{ "results": { "anli_r1": { "acc": 0.329, "acc_stderr": 0.014865395385928366 }, "anli_r2": { "acc": 0.329, "acc_stderr": 0.014865395385928364 }, "anli_r3": { "acc": 0.3458333333333333, "acc_stderr": 0.013736245342311012 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.1940928270042194 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.45429197371041624, "acc_stderr": 0.00496888813029007, "acc_norm": 0.5936068512248556, "acc_norm_stderr": 0.004901558132335521 }, "rte": { "acc": 0.5342960288808665, "acc_stderr": 0.030025579819366426 }, "winogrande": { "acc": 0.5619573796369376, "acc_stderr": 0.013944181296470804 }, "storycloze_2016": { "acc": 0.7108498129342598, "acc_stderr": 0.010484068799942079 }, "boolq": { "acc": 0.6241590214067279, "acc_stderr": 0.008471147248160112 }, "arc_easy": { "acc": 0.5652356902356902, "acc_stderr": 0.010172083670402784, "acc_norm": 0.5130471380471381, "acc_norm_stderr": 0.01025628992505844 }, "arc_challenge": { "acc": 0.2627986348122867, "acc_stderr": 0.012862523175351333, "acc_norm": 0.28242320819112626, "acc_norm_stderr": 0.013155456884097222 }, "sciq": { "acc": 0.826, "acc_stderr": 0.011994493230973428, "acc_norm": 0.726, "acc_norm_stderr": 0.014111099288259588 }, "piqa": { "acc": 0.7372143634385201, "acc_stderr": 0.010269354068140767, "acc_norm": 0.7459194776931447, "acc_norm_stderr": 0.010157271999135051 } }, "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 } }