{ "results": { "anli_r1": { "acc": 0.34, "acc_stderr": 0.014987482264363937 }, "anli_r2": { "acc": 0.327, "acc_stderr": 0.014842213153411242 }, "anli_r3": { "acc": 0.33416666666666667, "acc_stderr": 0.013622434813136783 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.32523809523809527 }, "copa": { "acc": 0.74, "acc_stderr": 0.04408440022768079 }, "hellaswag": { "acc": 0.4448317068313085, "acc_stderr": 0.00495931519801116, "acc_norm": 0.578370842461661, "acc_norm_stderr": 0.004928105880776072 }, "rte": { "acc": 0.5451263537906137, "acc_stderr": 0.029973636495415255 }, "winogrande": { "acc": 0.5588003157063931, "acc_stderr": 0.013954975072834731 }, "storycloze_2016": { "acc": 0.7033671833244255, "acc_stderr": 0.01056281918156322 }, "boolq": { "acc": 0.5813455657492355, "acc_stderr": 0.008628545022868549 }, "arc_easy": { "acc": 0.5951178451178452, "acc_stderr": 0.010072423960395703, "acc_norm": 0.561026936026936, "acc_norm_stderr": 0.01018307601297206 }, "arc_challenge": { "acc": 0.27303754266211605, "acc_stderr": 0.013019332762635746, "acc_norm": 0.2841296928327645, "acc_norm_stderr": 0.013179442447653886 }, "sciq": { "acc": 0.862, "acc_stderr": 0.0109121526325044, "acc_norm": 0.828, "acc_norm_stderr": 0.011939788882495321 }, "piqa": { "acc": 0.7285092491838956, "acc_stderr": 0.010376251176596137, "acc_norm": 0.735582154515778, "acc_norm_stderr": 0.01028978724476716 } }, "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 } }