{ "results": { "anli_r1": { "acc": 0.324, "acc_stderr": 0.01480686473373886 }, "anli_r2": { "acc": 0.361, "acc_stderr": 0.015195720118175124 }, "anli_r3": { "acc": 0.3641666666666667, "acc_stderr": 0.013896714966807262 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.24317460317460324 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.45488946425014937, "acc_stderr": 0.004969431900874299, "acc_norm": 0.5929097789285003, "acc_norm_stderr": 0.004902878806733035 }, "rte": { "acc": 0.44765342960288806, "acc_stderr": 0.029931070362939526 }, "winogrande": { "acc": 0.5627466456195738, "acc_stderr": 0.013941393310695917 }, "storycloze_2016": { "acc": 0.7006948156066275, "acc_stderr": 0.010590117252248798 }, "boolq": { "acc": 0.5868501529051988, "acc_stderr": 0.008612117547803578 }, "arc_easy": { "acc": 0.6001683501683501, "acc_stderr": 0.010051788039412911, "acc_norm": 0.5787037037037037, "acc_norm_stderr": 0.010131882498193126 }, "arc_challenge": { "acc": 0.2764505119453925, "acc_stderr": 0.013069662474252425, "acc_norm": 0.2935153583617747, "acc_norm_stderr": 0.01330725044494112 }, "sciq": { "acc": 0.892, "acc_stderr": 0.009820001651345693, "acc_norm": 0.872, "acc_norm_stderr": 0.010570133761108654 }, "piqa": { "acc": 0.7377584330794341, "acc_stderr": 0.010262502565172445, "acc_norm": 0.749727965179543, "acc_norm_stderr": 0.010106561880089775 } }, "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 } }