|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.304, |
|
"acc_stderr": 0.014553205687950434 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.332, |
|
"acc_stderr": 0.014899597242811482 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.34833333333333333, |
|
"acc_stderr": 0.013759437498874061 |
|
}, |
|
"cb": { |
|
"acc": 0.42857142857142855, |
|
"acc_stderr": 0.06672848092813058, |
|
"f1": 0.30465949820788535 |
|
}, |
|
"copa": { |
|
"acc": 0.77, |
|
"acc_stderr": 0.042295258468165065 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.45429197371041624, |
|
"acc_stderr": 0.004968888130290068, |
|
"acc_norm": 0.5927106154152559, |
|
"acc_norm_stderr": 0.004903254264177628 |
|
}, |
|
"rte": { |
|
"acc": 0.5595667870036101, |
|
"acc_stderr": 0.02988212336311872 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5603788476716653, |
|
"acc_stderr": 0.013949649776015696 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6734366648850882, |
|
"acc_stderr": 0.010844543793668893 |
|
}, |
|
"boolq": { |
|
"acc": 0.6155963302752293, |
|
"acc_stderr": 0.008508133844703919 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5096801346801347, |
|
"acc_stderr": 0.010257860554461122, |
|
"acc_norm": 0.46296296296296297, |
|
"acc_norm_stderr": 0.010231597249131062 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2508532423208191, |
|
"acc_stderr": 0.01266819862131543, |
|
"acc_norm": 0.2764505119453925, |
|
"acc_norm_stderr": 0.013069662474252425 |
|
}, |
|
"sciq": { |
|
"acc": 0.827, |
|
"acc_stderr": 0.011967214137559941, |
|
"acc_norm": 0.789, |
|
"acc_norm_stderr": 0.01290913032104209 |
|
}, |
|
"piqa": { |
|
"acc": 0.6953210010881393, |
|
"acc_stderr": 0.010738889044325161, |
|
"acc_norm": 0.6953210010881393, |
|
"acc_norm_stderr": 0.010738889044325161 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |