{ "results": { "anli_r1": { "acc": 0.324, "acc_stderr": 0.014806864733738857 }, "anli_r2": { "acc": 0.338, "acc_stderr": 0.014965960710224498 }, "anli_r3": { "acc": 0.3525, "acc_stderr": 0.013797164918918362 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813057, "f1": 0.25882352941176473 }, "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036623 }, "hellaswag": { "acc": 0.45907189802828124, "acc_stderr": 0.004973036453863711, "acc_norm": 0.6099382593108943, "acc_norm_stderr": 0.004867670042866713 }, "rte": { "acc": 0.5234657039711191, "acc_stderr": 0.030063300411902652 }, "winogrande": { "acc": 0.5777426992896606, "acc_stderr": 0.013881582030658552 }, "storycloze_2016": { "acc": 0.7151256012827365, "acc_stderr": 0.010437513986611718 }, "boolq": { "acc": 0.5730886850152905, "acc_stderr": 0.008651119069643816 }, "arc_easy": { "acc": 0.6043771043771043, "acc_stderr": 0.010033741393430983, "acc_norm": 0.5749158249158249, "acc_norm_stderr": 0.010143966195717845 }, "arc_challenge": { "acc": 0.2841296928327645, "acc_stderr": 0.013179442447653887, "acc_norm": 0.3037542662116041, "acc_norm_stderr": 0.01343890918477876 }, "sciq": { "acc": 0.836, "acc_stderr": 0.011715000693181331, "acc_norm": 0.791, "acc_norm_stderr": 0.012864077288499337 }, "piqa": { "acc": 0.7480957562568009, "acc_stderr": 0.010128421335088683, "acc_norm": 0.7573449401523396, "acc_norm_stderr": 0.01000200256970869 } }, "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 } }