|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.332, |
|
"acc_stderr": 0.014899597242811483 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.336, |
|
"acc_stderr": 0.014944140233795027 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3433333333333333, |
|
"acc_stderr": 0.01371263383046586 |
|
}, |
|
"cb": { |
|
"acc": 0.39285714285714285, |
|
"acc_stderr": 0.0658538889806635, |
|
"f1": 0.18803418803418803 |
|
}, |
|
"copa": { |
|
"acc": 0.73, |
|
"acc_stderr": 0.044619604333847394 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.45140410276837284, |
|
"acc_stderr": 0.004966158142645415, |
|
"acc_norm": 0.5865365465046803, |
|
"acc_norm_stderr": 0.004914480534533721 |
|
}, |
|
"rte": { |
|
"acc": 0.5415162454873647, |
|
"acc_stderr": 0.029992535385373314 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5737963693764798, |
|
"acc_stderr": 0.013898585965412342 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7017637626937466, |
|
"acc_stderr": 0.01057924979557881 |
|
}, |
|
"boolq": { |
|
"acc": 0.617125382262997, |
|
"acc_stderr": 0.008501734385335951 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6047979797979798, |
|
"acc_stderr": 0.010031894052790973, |
|
"acc_norm": 0.5526094276094277, |
|
"acc_norm_stderr": 0.01020283238541565 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2832764505119454, |
|
"acc_stderr": 0.013167478735134575, |
|
"acc_norm": 0.30204778156996587, |
|
"acc_norm_stderr": 0.013417519144716417 |
|
}, |
|
"sciq": { |
|
"acc": 0.859, |
|
"acc_stderr": 0.011010914595992446, |
|
"acc_norm": 0.792, |
|
"acc_norm_stderr": 0.012841374572096928 |
|
}, |
|
"piqa": { |
|
"acc": 0.7486398258977149, |
|
"acc_stderr": 0.010121156016819259, |
|
"acc_norm": 0.7519042437431991, |
|
"acc_norm_stderr": 0.010077118315574706 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |