|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.325, |
|
"acc_stderr": 0.014818724459095524 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.328, |
|
"acc_stderr": 0.014853842487270336 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3416666666666667, |
|
"acc_stderr": 0.013696658778002519 |
|
}, |
|
"cb": { |
|
"acc": 0.44642857142857145, |
|
"acc_stderr": 0.06703189227942397, |
|
"f1": 0.28883861236802416 |
|
}, |
|
"copa": { |
|
"acc": 0.82, |
|
"acc_stderr": 0.038612291966536955 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4342760406293567, |
|
"acc_stderr": 0.004946485466544626, |
|
"acc_norm": 0.5595498904600678, |
|
"acc_norm_stderr": 0.0049542655953734695 |
|
}, |
|
"rte": { |
|
"acc": 0.5342960288808665, |
|
"acc_stderr": 0.030025579819366426 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5769534333070244, |
|
"acc_stderr": 0.013885055359056476 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7055050774986639, |
|
"acc_stderr": 0.010540668963800296 |
|
}, |
|
"boolq": { |
|
"acc": 0.582262996941896, |
|
"acc_stderr": 0.008625883905552707 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6026936026936027, |
|
"acc_stderr": 0.010041053078884277, |
|
"acc_norm": 0.5833333333333334, |
|
"acc_norm_stderr": 0.010116282977781253 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2764505119453925, |
|
"acc_stderr": 0.013069662474252427, |
|
"acc_norm": 0.3003412969283277, |
|
"acc_norm_stderr": 0.013395909309957 |
|
}, |
|
"sciq": { |
|
"acc": 0.87, |
|
"acc_stderr": 0.010640169792499344, |
|
"acc_norm": 0.849, |
|
"acc_norm_stderr": 0.011328165223341674 |
|
}, |
|
"piqa": { |
|
"acc": 0.7170837867247007, |
|
"acc_stderr": 0.010508949177489686, |
|
"acc_norm": 0.7241566920565833, |
|
"acc_norm_stderr": 0.010427805502729119 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |