|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.343, |
|
"acc_stderr": 0.015019206922356951 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.329, |
|
"acc_stderr": 0.014865395385928364 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3333333333333333, |
|
"acc_stderr": 0.0136139500102256 |
|
}, |
|
"cb": { |
|
"acc": 0.39285714285714285, |
|
"acc_stderr": 0.0658538889806635, |
|
"f1": 0.20571590265987547 |
|
}, |
|
"copa": { |
|
"acc": 0.73, |
|
"acc_stderr": 0.044619604333847394 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.44453296156144195, |
|
"acc_stderr": 0.004958983318274571, |
|
"acc_norm": 0.5728938458474407, |
|
"acc_norm_stderr": 0.004936470085238491 |
|
}, |
|
"rte": { |
|
"acc": 0.48014440433212996, |
|
"acc_stderr": 0.0300727231673172 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5619573796369376, |
|
"acc_stderr": 0.013944181296470804 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7017637626937466, |
|
"acc_stderr": 0.010579249795578815 |
|
}, |
|
"boolq": { |
|
"acc": 0.5685015290519878, |
|
"acc_stderr": 0.008662594569027309 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5660774410774411, |
|
"acc_stderr": 0.01016979577046211, |
|
"acc_norm": 0.49873737373737376, |
|
"acc_norm_stderr": 0.010259750807991153 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2551194539249147, |
|
"acc_stderr": 0.012739038695202105, |
|
"acc_norm": 0.2841296928327645, |
|
"acc_norm_stderr": 0.013179442447653886 |
|
}, |
|
"sciq": { |
|
"acc": 0.802, |
|
"acc_stderr": 0.01260773393417531, |
|
"acc_norm": 0.706, |
|
"acc_norm_stderr": 0.014414290540008215 |
|
}, |
|
"piqa": { |
|
"acc": 0.7404787812840044, |
|
"acc_stderr": 0.010227939888173922, |
|
"acc_norm": 0.7459194776931447, |
|
"acc_norm_stderr": 0.010157271999135051 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |