|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.326, |
|
"acc_stderr": 0.014830507204541037 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.337, |
|
"acc_stderr": 0.014955087918653607 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.33416666666666667, |
|
"acc_stderr": 0.013622434813136774 |
|
}, |
|
"cb": { |
|
"acc": 0.42857142857142855, |
|
"acc_stderr": 0.06672848092813058, |
|
"f1": 0.26622479977906655 |
|
}, |
|
"copa": { |
|
"acc": 0.81, |
|
"acc_stderr": 0.039427724440366234 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4629555865365465, |
|
"acc_stderr": 0.004976067726432562, |
|
"acc_norm": 0.609838677554272, |
|
"acc_norm_stderr": 0.004867893927258165 |
|
}, |
|
"rte": { |
|
"acc": 0.5270758122743683, |
|
"acc_stderr": 0.0300523034631437 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5824782951854776, |
|
"acc_stderr": 0.013859978264440246 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7145911277391769, |
|
"acc_stderr": 0.010443395884062115 |
|
}, |
|
"boolq": { |
|
"acc": 0.5752293577981651, |
|
"acc_stderr": 0.008645503833361106 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5993265993265994, |
|
"acc_stderr": 0.010055304474255573, |
|
"acc_norm": 0.5694444444444444, |
|
"acc_norm_stderr": 0.010160345396860082 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.28071672354948807, |
|
"acc_stderr": 0.013131238126975576, |
|
"acc_norm": 0.3037542662116041, |
|
"acc_norm_stderr": 0.013438909184778766 |
|
}, |
|
"sciq": { |
|
"acc": 0.844, |
|
"acc_stderr": 0.011480235006122363, |
|
"acc_norm": 0.794, |
|
"acc_norm_stderr": 0.012795613612786548 |
|
}, |
|
"piqa": { |
|
"acc": 0.7437431991294886, |
|
"acc_stderr": 0.01018578783156506, |
|
"acc_norm": 0.7524483133841132, |
|
"acc_norm_stderr": 0.010069703966857116 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |