{ "results": { "anli_r1": { "acc": 0.337, "acc_stderr": 0.014955087918653603 }, "anli_r2": { "acc": 0.33, "acc_stderr": 0.014876872027456734 }, "anli_r3": { "acc": 0.3383333333333333, "acc_stderr": 0.01366414400661827 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.26694444444444443 }, "copa": { "acc": 0.73, "acc_stderr": 0.04461960433384741 }, "hellaswag": { "acc": 0.46285600477992433, "acc_stderr": 0.004975993795562032, "acc_norm": 0.6013742282413862, "acc_norm_stderr": 0.004886147907627405 }, "rte": { "acc": 0.5740072202166066, "acc_stderr": 0.029764956741777645 }, "winogrande": { "acc": 0.5816890292028414, "acc_stderr": 0.013863669961195892 }, "storycloze_2016": { "acc": 0.709246392303581, "acc_stderr": 0.010501233625213081 }, "boolq": { "acc": 0.6076452599388379, "acc_stderr": 0.008539983838167734 }, "arc_easy": { "acc": 0.5774410774410774, "acc_stderr": 0.01013597822298108, "acc_norm": 0.5290404040404041, "acc_norm_stderr": 0.010242463826395614 }, "arc_challenge": { "acc": 0.2721843003412969, "acc_stderr": 0.013006600406423706, "acc_norm": 0.30119453924914674, "acc_norm_stderr": 0.013406741767847632 }, "sciq": { "acc": 0.818, "acc_stderr": 0.012207580637662157, "acc_norm": 0.737, "acc_norm_stderr": 0.013929286594259734 }, "piqa": { "acc": 0.7437431991294886, "acc_stderr": 0.010185787831565062, "acc_norm": 0.749727965179543, "acc_norm_stderr": 0.010106561880089768 } }, "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 } }