| { | |
| "results": { | |
| "anli_r1": { | |
| "acc": 0.344, | |
| "acc_stderr": 0.015029633724408945 | |
| }, | |
| "anli_r2": { | |
| "acc": 0.365, | |
| "acc_stderr": 0.0152317762262649 | |
| }, | |
| "anli_r3": { | |
| "acc": 0.3333333333333333, | |
| "acc_stderr": 0.013613950010225612 | |
| }, | |
| "cb": { | |
| "acc": 0.44642857142857145, | |
| "acc_stderr": 0.06703189227942398, | |
| "f1": 0.428030303030303 | |
| }, | |
| "copa": { | |
| "acc": 0.74, | |
| "acc_stderr": 0.04408440022768079 | |
| }, | |
| "hellaswag": { | |
| "acc": 0.4431388169687313, | |
| "acc_stderr": 0.004957410545559414, | |
| "acc_norm": 0.58105954989046, | |
| "acc_norm_stderr": 0.004923772581848488 | |
| }, | |
| "rte": { | |
| "acc": 0.48736462093862815, | |
| "acc_stderr": 0.030086851767188564 | |
| }, | |
| "winogrande": { | |
| "acc": 0.5556432517758485, | |
| "acc_stderr": 0.013965196769083555 | |
| }, | |
| "storycloze_2016": { | |
| "acc": 0.6916087653661144, | |
| "acc_stderr": 0.010679734445487801 | |
| }, | |
| "boolq": { | |
| "acc": 0.5314984709480123, | |
| "acc_stderr": 0.00872768484861531 | |
| }, | |
| "arc_easy": { | |
| "acc": 0.6077441077441077, | |
| "acc_stderr": 0.010018744689650043, | |
| "acc_norm": 0.6022727272727273, | |
| "acc_norm_stderr": 0.010042861602178056 | |
| }, | |
| "arc_challenge": { | |
| "acc": 0.2858361774744027, | |
| "acc_stderr": 0.013203196088537369, | |
| "acc_norm": 0.3037542662116041, | |
| "acc_norm_stderr": 0.01343890918477876 | |
| }, | |
| "sciq": { | |
| "acc": 0.913, | |
| "acc_stderr": 0.008916866630745923, | |
| "acc_norm": 0.911, | |
| "acc_norm_stderr": 0.009008893392651518 | |
| }, | |
| "piqa": { | |
| "acc": 0.7323177366702938, | |
| "acc_stderr": 0.010330111189370429, | |
| "acc_norm": 0.735038084874864, | |
| "acc_norm_stderr": 0.010296557993316044 | |
| } | |
| }, | |
| "versions": { | |
| "anli_r1": 0, | |
| "anli_r2": 0, | |
| "anli_r3": 0, | |
| "cb": 1, | |
| "copa": 0, | |
| "hellaswag": 0, | |
| "rte": 0, | |
| "winogrande": 0, | |
| "storycloze_2016": 0, | |
| "boolq": 1, | |
| "arc_easy": 0, | |
| "arc_challenge": 0, | |
| "sciq": 0, | |
| "piqa": 0 | |
| } | |
| } |