{ "results": { "anli_r1": { "acc": 0.337, "acc_stderr": 0.014955087918653605 }, "anli_r2": { "acc": 0.339, "acc_stderr": 0.014976758771620345 }, "anli_r3": { "acc": 0.33, "acc_stderr": 0.013579531277800923 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.32751039809863336 }, "copa": { "acc": 0.78, "acc_stderr": 0.04163331998932261 }, "hellaswag": { "acc": 0.4508066122286397, "acc_stderr": 0.004965572246803864, "acc_norm": 0.5974905397331209, "acc_norm_stderr": 0.004894012555642632 }, "rte": { "acc": 0.5018050541516246, "acc_stderr": 0.030096267148976626 }, "winogrande": { "acc": 0.5611681136543015, "acc_stderr": 0.013946933444507032 }, "storycloze_2016": { "acc": 0.7001603420630679, "acc_stderr": 0.010595525174558598 }, "boolq": { "acc": 0.618348623853211, "acc_stderr": 0.008496550741178263 }, "arc_easy": { "acc": 0.63510101010101, "acc_stderr": 0.009878157021155649, "acc_norm": 0.625, "acc_norm_stderr": 0.009933992677987828 }, "arc_challenge": { "acc": 0.2901023890784983, "acc_stderr": 0.01326157367752076, "acc_norm": 0.3174061433447099, "acc_norm_stderr": 0.01360223908803817 }, "sciq": { "acc": 0.905, "acc_stderr": 0.009276910103103317, "acc_norm": 0.906, "acc_norm_stderr": 0.009233052000787735 }, "piqa": { "acc": 0.7470076169749728, "acc_stderr": 0.01014288869886246, "acc_norm": 0.7486398258977149, "acc_norm_stderr": 0.01012115601681924 } }, "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 } }