|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.332, |
|
"acc_stderr": 0.014899597242811487 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.337, |
|
"acc_stderr": 0.014955087918653605 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3433333333333333, |
|
"acc_stderr": 0.01371263383046586 |
|
}, |
|
"cb": { |
|
"acc": 0.4107142857142857, |
|
"acc_stderr": 0.0663363415035954, |
|
"f1": 0.3312277706643904 |
|
}, |
|
"copa": { |
|
"acc": 0.73, |
|
"acc_stderr": 0.0446196043338474 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4765982871937861, |
|
"acc_stderr": 0.004984313205791442, |
|
"acc_norm": 0.6216889065923122, |
|
"acc_norm_stderr": 0.004839746491523515 |
|
}, |
|
"rte": { |
|
"acc": 0.5740072202166066, |
|
"acc_stderr": 0.02976495674177765 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5714285714285714, |
|
"acc_stderr": 0.013908353814606696 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7194013896312133, |
|
"acc_stderr": 0.010389809647288816 |
|
}, |
|
"boolq": { |
|
"acc": 0.6296636085626911, |
|
"acc_stderr": 0.008445882436783665 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5963804713804713, |
|
"acc_stderr": 0.01006736896034822, |
|
"acc_norm": 0.5382996632996633, |
|
"acc_norm_stderr": 0.010229639820610512 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2764505119453925, |
|
"acc_stderr": 0.013069662474252425, |
|
"acc_norm": 0.2960750853242321, |
|
"acc_norm_stderr": 0.013340916085246258 |
|
}, |
|
"sciq": { |
|
"acc": 0.853, |
|
"acc_stderr": 0.011203415395160336, |
|
"acc_norm": 0.762, |
|
"acc_norm_stderr": 0.013473586661967222 |
|
}, |
|
"piqa": { |
|
"acc": 0.750816104461371, |
|
"acc_stderr": 0.010091882770120216, |
|
"acc_norm": 0.7589771490750816, |
|
"acc_norm_stderr": 0.009979042717267312 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |