|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.342, |
|
"acc_stderr": 0.01500870618212173 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.346, |
|
"acc_stderr": 0.015050266127564441 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3408333333333333, |
|
"acc_stderr": 0.013688600793296939 |
|
}, |
|
"cb": { |
|
"acc": 0.39285714285714285, |
|
"acc_stderr": 0.0658538889806635, |
|
"f1": 0.24418093983311376 |
|
}, |
|
"copa": { |
|
"acc": 0.78, |
|
"acc_stderr": 0.04163331998932262 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4781915952997411, |
|
"acc_stderr": 0.004985032806802436, |
|
"acc_norm": 0.6294562836088429, |
|
"acc_norm_stderr": 0.004819633668832535 |
|
}, |
|
"rte": { |
|
"acc": 0.5487364620938628, |
|
"acc_stderr": 0.029953149241808943 |
|
}, |
|
"winogrande": { |
|
"acc": 0.6045777426992897, |
|
"acc_stderr": 0.013741678387545348 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7247461250668092, |
|
"acc_stderr": 0.010328538400500567 |
|
}, |
|
"boolq": { |
|
"acc": 0.6165137614678899, |
|
"acc_stderr": 0.008504304838837027 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6224747474747475, |
|
"acc_stderr": 0.009947227833469435, |
|
"acc_norm": 0.5437710437710438, |
|
"acc_norm_stderr": 0.01022039438372202 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2841296928327645, |
|
"acc_stderr": 0.013179442447653886, |
|
"acc_norm": 0.29692832764505117, |
|
"acc_norm_stderr": 0.013352025976725223 |
|
}, |
|
"sciq": { |
|
"acc": 0.848, |
|
"acc_stderr": 0.011358918303475279, |
|
"acc_norm": 0.76, |
|
"acc_norm_stderr": 0.013512312258920831 |
|
}, |
|
"piqa": { |
|
"acc": 0.7519042437431991, |
|
"acc_stderr": 0.010077118315574719, |
|
"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 |
|
} |
|
} |