|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.34, |
|
"acc_stderr": 0.014987482264363935 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.337, |
|
"acc_stderr": 0.014955087918653605 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3325, |
|
"acc_stderr": 0.013605417345710526 |
|
}, |
|
"cb": { |
|
"acc": 0.23214285714285715, |
|
"acc_stderr": 0.0569293902400011, |
|
"f1": 0.223351041141572 |
|
}, |
|
"copa": { |
|
"acc": 0.76, |
|
"acc_stderr": 0.042923469599092816 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.5209121688906593, |
|
"acc_stderr": 0.004985415250690905, |
|
"acc_norm": 0.689205337582155, |
|
"acc_norm_stderr": 0.004618730353217064 |
|
}, |
|
"rte": { |
|
"acc": 0.5054151624548736, |
|
"acc_stderr": 0.030094698123239966 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5935280189423836, |
|
"acc_stderr": 0.01380444869775337 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7498663816141101, |
|
"acc_stderr": 0.010015143382536456 |
|
}, |
|
"boolq": { |
|
"acc": 0.6409785932721712, |
|
"acc_stderr": 0.008390241754319908 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6536195286195287, |
|
"acc_stderr": 0.009763542075695738, |
|
"acc_norm": 0.6401515151515151, |
|
"acc_norm_stderr": 0.009848484848484836 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.3310580204778157, |
|
"acc_stderr": 0.013752062419817834, |
|
"acc_norm": 0.3447098976109215, |
|
"acc_norm_stderr": 0.013888816286782112 |
|
}, |
|
"sciq": { |
|
"acc": 0.923, |
|
"acc_stderr": 0.008434580140240648, |
|
"acc_norm": 0.912, |
|
"acc_norm_stderr": 0.008963053962592074 |
|
}, |
|
"piqa": { |
|
"acc": 0.7606093579978237, |
|
"acc_stderr": 0.009955884250291688, |
|
"acc_norm": 0.7747551686615887, |
|
"acc_norm_stderr": 0.009746643471032136 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |