{ "results": { "anli_r1": { "acc": 0.318, "acc_stderr": 0.014734079309311903 }, "anli_r2": { "acc": 0.344, "acc_stderr": 0.015029633724408947 }, "anli_r3": { "acc": 0.30916666666666665, "acc_stderr": 0.013346684134591958 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.3583652618135376 }, "copa": { "acc": 0.7, "acc_stderr": 0.046056618647183814 }, "hellaswag": { "acc": 0.36436964748058154, "acc_stderr": 0.004802694106203663, "acc_norm": 0.44901414060944034, "acc_norm_stderr": 0.004963771168672096 }, "rte": { "acc": 0.48375451263537905, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.5209155485398579, "acc_stderr": 0.014040185494212943 }, "storycloze_2016": { "acc": 0.6365579903794762, "acc_stderr": 0.01112284144205971 }, "boolq": { "acc": 0.5596330275229358, "acc_stderr": 0.0086826356676869 }, "arc_easy": { "acc": 0.5488215488215489, "acc_stderr": 0.010210757101073475, "acc_norm": 0.5244107744107744, "acc_norm_stderr": 0.010247548905242272 }, "arc_challenge": { "acc": 0.22696245733788395, "acc_stderr": 0.01224049153613287, "acc_norm": 0.2568259385665529, "acc_norm_stderr": 0.0127669237941168 }, "sciq": { "acc": 0.886, "acc_stderr": 0.010055103435823328, "acc_norm": 0.876, "acc_norm_stderr": 0.010427498872343966 }, "piqa": { "acc": 0.7023939064200218, "acc_stderr": 0.010667353792388213, "acc_norm": 0.6991294885745375, "acc_norm_stderr": 0.010700745724145972 } }, "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 } }