|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.35, |
|
"acc_stderr": 0.015090650341444233 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.34, |
|
"acc_stderr": 0.014987482264363937 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.33166666666666667, |
|
"acc_stderr": 0.013596836729485163 |
|
}, |
|
"cb": { |
|
"acc": 0.44642857142857145, |
|
"acc_stderr": 0.06703189227942398, |
|
"f1": 0.3011143410852713 |
|
}, |
|
"copa": { |
|
"acc": 0.75, |
|
"acc_stderr": 0.04351941398892446 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4255128460466043, |
|
"acc_stderr": 0.004934100774481221, |
|
"acc_norm": 0.5439155546703844, |
|
"acc_norm_stderr": 0.004970497804772303 |
|
}, |
|
"rte": { |
|
"acc": 0.5487364620938628, |
|
"acc_stderr": 0.029953149241808946 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5295974743488555, |
|
"acc_stderr": 0.014027843827840083 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6787814003206841, |
|
"acc_stderr": 0.010798029402794913 |
|
}, |
|
"boolq": { |
|
"acc": 0.5951070336391437, |
|
"acc_stderr": 0.008585393347962315 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5656565656565656, |
|
"acc_stderr": 0.010170943451269425, |
|
"acc_norm": 0.5404040404040404, |
|
"acc_norm_stderr": 0.010226230740889027 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2636518771331058, |
|
"acc_stderr": 0.012875929151297061, |
|
"acc_norm": 0.2790102389078498, |
|
"acc_norm_stderr": 0.013106784883601345 |
|
}, |
|
"sciq": { |
|
"acc": 0.873, |
|
"acc_stderr": 0.010534798620855748, |
|
"acc_norm": 0.855, |
|
"acc_norm_stderr": 0.01113997751789013 |
|
}, |
|
"piqa": { |
|
"acc": 0.7295973884657236, |
|
"acc_stderr": 0.010363167031620803, |
|
"acc_norm": 0.7323177366702938, |
|
"acc_norm_stderr": 0.010330111189370415 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |