|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.347, |
|
"acc_stderr": 0.015060472031706613 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.328, |
|
"acc_stderr": 0.01485384248727033 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3475, |
|
"acc_stderr": 0.013751753243291856 |
|
}, |
|
"cb": { |
|
"acc": 0.5178571428571429, |
|
"acc_stderr": 0.06737697508644647, |
|
"f1": 0.3578242744909412 |
|
}, |
|
"copa": { |
|
"acc": 0.75, |
|
"acc_stderr": 0.04351941398892446 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4539932284405497, |
|
"acc_stderr": 0.00496861353930925, |
|
"acc_norm": 0.5944035052778331, |
|
"acc_norm_stderr": 0.0049000362613090395 |
|
}, |
|
"rte": { |
|
"acc": 0.48736462093862815, |
|
"acc_stderr": 0.030086851767188564 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5643251775848461, |
|
"acc_stderr": 0.013935709739615713 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6985569214323891, |
|
"acc_stderr": 0.010611646032767584 |
|
}, |
|
"boolq": { |
|
"acc": 0.6064220183486239, |
|
"acc_stderr": 0.00854467241848691 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6077441077441077, |
|
"acc_stderr": 0.010018744689650043, |
|
"acc_norm": 0.5833333333333334, |
|
"acc_norm_stderr": 0.01011628297778126 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2764505119453925, |
|
"acc_stderr": 0.013069662474252427, |
|
"acc_norm": 0.28754266211604096, |
|
"acc_norm_stderr": 0.013226719056266132 |
|
}, |
|
"sciq": { |
|
"acc": 0.899, |
|
"acc_stderr": 0.009533618929340983, |
|
"acc_norm": 0.886, |
|
"acc_norm_stderr": 0.010055103435823332 |
|
}, |
|
"piqa": { |
|
"acc": 0.73449401523395, |
|
"acc_stderr": 0.010303308653024429, |
|
"acc_norm": 0.7442872687704026, |
|
"acc_norm_stderr": 0.010178690109459878 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |