|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.36, |
|
"acc_stderr": 0.015186527932040117 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.352, |
|
"acc_stderr": 0.015110404505648673 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.35, |
|
"acc_stderr": 0.013774667009018552 |
|
}, |
|
"cb": { |
|
"acc": 0.48214285714285715, |
|
"acc_stderr": 0.0673769750864465, |
|
"f1": 0.3338164251207729 |
|
}, |
|
"copa": { |
|
"acc": 0.79, |
|
"acc_stderr": 0.040936018074033256 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4314877514439355, |
|
"acc_stderr": 0.004942716091996078, |
|
"acc_norm": 0.5659231228838877, |
|
"acc_norm_stderr": 0.004946221512145289 |
|
}, |
|
"rte": { |
|
"acc": 0.48375451263537905, |
|
"acc_stderr": 0.030080573208738064 |
|
}, |
|
"winogrande": { |
|
"acc": 0.569060773480663, |
|
"acc_stderr": 0.013917796623335964 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6916087653661144, |
|
"acc_stderr": 0.010679734445487801 |
|
}, |
|
"boolq": { |
|
"acc": 0.5951070336391437, |
|
"acc_stderr": 0.008585393347962307 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5972222222222222, |
|
"acc_stderr": 0.010063960494989161, |
|
"acc_norm": 0.5702861952861953, |
|
"acc_norm_stderr": 0.010157908005763676 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2636518771331058, |
|
"acc_stderr": 0.012875929151297056, |
|
"acc_norm": 0.2841296928327645, |
|
"acc_norm_stderr": 0.013179442447653886 |
|
}, |
|
"sciq": { |
|
"acc": 0.886, |
|
"acc_stderr": 0.010055103435823328, |
|
"acc_norm": 0.86, |
|
"acc_norm_stderr": 0.010978183844357807 |
|
}, |
|
"piqa": { |
|
"acc": 0.7301414581066377, |
|
"acc_stderr": 0.010356595421852209, |
|
"acc_norm": 0.7377584330794341, |
|
"acc_norm_stderr": 0.010262502565172443 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |