|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.328, |
|
"acc_stderr": 0.014853842487270334 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.344, |
|
"acc_stderr": 0.015029633724408943 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.38333333333333336, |
|
"acc_stderr": 0.014041190711780102 |
|
}, |
|
"cb": { |
|
"acc": 0.3392857142857143, |
|
"acc_stderr": 0.06384226561930825, |
|
"f1": 0.22990271377368152 |
|
}, |
|
"copa": { |
|
"acc": 0.74, |
|
"acc_stderr": 0.04408440022768077 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4500099581756622, |
|
"acc_stderr": 0.004964779805180658, |
|
"acc_norm": 0.5852419836685919, |
|
"acc_norm_stderr": 0.004916733258140278 |
|
}, |
|
"rte": { |
|
"acc": 0.4693140794223827, |
|
"acc_stderr": 0.03003973059219781 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5643251775848461, |
|
"acc_stderr": 0.013935709739615708 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7022982362373063, |
|
"acc_stderr": 0.010573790208173063 |
|
}, |
|
"boolq": { |
|
"acc": 0.5345565749235474, |
|
"acc_stderr": 0.008724144040604807 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6203703703703703, |
|
"acc_stderr": 0.009958037725468567, |
|
"acc_norm": 0.5622895622895623, |
|
"acc_norm_stderr": 0.010179856486006906 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2773037542662116, |
|
"acc_stderr": 0.013082095839059374, |
|
"acc_norm": 0.2935153583617747, |
|
"acc_norm_stderr": 0.013307250444941118 |
|
}, |
|
"sciq": { |
|
"acc": 0.86, |
|
"acc_stderr": 0.010978183844357805, |
|
"acc_norm": 0.793, |
|
"acc_norm_stderr": 0.012818553557843984 |
|
}, |
|
"piqa": { |
|
"acc": 0.7486398258977149, |
|
"acc_stderr": 0.01012115601681926, |
|
"acc_norm": 0.7529923830250272, |
|
"acc_norm_stderr": 0.01006226814077264 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |