_tr_en/noul": { |
| "n": 635, |
| "accuracy": 0.8945, |
| "brier": 0.1434, |
| "nll": 0.2821, |
| "ece": 0.0208 |
| }, |
| "source/jev_bench_tr_en/score": { |
| "n": 526, |
| "accuracy": 0.5856, |
| "brier": 0.5053, |
| "nll": 0.988, |
| "ece": 0.0867 |
| }, |
| "source/massive_tr": { |
| "n": 2974, |
| "accuracy": 0.8705, |
| "brier": 0.1941, |
| "nll": 0.5568, |
| "ece": 0.0362 |
| }, |
| "source/massive_tr/choice": { |
| "n": 2974, |
| "accuracy": 0.8705, |
| "brier": 0.1941, |
| "nll": 0.5568, |
| "ece": 0.0362 |
| }, |
| "source/squad_tr": { |
| "n": 11873, |
| "accuracy": 0.8619, |
| "brier": 0.2028, |
| "nll": 0.3322, |
| "ece": 0.0168 |
| }, |
| "source/squad_tr/noul": { |
| "n": 11873, |
| "accuracy": 0.8619, |
| "brier": 0.2028, |
| "nll": 0.3322, |
| "ece": 0.0168 |
| }, |
| "source/xnli_tr": { |
| "n": 5010, |
| "accuracy": 0.8315, |
| "brier": 0.2488, |
| "nll": 0.4509, |
| "ece": 0.0151 |
| }, |
| "source/xnli_tr/choice": { |
| "n": 5010, |
| "accuracy": 0.8315, |
| "brier": 0.2488, |
| "nll": 0.4509, |
| "ece": 0.0151 |
| }, |
| "type/choice": { |
| "n": 39616, |
| "accuracy": 0.8135, |
| "brier": 0.2401, |
| "nll": 0.5701, |
| "ece": 0.0214 |
| }, |
| "type/noul": { |
| "n": 39371, |
| "accuracy": 0.8746, |
| "brier": 0.1753, |
| "nll": 0.2943, |
| "ece": 0.0177 |
| }, |
| "type/score": { |
| "n": 22729, |
| "accuracy": 0.6304, |
| "brier": 0.465, |
| "nll": 0.8684, |
| "ece": 0.0235 |
| }, |
| "workflow/bev_tr/Browser interaction": { |
| "n": 286, |
| "accuracy": 0.8497, |
| "brier": 0.1897, |
| "nll": 0.3352, |
| "ece": 0.0394 |
| }, |
| "workflow/bev_tr/Civic and safety operations": { |
| "n": 261, |
| "accuracy": 0.7701, |
| "brier": 0.3154, |
| "nll": 0.6527, |
| "ece": 0.0616 |
| }, |
| "workflow/bev_tr/Contract evidence": { |
| "n": 320, |
| "accuracy": 0.8375, |
| "brier": 0.2302, |
| "nll": 0.4253, |
| "ece": 0.0491 |
| }, |
| "workflow/bev_tr/Engagement and ranking": { |
| "n": 82, |
| "accuracy": 0.6463, |
| "brier": 0.4851, |
| "nll": 0.6918, |
| "ece": 0.1104 |
| }, |
| "workflow/bev_tr/Financial reporting and banking": { |
| "n": 1740, |
| "accuracy": 0.8264, |
| "brier": 0.2371, |
| "nll": 0.4219, |
| "ece": 0.0215 |
| }, |
| "workflow/bev_tr/Game-state decisions": { |
| "n": 2039, |
| "accuracy": 0.8794, |
| "brier": 0.1475, |
| "nll": 0.2267, |
| "ece": 0.0145 |
| }, |
| "workflow/bev_tr/Reading comprehension": { |
| "n": 1422, |
| "accuracy": 0.8643, |
| "brier": 0.1945, |
| "nll": 0.3188, |
| "ece": 0.0163 |
| }, |
| "workflow/bev_tr/Response preference and quality": { |
| "n": 3176, |
| "accuracy": 0.6382, |
| "brier": 0.4731, |
| "nll": 0.8563, |
| "ece": 0.0269 |
| }, |
| "workflow/bev_tr/Retail, product, and shopping": { |
| "n": 6601, |
| "accuracy": 0.9365, |
| "brier": 0.0922, |
| "nll": 0.1653, |
| "ece": 0.0122 |
| }, |
| "workflow/bev_tr/Scientific and paper understanding": { |
| "n": 508, |
| "accuracy": 0.8346, |
| "brier": 0.248, |
| "nll": 0.4421, |
| "ece": 0.0278 |
| }, |
| "workflow/bev_tr/Sensory quality rating": { |
| "n": 260, |
| "accuracy": 0.4, |
| "brier": 0.6968, |
| "nll": 1.3241, |
| "ece": 0.0533 |
| }, |
| "workflow/bev_tr/Sentiment, emotion, and moderation": { |
| "n": 11526, |
| "accuracy": 0.8647, |
| "brier": 0.1892, |
| "nll": 0.3338, |
| "ece": 0.0152 |
| }, |
| "workflow/bev_tr/Software engineering and code": { |
| "n": 2039, |
| "accuracy": 0.7229, |
| "brier": 0.3732, |
| "nll": 0.7028, |
| "ece": 0.0368 |
| }, |
| "workflow/bev_tr/Software security": { |
| "n": 2240, |
| "accuracy": 0.6879, |
| "brier": 0.4086, |
| "nll": 0.7059, |
| "ece": 0.0458 |
| }, |
| "workflow/bev_tr/Spam detection": { |
| "n": 271, |
| "accuracy": 0.9779, |
| "brier": 0.0284, |
| "nll": 0.0569, |
| "ece": 0.0159 |
| }, |
| "workflow/bev_tr/Spatial and logical reasoning": { |
| "n": 8384, |
| "accuracy": 0.7832, |
| "brier": 0.3054, |
| "nll": 0.5545, |
| "ece": 0.0198 |
| }, |
| "workflow/bev_tr/Support and intent routing": { |
| "n": 2858, |
| "accuracy": 0.971, |
| "brier": 0.0462, |
| "nll": 0.087, |
| "ece": 0.011 |
| }, |
| "workflow/bev_tr/Tool and workflow decisions": { |
| "n": 2307, |
| "accuracy": 0.9866, |
| "brier": 0.0197, |
| "nll": 0.0423, |
| "ece": 0.0068 |
| }, |
| "workflow/bev_tr_en/Browser interaction": { |
| "n": 39, |
| "accuracy": 0.7692, |
| "brier": 0.2566, |
| "nll": 0.4157, |
| "ece": 0.1178 |
| }, |
| "workflow/bev_tr_en/Civic and safety operations": { |
| "n": 31, |
| "accuracy": 0.5484, |
| "brier": 0.5519, |
| "nll": 0.9665, |
| "ece": 0.2049 |
| }, |
| "workflow/bev_tr_en/Contract evidence": { |
| "n": 49, |
| "accuracy": 0.7959, |
| "brier": 0.3148, |
| "nll": 0.5499, |
| "ece": 0.1107 |
| }, |
| "workflow/bev_tr_en/Engagement and ranking": { |
| "n": 6, |
| "accuracy": 0.6667, |
| "brier": 0.4327, |
| "nll": 0.6113, |
| "ece": 0.278 |
| }, |
| "workflow/bev_tr_en/Financial reporting and banking": { |
| "n": 196, |
| "accuracy": 0.6531, |
| "brier": 0.4856, |
| "nll": 0.975, |
| "ece": 0.1033 |
| }, |
| "workflow/bev_tr_en/Game-state decisions": { |
| "n": 303, |
| "accuracy": 0.835, |
| "brier": 0.2434, |
| "nll": 0.4021, |
| "ece": 0.0929 |
| }, |
| "workflow/bev_tr_en/Reading comprehension": { |
| "n": 168, |
| "accuracy": 0.9048, |
| "brier": 0.1584, |
| "nll": 0.2737, |
| "ece": 0.0486 |
| }, |
| "workflow/bev_tr_en/Response preference and quality": { |
| "n": 389, |
| "accuracy": 0.5604, |
| "brier": 0.5324, |
| "nll": 0.9589, |
| "ece": 0.0574 |
| }, |
| "workflow/bev_tr_en/Retail, product, and shopping": { |
| "n": 902, |
| "accuracy": 0.6896, |
| "brier": 0.3378, |
| "nll": 0.5532, |
| "ece": 0.1003 |
| }, |
| "workflow/bev_tr_en/Scientific and paper understanding": { |
| "n": 66, |
| "accuracy": 0.7424, |
| "brier": 0.3035, |
| "nll": 0.5148, |
| "ece": 0.1262 |
| }, |
| "workflow/bev_tr_en/Sensory quality rating": { |
| "n": 37, |
| "accuracy": 0.2432, |
| "brier": 0.7863, |
| "nll": 1.5804, |
| "ece": 0.1299 |
| }, |
| "workflow/bev_tr_en/Sentiment, emotion, and moderation": { |
| "n": 1439, |
| "accuracy": 0.8457, |
| "brier": 0.202, |
| "nll": 0.3659, |
| "ece": 0.0443 |
| }, |
| "workflow/bev_tr_en/Software engineering and code": { |
| "n": 260, |
| "accuracy": 0.7077, |
| "brier": 0.3893, |
| "nll": 0.7283, |
| "ece": 0.076 |
| }, |
| "workflow/bev_tr_en/Software security": { |
| "n": 234, |
| "accuracy": 0.5556, |
| "brier": 0.5142, |
| "nll": 0.8403, |
| "ece": 0.0889 |
| }, |
| "workflow/bev_tr_en/Spam detection": { |
| "n": 23, |
| "accuracy": 1.0, |
| "brier": 0.0001, |
| "nll": 0.006, |
| "ece": 0.006 |
| }, |
| "workflow/bev_tr_en/Spatial and logical reasoning": { |
| "n": 1042, |
| "accuracy": 0.6823, |
| "brier": 0.4407, |
| "nll": 0.8513, |
| "ece": 0.0635 |
| }, |
| "workflow/bev_tr_en/Support and intent routing": { |
| "n": 310, |
| "accuracy": 0.9581, |
| "brier": 0.0834, |
| "nll": 0.1668, |
| "ece": 0.0519 |
| }, |
| "workflow/bev_tr_en/Tool and workflow decisions": { |
| "n": 272, |
| "accuracy": 0.9779, |
| "brier": 0.0379, |
| "nll": 0.074, |
| "ece": 0.0203 |
| }, |
| "workflow/beyazperde_tr": { |
| "n": 5000, |
| "accuracy": 0.6336, |
| "brier": 0.4769, |
| "nll": 0.8667, |
| "ece": 0.0402 |
| }, |
| "workflow/jev_bench_tr/arc_challenge": { |
| "n": 1000, |
| "accuracy": 0.833, |
| "brier": 0.2373, |
| "nll": 0.452, |
| "ece": 0.0305 |
| }, |
| "workflow/jev_bench_tr/banking77": { |
| "n": 1000, |
| "accuracy": 0.81, |
| "brier": 0.2667, |
| "nll": 0.6704, |
| "ece": 0.0496 |
| }, |
| "workflow/jev_bench_tr/boolq": { |
| "n": 1000, |
| "accuracy": 0.877, |
| "brier": 0.1889, |
| "nll": 0.3099, |
| "ece": 0.0233 |
| }, |
| "workflow/jev_bench_tr/chaosnli": { |
| "n": 1599, |
| "accuracy": 0.6373, |
| "brier": 0.2039, |
| "nll": 1.1669, |
| "ece": 0.1133 |
| }, |
| "workflow/jev_bench_tr/civil_comments": { |
| "n": 2000, |
| "accuracy": 0.863, |
| "brier": 0.1263, |
| "nll": 0.3793, |
| "ece": 0.0208 |
| }, |
| "workflow/jev_bench_tr/clinc150": { |
| "n": 1000, |
| "accuracy": 0.873, |
| "brier": 0.1986, |
| "nll": 0.6114, |
| "ece": 0.0333 |
| }, |
| "workflow/jev_bench_tr/fever_evidence": { |
| "n": 1000, |
| "accuracy": 0.926, |
| "brier": 0.1063, |
| "nll": 0.1935, |
| "ece": 0.0218 |
| }, |
| "workflow/jev_bench_tr/go_emotions": { |
| "n": 1000, |
| "accuracy": 0.496, |
| "brier": 0.3399, |
| "nll": 2.3234, |
| "ece": 0.1412 |
| }, |
| "workflow/jev_bench_tr/helpsteer2_helpfulness": { |
| "n": 1000, |
| "accuracy": 0.403, |
| "brier": 0.7142, |
| "nll": 1.3625, |
| "ece": 0.1558 |
| }, |
| "workflow/jev_bench_tr/helpsteer2_verbosity": { |
| "n": 1000, |
| "accuracy": 0.661, |
| "brier": 0.5088, |
| "nll": 0.9137, |
| "ece": 0.1524 |
| }, |
| "workflow/jev_bench_tr/ledgar": { |
| "n": 1000, |
| "accuracy": 0.678, |
| "brier": 0.4474, |
| "nll": 1.2384, |
| "ece": 0.0563 |
| }, |
| "workflow/jev_bench_tr/massive": { |
| "n": 1000, |
| "accuracy": 0.867, |
| "brier": 0.1986, |
| "nll": 0.5556, |
| "ece": 0.0434 |
| }, |
| "workflow/jev_bench_tr/measuring_hate_speech": { |
| "n": 1000, |
| "accuracy": 0.534, |
| "brier": 0.3917, |
| "nll": 1.1279, |
| "ece": 0.1391 |
| }, |
| "workflow/jev_bench_tr/mmlu": { |
| "n": 1000, |
| "accuracy": 0.615, |
| "brier": 0.5026, |
| "nll": 0.9645, |
| "ece": 0.0798 |
| }, |
| "workflow/jev_bench_tr/mnli": { |
| "n": 1000, |
| "accuracy": 0.832, |
| "brier": 0.2406, |
| "nll": 0.4346, |
| "ece": 0.0289 |
| }, |
| "workflow/jev_bench_tr/paws": { |
| "n": 1000, |
| "accuracy": 0.694, |
| "brier": 0.4599, |
| "nll": 0.7411, |
| "ece": 0.1698 |
| }, |
| "workflow/jev_bench_tr/sms_spam": { |
| "n": 800, |
| "accuracy": 0.9587, |
| "brier": 0.0616, |
| "nll": 0.1232, |
| "ece": 0.0165 |
| }, |
| "workflow/jev_bench_tr/sst5": { |
| "n": 1000, |
| "accuracy": 0.428, |
| "brier": 0.6809, |
| "nll": 1.2517, |
| "ece": 0.0952 |
| }, |
| "workflow/jev_bench_tr/strategyqa_closed": { |
| "n": 687, |
| "accuracy": 0.5429, |
| "brier": 0.5218, |
| "nll": 0.7334, |
| "ece": 0.1441 |
| }, |
| "workflow/jev_bench_tr/strategyqa_grounded": { |
| "n": 687, |
| "accuracy": 0.8049, |
| "brier": 0.2641, |
| "nll": 0.4067, |
| "ece": 0.0331 |
| }, |
| "workflow/jev_bench_tr/stsb": { |
| "n": 1000, |
| "accuracy": 0.51, |
| "brier": 0.634, |
| "nll": 1.2248, |
| "ece": 0.0975 |
| }, |
| "workflow/jev_bench_tr/yelp5": { |
| "n": 1000, |
| "accuracy": 0.643, |
| "brier": 0.4752, |
| "nll": 0.8146, |
| "ece": 0.0633 |
| }, |
| "workflow/jev_bench_tr_en/arc_challenge": { |
| "n": 91, |
| "accuracy": 0.9121, |
| "brier": 0.1091, |
| "nll": 0.1997, |
| "ece": 0.0625 |
| }, |
| "workflow/jev_bench_tr_en/banking77": { |
| "n": 71, |
| "accuracy": 0.8592, |
| "brier": 0.2199, |
| "nll": 0.5531, |
| "ece": 0.0805 |
| }, |
| "workflow/jev_bench_tr_en/boolq": { |
| "n": 80, |
| "accuracy": 0.9, |
| "brier": 0.1214, |
| "nll": 0.2017, |
| "ece": 0.0737 |
| }, |
| "workflow/jev_bench_tr_en/chaosnli": { |
| "n": 151, |
| "accuracy": 0.7086, |
| "brier": 0.1814, |
| "nll": 1.1407, |
| "ece": 0.1201 |
| }, |
| "workflow/jev_bench_tr_en/civil_comments": { |
| "n": 171, |
| "accuracy": 0.8655, |
| "brier": 0.14, |
| "nll": 0.3978, |
| "ece": 0.0587 |
| }, |
| "workflow/jev_bench_tr_en/clinc150": { |
| "n": 96, |
| "accuracy": 0.8854, |
| "brier": 0.1594, |
| "nll": 0.3886, |
| "ece": 0.0521 |
| }, |
| "workflow/jev_bench_tr_en/fever_evidence": { |
| "n": 91, |
| "accuracy": 0.967, |
| "brier": 0.0561, |
| "nll": 0.1315, |
| "ece": 0.0348 |
| }, |
| "workflow/jev_bench_tr_en/go_emotions": { |
| "n": 93, |
| "accuracy": 0.5269, |
| "brier": 0.323, |
| "nll": 2.3535, |
| "ece": 0.1604 |
| }, |
| "workflow/jev_bench_tr_en/helpsteer2_helpfulness": { |
| "n": 89, |
| "accuracy": 0.4831, |
| "brier": 0.6573, |
| "nll": 1.1603, |
| "ece": 0.1857 |
| }, |
| "workflow/jev_bench_tr_en/helpsteer2_verbosity": { |
| "n": 79, |
| "accuracy": 0.7089, |
| "brier": 0.4661, |
| "nll": 0.8944, |
| "ece": 0.1493 |
| }, |
| "workflow/jev_bench_tr_en/ledgar": { |
| "n": 70, |
| "accuracy": 0.7857, |
| "brier": 0.3543, |
| "nll": 0.8834, |
| "ece": 0.1722 |
| }, |
| "workflow/jev_bench_tr_en/massive": { |
| "n": 95, |
| "accuracy": 0.8526, |
| "brier": 0.207, |
| "nll": 0.73, |
| "ece": 0.0683 |
| }, |
| "workflow/jev_bench_tr_en/measuring_hate_speech": { |
| "n": 96, |
| "accuracy": 0.5729, |
| "brier": 0.3906, |
| "nll": 1.1441, |
| "ece": 0.187 |
| }, |
| "workflow/jev_bench_tr_en/mmlu": { |
| "n": 80, |
| "accuracy": 0.725, |
| "brier": 0.3559, |
| "nll": 0.6658, |
| "ece": 0.071 |
| }, |
| "workflow/jev_bench_tr_en/mnli": { |
| "n": 92, |
| "accuracy": 0.9348, |
| "brier": 0.1053, |
| "nll": 0.1974, |
| "ece": 0.0927 |
| }, |
| "workflow/jev_bench_tr_en/paws": { |
| "n": 80, |
| "accuracy": 0.8375, |
| "brier": 0.2238, |
| "nll": 0.3598, |
| "ece": 0.0984 |
| }, |
| "workflow/jev_bench_tr_en/sms_spam": { |
| "n": 82, |
| "accuracy": 1.0, |
| "brier": 0.0055, |
| "nll": 0.0164, |
| "ece": 0.0147 |
| }, |
| "workflow/jev_bench_tr_en/sst5": { |
| "n": 73, |
| "accuracy": 0.5205, |
| "brier": 0.5669, |
| "nll": 0.9347, |
| "ece": 0.0965 |
| }, |
| "workflow/jev_bench_tr_en/strategyqa_closed": { |
| "n": 60, |
| "accuracy": 0.8333, |
| "brier": 0.3338, |
| "nll": 0.5123, |
| "ece": 0.1264 |
| }, |
| "workflow/jev_bench_tr_en/strategyqa_grounded": { |
| "n": 71, |
| "accuracy": 0.8592, |
| "brier": 0.1958, |
| "nll": 0.3115, |
| "ece": 0.0442 |
| }, |
| "workflow/jev_bench_tr_en/stsb": { |
| "n": 90, |
| "accuracy": 0.5111, |
| "brier": 0.577, |
| "nll": 1.098, |
| "ece": 0.1376 |
| }, |
| "workflow/jev_bench_tr_en/yelp5": { |
| "n": 99, |
| "accuracy": 0.7071, |
| "brier": 0.4005, |
| "nll": 0.6957, |
| "ece": 0.1338 |
| }, |
| "workflow/massive_tr": { |
| "n": 2974, |
| "accuracy": 0.8705, |
| "brier": 0.1941, |
| "nll": 0.5568, |
| "ece": 0.0362 |
| }, |
| "workflow/squad_tr": { |
| "n": 11873, |
| "accuracy": 0.8619, |
| "brier": 0.2028, |
| "nll": 0.3322, |
| "ece": 0.0168 |
| }, |
| "workflow/xnli_tr": { |
| "n": 5010, |
| "accuracy": 0.8315, |
| "brier": 0.2488, |
| "nll": 0.4509, |
| "ece": 0.0151 |
| }, |
| "squad_tr/answerability": { |
| "auroc": 0.9397, |
| "acc_answerable": 0.9379, |
| "acc_unanswerable": 0.783 |
| } |
| }, |
| "train_key": "411bcda4c97e6b5b" |
| } |
