{ "results": { "anli_r1": { "acc": 0.305, "acc_stderr": 0.014566646394664387 }, "anli_r2": { "acc": 0.317, "acc_stderr": 0.014721675438880213 }, "anli_r3": { "acc": 0.335, "acc_stderr": 0.013630871843821477 }, "cb": { "acc": 0.5357142857142857, "acc_stderr": 0.06724777654937658, "f1": 0.37216374269005853 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 }, "hellaswag": { "acc": 0.4765982871937861, "acc_stderr": 0.004984313205791443, "acc_norm": 0.6290579565823541, "acc_norm_stderr": 0.004820697457420433 }, "rte": { "acc": 0.555956678700361, "acc_stderr": 0.029907396333795987 }, "winogrande": { "acc": 0.5816890292028414, "acc_stderr": 0.013863669961195904 }, "storycloze_2016": { "acc": 0.7172634954569749, "acc_stderr": 0.01041380648612127 }, "boolq": { "acc": 0.6314984709480123, "acc_stderr": 0.00843719989350296 }, "arc_easy": { "acc": 0.6195286195286195, "acc_stderr": 0.009962305992058584, "acc_norm": 0.5904882154882155, "acc_norm_stderr": 0.010090368160990062 }, "arc_challenge": { "acc": 0.29436860068259385, "acc_stderr": 0.013318528460539427, "acc_norm": 0.3097269624573379, "acc_norm_stderr": 0.013512058415238361 }, "sciq": { "acc": 0.905, "acc_stderr": 0.009276910103103322, "acc_norm": 0.876, "acc_norm_stderr": 0.01042749887234396 }, "piqa": { "acc": 0.7627856365614799, "acc_stderr": 0.009924694933586376, "acc_norm": 0.7584330794341676, "acc_norm_stderr": 0.009986718001804444 } }, "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 } }