|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.334, |
|
"acc_stderr": 0.01492201952373296 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.335, |
|
"acc_stderr": 0.014933117490932572 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.33166666666666667, |
|
"acc_stderr": 0.01359683672948516 |
|
}, |
|
"cb": { |
|
"acc": 0.4107142857142857, |
|
"acc_stderr": 0.0663363415035954, |
|
"f1": 0.1940928270042194 |
|
}, |
|
"copa": { |
|
"acc": 0.7, |
|
"acc_stderr": 0.046056618647183814 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.36666002788289187, |
|
"acc_stderr": 0.004809077205343495, |
|
"acc_norm": 0.4478191595299741, |
|
"acc_norm_stderr": 0.004962534264751926 |
|
}, |
|
"rte": { |
|
"acc": 0.5270758122743683, |
|
"acc_stderr": 0.030052303463143706 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5382794001578532, |
|
"acc_stderr": 0.014011242594964115 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6493853554249065, |
|
"acc_stderr": 0.011034317290463292 |
|
}, |
|
"boolq": { |
|
"acc": 0.5415902140672783, |
|
"acc_stderr": 0.00871474901770989 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5168350168350169, |
|
"acc_stderr": 0.010253966261288907, |
|
"acc_norm": 0.45454545454545453, |
|
"acc_norm_stderr": 0.010217299762709433 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.22525597269624573, |
|
"acc_stderr": 0.01220783999540731, |
|
"acc_norm": 0.25426621160409557, |
|
"acc_norm_stderr": 0.012724999945157738 |
|
}, |
|
"sciq": { |
|
"acc": 0.809, |
|
"acc_stderr": 0.012436787112179467, |
|
"acc_norm": 0.711, |
|
"acc_norm_stderr": 0.01434171135829618 |
|
}, |
|
"piqa": { |
|
"acc": 0.6931447225244831, |
|
"acc_stderr": 0.010760295070580359, |
|
"acc_norm": 0.6942328618063112, |
|
"acc_norm_stderr": 0.010749627366141646 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |