{ "results": { "anli_r1": { "acc": 0.336, "acc_stderr": 0.014944140233795027 }, "anli_r2": { "acc": 0.329, "acc_stderr": 0.014865395385928364 }, "anli_r3": { "acc": 0.34833333333333333, "acc_stderr": 0.013759437498874072 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.0672477765493766, "f1": 0.3271604938271605 }, "copa": { "acc": 0.78, "acc_stderr": 0.04163331998932261 }, "hellaswag": { "acc": 0.47410874327823144, "acc_stderr": 0.004983087049281741, "acc_norm": 0.619896434973113, "acc_norm_stderr": 0.004844199910173022 }, "rte": { "acc": 0.5451263537906137, "acc_stderr": 0.029973636495415252 }, "winogrande": { "acc": 0.585635359116022, "acc_stderr": 0.013844846232268563 }, "storycloze_2016": { "acc": 0.726349545697488, "acc_stderr": 0.0103097970944971 }, "boolq": { "acc": 0.6201834862385321, "acc_stderr": 0.008488668235778617 }, "arc_easy": { "acc": 0.5909090909090909, "acc_stderr": 0.010088775152615786, "acc_norm": 0.5311447811447811, "acc_norm_stderr": 0.010239860250021745 }, "arc_challenge": { "acc": 0.2713310580204778, "acc_stderr": 0.01299380772754579, "acc_norm": 0.295221843003413, "acc_norm_stderr": 0.013329750293382318 }, "sciq": { "acc": 0.843, "acc_stderr": 0.01151014697923019, "acc_norm": 0.755, "acc_norm_stderr": 0.013607356839598123 }, "piqa": { "acc": 0.7595212187159956, "acc_stderr": 0.009971345364651078, "acc_norm": 0.764417845484222, "acc_norm_stderr": 0.009901067586473883 } }, "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 } }