{ "results": { "anli_r1": { "acc": 0.323, "acc_stderr": 0.014794927843348639 }, "anli_r2": { "acc": 0.332, "acc_stderr": 0.014899597242811475 }, "anli_r3": { "acc": 0.3275, "acc_stderr": 0.013553211167251961 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.32470238095238096 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4792869946225851, "acc_stderr": 0.004985498055190358, "acc_norm": 0.6384186417048396, "acc_norm_stderr": 0.004794764843685288 }, "rte": { "acc": 0.5054151624548736, "acc_stderr": 0.030094698123239966 }, "winogrande": { "acc": 0.5880031570639306, "acc_stderr": 0.013833112857645937 }, "storycloze_2016": { "acc": 0.7306253340459647, "acc_stderr": 0.010258997754057014 }, "boolq": { "acc": 0.618960244648318, "acc_stderr": 0.008493937524439337 }, "arc_easy": { "acc": 0.6426767676767676, "acc_stderr": 0.00983320561246312, "acc_norm": 0.625, "acc_norm_stderr": 0.009933992677987828 }, "arc_challenge": { "acc": 0.29948805460750855, "acc_stderr": 0.013385021637313565, "acc_norm": 0.31313993174061433, "acc_norm_stderr": 0.013552671543623504 }, "sciq": { "acc": 0.919, "acc_stderr": 0.008632121032139964, "acc_norm": 0.911, "acc_norm_stderr": 0.009008893392651526 }, "piqa": { "acc": 0.7557127312295974, "acc_stderr": 0.010024765172284247, "acc_norm": 0.7616974972796517, "acc_norm_stderr": 0.009940334245876222 } }, "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 } }