|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.33, |
|
"acc_stderr": 0.014876872027456732 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.333, |
|
"acc_stderr": 0.014910846164229857 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3425, |
|
"acc_stderr": 0.013704669762934727 |
|
}, |
|
"cb": { |
|
"acc": 0.48214285714285715, |
|
"acc_stderr": 0.0673769750864465, |
|
"f1": 0.31768388106416273 |
|
}, |
|
"copa": { |
|
"acc": 0.7, |
|
"acc_stderr": 0.046056618647183814 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.45439155546703847, |
|
"acc_stderr": 0.004968979259738328, |
|
"acc_norm": 0.5930093606851224, |
|
"acc_norm_stderr": 0.004902690765066431 |
|
}, |
|
"rte": { |
|
"acc": 0.5487364620938628, |
|
"acc_stderr": 0.029953149241808946 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5666929755327546, |
|
"acc_stderr": 0.013926915052757352 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.692143238909674, |
|
"acc_stderr": 0.010674598158758177 |
|
}, |
|
"boolq": { |
|
"acc": 0.5706422018348624, |
|
"acc_stderr": 0.008657333755353679 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5900673400673401, |
|
"acc_stderr": 0.01009195352750625, |
|
"acc_norm": 0.5538720538720538, |
|
"acc_norm_stderr": 0.010200057828765008 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.26109215017064846, |
|
"acc_stderr": 0.012835523909473848, |
|
"acc_norm": 0.28924914675767915, |
|
"acc_norm_stderr": 0.013250012579393441 |
|
}, |
|
"sciq": { |
|
"acc": 0.865, |
|
"acc_stderr": 0.010811655372416051, |
|
"acc_norm": 0.837, |
|
"acc_norm_stderr": 0.01168621271274684 |
|
}, |
|
"piqa": { |
|
"acc": 0.7383025027203483, |
|
"acc_stderr": 0.01025563077270823, |
|
"acc_norm": 0.7415669205658324, |
|
"acc_norm_stderr": 0.010213971636773315 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |