|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.332, |
|
"acc_stderr": 0.014899597242811475 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.333, |
|
"acc_stderr": 0.014910846164229864 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.34, |
|
"acc_stderr": 0.013680495725767797 |
|
}, |
|
"cb": { |
|
"acc": 0.35714285714285715, |
|
"acc_stderr": 0.06460957383809218, |
|
"f1": 0.2528248587570622 |
|
}, |
|
"copa": { |
|
"acc": 0.77, |
|
"acc_stderr": 0.04229525846816506 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.46932881896036643, |
|
"acc_stderr": 0.004980384575535383, |
|
"acc_norm": 0.6172077275443139, |
|
"acc_norm_stderr": 0.0048507486878599185 |
|
}, |
|
"rte": { |
|
"acc": 0.4693140794223827, |
|
"acc_stderr": 0.03003973059219781 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5927387529597474, |
|
"acc_stderr": 0.013808654122417862 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7183324425440941, |
|
"acc_stderr": 0.010401844358587665 |
|
}, |
|
"boolq": { |
|
"acc": 0.6180428134556575, |
|
"acc_stderr": 0.00849785199842719 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6195286195286195, |
|
"acc_stderr": 0.009962305992058577, |
|
"acc_norm": 0.5959595959595959, |
|
"acc_norm_stderr": 0.01006906164954955 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.295221843003413, |
|
"acc_stderr": 0.01332975029338232, |
|
"acc_norm": 0.30802047781569963, |
|
"acc_norm_stderr": 0.013491429517292038 |
|
}, |
|
"sciq": { |
|
"acc": 0.896, |
|
"acc_stderr": 0.009658016218524301, |
|
"acc_norm": 0.871, |
|
"acc_norm_stderr": 0.010605256784796586 |
|
}, |
|
"piqa": { |
|
"acc": 0.7464635473340587, |
|
"acc_stderr": 0.010150090834551794, |
|
"acc_norm": 0.7573449401523396, |
|
"acc_norm_stderr": 0.010002002569708688 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |