{ "results": { "anli_r1": { "acc": 0.342, "acc_stderr": 0.015008706182121728 }, "anli_r2": { "acc": 0.355, "acc_stderr": 0.015139491543780536 }, "anli_r3": { "acc": 0.37833333333333335, "acc_stderr": 0.014005754275030409 }, "cb": { "acc": 0.44642857142857145, "acc_stderr": 0.067031892279424, "f1": 0.3196581196581197 }, "copa": { "acc": 0.85, "acc_stderr": 0.035887028128263714 }, "hellaswag": { "acc": 0.5375423222465644, "acc_stderr": 0.004975696076240844, "acc_norm": 0.7148974307906791, "acc_norm_stderr": 0.004505406176606851 }, "rte": { "acc": 0.49458483754512633, "acc_stderr": 0.030094698123239966 }, "winogrande": { "acc": 0.6440410418310971, "acc_stderr": 0.013456740656273955 }, "storycloze_2016": { "acc": 0.7739176910742919, "acc_stderr": 0.009672970735149765 }, "boolq": { "acc": 0.6626911314984709, "acc_stderr": 0.008269171495741622 }, "arc_easy": { "acc": 0.6843434343434344, "acc_stderr": 0.00953701924556608, "acc_norm": 0.6788720538720538, "acc_norm_stderr": 0.009580787536986797 }, "arc_challenge": { "acc": 0.3583617747440273, "acc_stderr": 0.01401288333485986, "acc_norm": 0.3728668941979522, "acc_norm_stderr": 0.014131176760131162 }, "sciq": { "acc": 0.937, "acc_stderr": 0.0076870078762864245, "acc_norm": 0.931, "acc_norm_stderr": 0.008018934050315151 }, "piqa": { "acc": 0.7736670293797606, "acc_stderr": 0.009763294246879429, "acc_norm": 0.7894450489662677, "acc_norm_stderr": 0.009512378081238747 } }, "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 } }