|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.329, |
|
"acc_stderr": 0.014865395385928357 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.356, |
|
"acc_stderr": 0.015149042659306623 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3383333333333333, |
|
"acc_stderr": 0.01366414400661828 |
|
}, |
|
"cb": { |
|
"acc": 0.4642857142857143, |
|
"acc_stderr": 0.0672477765493766, |
|
"f1": 0.2798941798941799 |
|
}, |
|
"copa": { |
|
"acc": 0.66, |
|
"acc_stderr": 0.04760952285695237 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.39543915554670384, |
|
"acc_stderr": 0.004879455474663814, |
|
"acc_norm": 0.4986058554072894, |
|
"acc_norm_stderr": 0.004989762014739185 |
|
}, |
|
"rte": { |
|
"acc": 0.4981949458483754, |
|
"acc_stderr": 0.030096267148976626 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5035516969218626, |
|
"acc_stderr": 0.014052131146915852 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6616782469267771, |
|
"acc_stderr": 0.010941266252293478 |
|
}, |
|
"boolq": { |
|
"acc": 0.4327217125382263, |
|
"acc_stderr": 0.00866552668441624 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.4802188552188552, |
|
"acc_stderr": 0.010251751199542738, |
|
"acc_norm": 0.4701178451178451, |
|
"acc_norm_stderr": 0.010241444322886432 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.22696245733788395, |
|
"acc_stderr": 0.012240491536132868, |
|
"acc_norm": 0.2551194539249147, |
|
"acc_norm_stderr": 0.012739038695202109 |
|
}, |
|
"sciq": { |
|
"acc": 0.756, |
|
"acc_stderr": 0.013588548437881431, |
|
"acc_norm": 0.737, |
|
"acc_norm_stderr": 0.013929286594259717 |
|
}, |
|
"piqa": { |
|
"acc": 0.6942328618063112, |
|
"acc_stderr": 0.010749627366141639, |
|
"acc_norm": 0.7007616974972797, |
|
"acc_norm_stderr": 0.010684130673134581 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |