|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.343, |
|
"acc_stderr": 0.015019206922356951 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.356, |
|
"acc_stderr": 0.015149042659306621 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3433333333333333, |
|
"acc_stderr": 0.01371263383046586 |
|
}, |
|
"cb": { |
|
"acc": 0.4107142857142857, |
|
"acc_stderr": 0.06633634150359541, |
|
"f1": 0.19658119658119658 |
|
}, |
|
"copa": { |
|
"acc": 0.73, |
|
"acc_stderr": 0.0446196043338474 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4047002589125672, |
|
"acc_stderr": 0.004898308167211846, |
|
"acc_norm": 0.4994025094602669, |
|
"acc_norm_stderr": 0.004989777848791008 |
|
}, |
|
"rte": { |
|
"acc": 0.5018050541516246, |
|
"acc_stderr": 0.030096267148976633 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5193370165745856, |
|
"acc_stderr": 0.014041972733712974 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6563335114911811, |
|
"acc_stderr": 0.010982724236255945 |
|
}, |
|
"boolq": { |
|
"acc": 0.5333333333333333, |
|
"acc_stderr": 0.008725599880049204 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.49284511784511786, |
|
"acc_stderr": 0.010258733022446367, |
|
"acc_norm": 0.4696969696969697, |
|
"acc_norm_stderr": 0.01024092360872654 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.23890784982935154, |
|
"acc_stderr": 0.012461071376316614, |
|
"acc_norm": 0.26535836177474403, |
|
"acc_norm_stderr": 0.012902554762313967 |
|
}, |
|
"sciq": { |
|
"acc": 0.724, |
|
"acc_stderr": 0.014142984975740668, |
|
"acc_norm": 0.688, |
|
"acc_norm_stderr": 0.014658474370509001 |
|
}, |
|
"piqa": { |
|
"acc": 0.7110990206746464, |
|
"acc_stderr": 0.010575111841364905, |
|
"acc_norm": 0.7072905331882481, |
|
"acc_norm_stderr": 0.010616044462393094 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |