|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.348, |
|
"acc_stderr": 0.01507060460376841 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.344, |
|
"acc_stderr": 0.015029633724408947 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3325, |
|
"acc_stderr": 0.013605417345710528 |
|
}, |
|
"cb": { |
|
"acc": 0.3392857142857143, |
|
"acc_stderr": 0.06384226561930825, |
|
"f1": 0.3185837135128588 |
|
}, |
|
"copa": { |
|
"acc": 0.78, |
|
"acc_stderr": 0.04163331998932263 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.5206134236207927, |
|
"acc_stderr": 0.00498553915978342, |
|
"acc_norm": 0.6902011551483768, |
|
"acc_norm_stderr": 0.00461465517501001 |
|
}, |
|
"rte": { |
|
"acc": 0.48014440433212996, |
|
"acc_stderr": 0.0300727231673172 |
|
}, |
|
"winogrande": { |
|
"acc": 0.601420678768745, |
|
"acc_stderr": 0.01376035717687383 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7504008551576697, |
|
"acc_stderr": 0.010008002459430848 |
|
}, |
|
"boolq": { |
|
"acc": 0.6363914373088685, |
|
"acc_stderr": 0.008413404209789989 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.648989898989899, |
|
"acc_stderr": 0.009793703885101042, |
|
"acc_norm": 0.6393097643097643, |
|
"acc_norm_stderr": 0.009853512108416748 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.3148464163822526, |
|
"acc_stderr": 0.01357265770308495, |
|
"acc_norm": 0.3250853242320819, |
|
"acc_norm_stderr": 0.013688147309729119 |
|
}, |
|
"sciq": { |
|
"acc": 0.917, |
|
"acc_stderr": 0.008728527206074792, |
|
"acc_norm": 0.911, |
|
"acc_norm_stderr": 0.009008893392651521 |
|
}, |
|
"piqa": { |
|
"acc": 0.7584330794341676, |
|
"acc_stderr": 0.009986718001804467, |
|
"acc_norm": 0.7665941240478781, |
|
"acc_norm_stderr": 0.009869247889520991 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |