{ "results": { "anli_r1": { "acc": 0.336, "acc_stderr": 0.014944140233795018 }, "anli_r2": { "acc": 0.329, "acc_stderr": 0.01486539538592835 }, "anli_r3": { "acc": 0.35083333333333333, "acc_stderr": 0.013782212417178195 }, "cb": { "acc": 0.19642857142857142, "acc_stderr": 0.05357142857142858, "f1": 0.1668300653594771 }, "copa": { "acc": 0.78, "acc_stderr": 0.04163331998932263 }, "hellaswag": { "acc": 0.5200159330810595, "acc_stderr": 0.004985781620467012, "acc_norm": 0.6863174666401115, "acc_norm_stderr": 0.004630407476835209 }, "rte": { "acc": 0.48014440433212996, "acc_stderr": 0.0300727231673172 }, "winogrande": { "acc": 0.5864246250986582, "acc_stderr": 0.013840971763195306 }, "storycloze_2016": { "acc": 0.743452699091395, "acc_stderr": 0.01009926092771917 }, "boolq": { "acc": 0.6382262996941896, "acc_stderr": 0.008404238796949254 }, "arc_easy": { "acc": 0.6481481481481481, "acc_stderr": 0.009799078929868706, "acc_norm": 0.6212121212121212, "acc_norm_stderr": 0.00995373765654204 }, "arc_challenge": { "acc": 0.310580204778157, "acc_stderr": 0.013522292098053059, "acc_norm": 0.33532423208191126, "acc_norm_stderr": 0.013796182947785562 }, "sciq": { "acc": 0.913, "acc_stderr": 0.00891686663074591, "acc_norm": 0.889, "acc_norm_stderr": 0.009938701010583726 }, "piqa": { "acc": 0.7573449401523396, "acc_stderr": 0.0100020025697087, "acc_norm": 0.764961915125136, "acc_norm_stderr": 0.009893146688805319 } }, "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 } }