|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.321, |
|
"acc_stderr": 0.014770821817934645 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.332, |
|
"acc_stderr": 0.014899597242811482 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3425, |
|
"acc_stderr": 0.013704669762934728 |
|
}, |
|
"cb": { |
|
"acc": 0.39285714285714285, |
|
"acc_stderr": 0.0658538889806635, |
|
"f1": 0.2736842105263158 |
|
}, |
|
"copa": { |
|
"acc": 0.76, |
|
"acc_stderr": 0.04292346959909283 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.46873132842063336, |
|
"acc_stderr": 0.004980014536539821, |
|
"acc_norm": 0.6212905795658236, |
|
"acc_norm_stderr": 0.0048407422067181065 |
|
}, |
|
"rte": { |
|
"acc": 0.5234657039711191, |
|
"acc_stderr": 0.03006330041190266 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5895816890292028, |
|
"acc_stderr": 0.013825107120035866 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7156600748262961, |
|
"acc_stderr": 0.010431614128665253 |
|
}, |
|
"boolq": { |
|
"acc": 0.5532110091743119, |
|
"acc_stderr": 0.008695392261996192 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6178451178451179, |
|
"acc_stderr": 0.009970747281292436, |
|
"acc_norm": 0.601010101010101, |
|
"acc_norm_stderr": 0.010048240683798748 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.27474402730375425, |
|
"acc_stderr": 0.013044617212771227, |
|
"acc_norm": 0.3037542662116041, |
|
"acc_norm_stderr": 0.013438909184778757 |
|
}, |
|
"sciq": { |
|
"acc": 0.887, |
|
"acc_stderr": 0.010016552866696846, |
|
"acc_norm": 0.876, |
|
"acc_norm_stderr": 0.010427498872343973 |
|
}, |
|
"piqa": { |
|
"acc": 0.7557127312295974, |
|
"acc_stderr": 0.010024765172284242, |
|
"acc_norm": 0.7600652883569097, |
|
"acc_norm_stderr": 0.009963625892809545 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |