|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.348, |
|
"acc_stderr": 0.015070604603768408 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.344, |
|
"acc_stderr": 0.015029633724408948 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3383333333333333, |
|
"acc_stderr": 0.013664144006618271 |
|
}, |
|
"cb": { |
|
"acc": 0.4107142857142857, |
|
"acc_stderr": 0.0663363415035954, |
|
"f1": 0.21777777777777776 |
|
}, |
|
"copa": { |
|
"acc": 0.71, |
|
"acc_stderr": 0.04560480215720684 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.46285600477992433, |
|
"acc_stderr": 0.004975993795562031, |
|
"acc_norm": 0.6014738099980084, |
|
"acc_norm_stderr": 0.004885942040894556 |
|
}, |
|
"rte": { |
|
"acc": 0.5415162454873647, |
|
"acc_stderr": 0.029992535385373314 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5753749013417522, |
|
"acc_stderr": 0.01389189315026423 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.694815606627472, |
|
"acc_stderr": 0.010648664383985658 |
|
}, |
|
"boolq": { |
|
"acc": 0.6058103975535168, |
|
"acc_stderr": 0.008546995661233635 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6043771043771043, |
|
"acc_stderr": 0.010033741393430986, |
|
"acc_norm": 0.5677609427609428, |
|
"acc_norm_stderr": 0.010165130379698746 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.28924914675767915, |
|
"acc_stderr": 0.013250012579393443, |
|
"acc_norm": 0.31313993174061433, |
|
"acc_norm_stderr": 0.01355267154362349 |
|
}, |
|
"sciq": { |
|
"acc": 0.856, |
|
"acc_stderr": 0.01110798754893915, |
|
"acc_norm": 0.829, |
|
"acc_norm_stderr": 0.011912216456264614 |
|
}, |
|
"piqa": { |
|
"acc": 0.7388465723612623, |
|
"acc_stderr": 0.01024873864993558, |
|
"acc_norm": 0.7399347116430903, |
|
"acc_norm_stderr": 0.010234893249061282 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |