|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.36, |
|
"acc_stderr": 0.015186527932040126 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.368, |
|
"acc_stderr": 0.015258073561521802 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.335, |
|
"acc_stderr": 0.013630871843821474 |
|
}, |
|
"cb": { |
|
"acc": 0.5, |
|
"acc_stderr": 0.06741998624632421, |
|
"f1": 0.2222222222222222 |
|
}, |
|
"copa": { |
|
"acc": 0.8, |
|
"acc_stderr": 0.040201512610368445 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4727145986855208, |
|
"acc_stderr": 0.004982346155911132, |
|
"acc_norm": 0.6279625572595101, |
|
"acc_norm_stderr": 0.004823604775015894 |
|
}, |
|
"rte": { |
|
"acc": 0.5342960288808665, |
|
"acc_stderr": 0.030025579819366426 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5895816890292028, |
|
"acc_stderr": 0.01382510712003587 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7220737573490112, |
|
"acc_stderr": 0.010359403651225865 |
|
}, |
|
"boolq": { |
|
"acc": 0.6079510703363914, |
|
"acc_stderr": 0.008538802914911995 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6233164983164983, |
|
"acc_stderr": 0.009942848077476172, |
|
"acc_norm": 0.6220538720538721, |
|
"acc_norm_stderr": 0.009949405744045481 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.302901023890785, |
|
"acc_stderr": 0.013428241573185349, |
|
"acc_norm": 0.3199658703071672, |
|
"acc_norm_stderr": 0.013631345807016193 |
|
}, |
|
"sciq": { |
|
"acc": 0.912, |
|
"acc_stderr": 0.008963053962592085, |
|
"acc_norm": 0.905, |
|
"acc_norm_stderr": 0.0092769101031033 |
|
}, |
|
"piqa": { |
|
"acc": 0.749727965179543, |
|
"acc_stderr": 0.01010656188008979, |
|
"acc_norm": 0.7546245919477693, |
|
"acc_norm_stderr": 0.010039831320422384 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |