{ "results": { "anli_r1": { "acc": 0.318, "acc_stderr": 0.014734079309311901 }, "anli_r2": { "acc": 0.354, "acc_stderr": 0.015129868238451772 }, "anli_r3": { "acc": 0.3525, "acc_stderr": 0.013797164918918366 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.06633634150359541, "f1": 0.3024109014675052 }, "copa": { "acc": 0.72, "acc_stderr": 0.04512608598542126 }, "hellaswag": { "acc": 0.45628360884286, "acc_stderr": 0.004970672651595843, "acc_norm": 0.5851424019119698, "acc_norm_stderr": 0.004916905095810849 }, "rte": { "acc": 0.5306859205776173, "acc_stderr": 0.03003973059219781 }, "winogrande": { "acc": 0.5595895816890292, "acc_stderr": 0.013952330311915591 }, "storycloze_2016": { "acc": 0.7108498129342598, "acc_stderr": 0.010484068799942074 }, "boolq": { "acc": 0.5522935779816514, "acc_stderr": 0.008697094687974059 }, "arc_easy": { "acc": 0.569023569023569, "acc_stderr": 0.010161552863493751, "acc_norm": 0.49747474747474746, "acc_norm_stderr": 0.01025965266878347 }, "arc_challenge": { "acc": 0.26109215017064846, "acc_stderr": 0.012835523909473848, "acc_norm": 0.2764505119453925, "acc_norm_stderr": 0.013069662474252425 }, "sciq": { "acc": 0.826, "acc_stderr": 0.01199449323097343, "acc_norm": 0.725, "acc_norm_stderr": 0.014127086556490526 }, "piqa": { "acc": 0.73449401523395, "acc_stderr": 0.010303308653024429, "acc_norm": 0.7421109902067464, "acc_norm_stderr": 0.010206956662056243 } }, "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 } }