{ "results": { "anli_r1": { "acc": 0.35, "acc_stderr": 0.015090650341444236 }, "anli_r2": { "acc": 0.32, "acc_stderr": 0.01475865230357488 }, "anli_r3": { "acc": 0.33416666666666667, "acc_stderr": 0.013622434813136783 }, "cb": { "acc": 0.44642857142857145, "acc_stderr": 0.067031892279424, "f1": 0.30886196246139225 }, "copa": { "acc": 0.61, "acc_stderr": 0.04902071300001975 }, "hellaswag": { "acc": 0.2802230631348337, "acc_stderr": 0.004481902637505665, "acc_norm": 0.2960565624377614, "acc_norm_stderr": 0.00455583246277459 }, "rte": { "acc": 0.4548736462093863, "acc_stderr": 0.029973636495415252 }, "winogrande": { "acc": 0.505130228887135, "acc_stderr": 0.014051745961790516 }, "storycloze_2016": { "acc": 0.569748797434527, "acc_stderr": 0.011449379528209637 }, "boolq": { "acc": 0.5675840978593272, "acc_stderr": 0.008664798701065799 }, "arc_easy": { "acc": 0.39436026936026936, "acc_stderr": 0.010028176038392995, "acc_norm": 0.35395622895622897, "acc_norm_stderr": 0.00981237064417441 }, "arc_challenge": { "acc": 0.19539249146757678, "acc_stderr": 0.01158690718995291, "acc_norm": 0.22781569965870307, "acc_norm_stderr": 0.012256708602326903 }, "sciq": { "acc": 0.681, "acc_stderr": 0.01474640486547349, "acc_norm": 0.645, "acc_norm_stderr": 0.015139491543780532 }, "piqa": { "acc": 0.6311207834602829, "acc_stderr": 0.011257546676908804, "acc_norm": 0.6207834602829162, "acc_norm_stderr": 0.011320331012905077 } }, "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 } }