{ "results": { "anli_r1": { "acc": 0.312, "acc_stderr": 0.014658474370509007 }, "anli_r2": { "acc": 0.342, "acc_stderr": 0.01500870618212173 }, "anli_r3": { "acc": 0.32166666666666666, "acc_stderr": 0.013490095282989521 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.3971014492753624 }, "copa": { "acc": 0.72, "acc_stderr": 0.04512608598542127 }, "hellaswag": { "acc": 0.3690499900418243, "acc_stderr": 0.0048156131443854, "acc_norm": 0.4477195777733519, "acc_norm_stderr": 0.004962429881904027 }, "rte": { "acc": 0.47653429602888087, "acc_stderr": 0.03006330041190266 }, "winogrande": { "acc": 0.5438042620363063, "acc_stderr": 0.013998453610924324 }, "storycloze_2016": { "acc": 0.6413682522715125, "acc_stderr": 0.011090657465688191 }, "boolq": { "acc": 0.5256880733944954, "acc_stderr": 0.008733506027183658 }, "arc_easy": { "acc": 0.5475589225589226, "acc_stderr": 0.01021326586017139, "acc_norm": 0.5256734006734006, "acc_norm_stderr": 0.010246249665591229 }, "arc_challenge": { "acc": 0.2235494880546075, "acc_stderr": 0.012174896631202607, "acc_norm": 0.26023890784982934, "acc_norm_stderr": 0.012821930225112556 }, "sciq": { "acc": 0.89, "acc_stderr": 0.009899393819724444, "acc_norm": 0.889, "acc_norm_stderr": 0.009938701010583726 }, "piqa": { "acc": 0.7034820457018498, "acc_stderr": 0.010656078922661153, "acc_norm": 0.7029379760609358, "acc_norm_stderr": 0.010661725404814778 } }, "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 } }