|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.316, |
|
"acc_stderr": 0.014709193056057128 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.333, |
|
"acc_stderr": 0.014910846164229863 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.35, |
|
"acc_stderr": 0.013774667009018554 |
|
}, |
|
"cb": { |
|
"acc": 0.30357142857142855, |
|
"acc_stderr": 0.06199938655510754, |
|
"f1": 0.24554767533490937 |
|
}, |
|
"copa": { |
|
"acc": 0.78, |
|
"acc_stderr": 0.04163331998932261 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4780920135431189, |
|
"acc_stderr": 0.004984989320648131, |
|
"acc_norm": 0.6307508464449313, |
|
"acc_norm_stderr": 0.004816152074023083 |
|
}, |
|
"rte": { |
|
"acc": 0.5812274368231047, |
|
"acc_stderr": 0.029696661081234824 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5840568271507498, |
|
"acc_stderr": 0.013852485356798252 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7188669160876536, |
|
"acc_stderr": 0.010395836091628103 |
|
}, |
|
"boolq": { |
|
"acc": 0.5896024464831804, |
|
"acc_stderr": 0.008603488048617521 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.627104377104377, |
|
"acc_stderr": 0.009922743197129257, |
|
"acc_norm": 0.5955387205387206, |
|
"acc_norm_stderr": 0.010070746648278795 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2815699658703072, |
|
"acc_stderr": 0.013143376735009024, |
|
"acc_norm": 0.30802047781569963, |
|
"acc_norm_stderr": 0.013491429517292038 |
|
}, |
|
"sciq": { |
|
"acc": 0.901, |
|
"acc_stderr": 0.009449248027662765, |
|
"acc_norm": 0.884, |
|
"acc_norm_stderr": 0.010131468138756997 |
|
}, |
|
"piqa": { |
|
"acc": 0.7486398258977149, |
|
"acc_stderr": 0.010121156016819257, |
|
"acc_norm": 0.7611534276387377, |
|
"acc_norm_stderr": 0.009948120385337485 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |