{ "results": { "anli_r1": { "acc": 0.316, "acc_stderr": 0.014709193056057121 }, "anli_r2": { "acc": 0.347, "acc_stderr": 0.015060472031706622 }, "anli_r3": { "acc": 0.3308333333333333, "acc_stderr": 0.013588208070709007 }, "cb": { "acc": 0.5178571428571429, "acc_stderr": 0.06737697508644647, "f1": 0.39707602339181286 }, "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036623 }, "hellaswag": { "acc": 0.47211710814578767, "acc_stderr": 0.004982016702445961, "acc_norm": 0.6292571200955985, "acc_norm_stderr": 0.004820166002253063 }, "rte": { "acc": 0.5234657039711191, "acc_stderr": 0.03006330041190266 }, "winogrande": { "acc": 0.5943172849250198, "acc_stderr": 0.013800206336014208 }, "storycloze_2016": { "acc": 0.7258150721539284, "acc_stderr": 0.010316062787590011 }, "boolq": { "acc": 0.6030581039755352, "acc_stderr": 0.008557276964675146 }, "arc_easy": { "acc": 0.6321548821548821, "acc_stderr": 0.00989492346445519, "acc_norm": 0.6123737373737373, "acc_norm_stderr": 0.009997307914447612 }, "arc_challenge": { "acc": 0.29948805460750855, "acc_stderr": 0.013385021637313562, "acc_norm": 0.31569965870307165, "acc_norm_stderr": 0.013582571095815291 }, "sciq": { "acc": 0.915, "acc_stderr": 0.008823426366942314, "acc_norm": 0.909, "acc_norm_stderr": 0.009099549538400241 }, "piqa": { "acc": 0.7611534276387377, "acc_stderr": 0.0099481203853375, "acc_norm": 0.7611534276387377, "acc_norm_stderr": 0.009948120385337484 } }, "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 } }