{ "results": { "anli_r1": { "acc": 0.33, "acc_stderr": 0.014876872027456732 }, "anli_r2": { "acc": 0.346, "acc_stderr": 0.015050266127564443 }, "anli_r3": { "acc": 0.3258333333333333, "acc_stderr": 0.01353542204341746 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.38268797942216715 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4753037243576977, "acc_stderr": 0.0049836910991109115, "acc_norm": 0.6382194781915953, "acc_norm_stderr": 0.004795337009118188 }, "rte": { "acc": 0.5487364620938628, "acc_stderr": 0.029953149241808946 }, "winogrande": { "acc": 0.5974743488555643, "acc_stderr": 0.013782866831703048 }, "storycloze_2016": { "acc": 0.7161945483698557, "acc_stderr": 0.010425696279730922 }, "boolq": { "acc": 0.6256880733944954, "acc_stderr": 0.008464246656443233 }, "arc_easy": { "acc": 0.6414141414141414, "acc_stderr": 0.009840882301225297, "acc_norm": 0.6136363636363636, "acc_norm_stderr": 0.009991296778159619 }, "arc_challenge": { "acc": 0.3148464163822526, "acc_stderr": 0.01357265770308495, "acc_norm": 0.3225255972696246, "acc_norm_stderr": 0.013659980894277366 }, "sciq": { "acc": 0.923, "acc_stderr": 0.008434580140240643, "acc_norm": 0.915, "acc_norm_stderr": 0.008823426366942314 }, "piqa": { "acc": 0.7584330794341676, "acc_stderr": 0.009986718001804467, "acc_norm": 0.7633297062023939, "acc_norm_stderr": 0.009916841655042809 } }, "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 } }