{ "results": { "anli_r1": { "acc": 0.332, "acc_stderr": 0.014899597242811492 }, "anli_r2": { "acc": 0.368, "acc_stderr": 0.0152580735615218 }, "anli_r3": { "acc": 0.3491666666666667, "acc_stderr": 0.013767075395077247 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.0673769750864465, "f1": 0.33712121212121215 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.4765982871937861, "acc_stderr": 0.004984313205791442, "acc_norm": 0.6384186417048396, "acc_norm_stderr": 0.0047947648436852865 }, "rte": { "acc": 0.47653429602888087, "acc_stderr": 0.03006330041190266 }, "winogrande": { "acc": 0.580110497237569, "acc_stderr": 0.013870943986310395 }, "storycloze_2016": { "acc": 0.7300908605024051, "acc_stderr": 0.01026541350322146 }, "boolq": { "acc": 0.5691131498470948, "acc_stderr": 0.008661108320775374 }, "arc_easy": { "acc": 0.6304713804713805, "acc_stderr": 0.009904325878447319, "acc_norm": 0.6085858585858586, "acc_norm_stderr": 0.010014917532627819 }, "arc_challenge": { "acc": 0.2960750853242321, "acc_stderr": 0.013340916085246263, "acc_norm": 0.3250853242320819, "acc_norm_stderr": 0.013688147309729124 }, "sciq": { "acc": 0.908, "acc_stderr": 0.009144376393151108, "acc_norm": 0.9, "acc_norm_stderr": 0.009491579957525044 }, "piqa": { "acc": 0.7589771490750816, "acc_stderr": 0.009979042717267315, "acc_norm": 0.764417845484222, "acc_norm_stderr": 0.009901067586473885 } }, "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 } }