|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.322, |
|
"acc_stderr": 0.014782913600996664 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.353, |
|
"acc_stderr": 0.015120172605483689 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3333333333333333, |
|
"acc_stderr": 0.013613950010225593 |
|
}, |
|
"cb": { |
|
"acc": 0.375, |
|
"acc_stderr": 0.06527912098338669, |
|
"f1": 0.34540644540644544 |
|
}, |
|
"copa": { |
|
"acc": 0.77, |
|
"acc_stderr": 0.04229525846816506 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4303923521210914, |
|
"acc_stderr": 0.004941191607317909, |
|
"acc_norm": 0.5595498904600678, |
|
"acc_norm_stderr": 0.004954265595373475 |
|
}, |
|
"rte": { |
|
"acc": 0.49458483754512633, |
|
"acc_stderr": 0.030094698123239966 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5390686661404893, |
|
"acc_stderr": 0.014009521680980316 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6905398182789952, |
|
"acc_stderr": 0.01068995674518907 |
|
}, |
|
"boolq": { |
|
"acc": 0.5834862385321101, |
|
"acc_stderr": 0.008622288020674003 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5765993265993266, |
|
"acc_stderr": 0.010138671005289045, |
|
"acc_norm": 0.5517676767676768, |
|
"acc_norm_stderr": 0.010204645126856942 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2525597269624573, |
|
"acc_stderr": 0.012696728980207706, |
|
"acc_norm": 0.28242320819112626, |
|
"acc_norm_stderr": 0.013155456884097222 |
|
}, |
|
"sciq": { |
|
"acc": 0.881, |
|
"acc_stderr": 0.01024421514533666, |
|
"acc_norm": 0.856, |
|
"acc_norm_stderr": 0.01110798754893915 |
|
}, |
|
"piqa": { |
|
"acc": 0.7377584330794341, |
|
"acc_stderr": 0.010262502565172449, |
|
"acc_norm": 0.7475516866158868, |
|
"acc_norm_stderr": 0.010135665547362355 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |