{ "results": { "anli_r1": { "acc": 0.326, "acc_stderr": 0.01483050720454104 }, "anli_r2": { "acc": 0.333, "acc_stderr": 0.014910846164229863 }, "anli_r3": { "acc": 0.3333333333333333, "acc_stderr": 0.013613950010225605 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.2880105401844532 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.43308105954989046, "acc_stderr": 0.00494488954549795, "acc_norm": 0.5610436168094005, "acc_norm_stderr": 0.004952454721934803 }, "rte": { "acc": 0.5270758122743683, "acc_stderr": 0.030052303463143713 }, "winogrande": { "acc": 0.5595895816890292, "acc_stderr": 0.013952330311915605 }, "storycloze_2016": { "acc": 0.6884019241047569, "acc_stderr": 0.010710200919679802 }, "boolq": { "acc": 0.6064220183486239, "acc_stderr": 0.00854467241848691 }, "arc_easy": { "acc": 0.5888047138047138, "acc_stderr": 0.010096663811817685, "acc_norm": 0.5648148148148148, "acc_norm_stderr": 0.010173216430370911 }, "arc_challenge": { "acc": 0.26023890784982934, "acc_stderr": 0.012821930225112568, "acc_norm": 0.30716723549488056, "acc_norm_stderr": 0.013481034054980943 }, "sciq": { "acc": 0.872, "acc_stderr": 0.010570133761108654, "acc_norm": 0.849, "acc_norm_stderr": 0.011328165223341673 }, "piqa": { "acc": 0.7480957562568009, "acc_stderr": 0.010128421335088681, "acc_norm": 0.7459194776931447, "acc_norm_stderr": 0.010157271999135046 } }, "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 } }