|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.321, |
|
"acc_stderr": 0.014770821817934635 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.334, |
|
"acc_stderr": 0.01492201952373296 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.32, |
|
"acc_stderr": 0.013471620929769135 |
|
}, |
|
"cb": { |
|
"acc": 0.42857142857142855, |
|
"acc_stderr": 0.06672848092813058, |
|
"f1": 0.2988943957300801 |
|
}, |
|
"copa": { |
|
"acc": 0.78, |
|
"acc_stderr": 0.04163331998932261 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.45130452101175067, |
|
"acc_stderr": 0.004966060995315068, |
|
"acc_norm": 0.5956980681139216, |
|
"acc_norm_stderr": 0.004897534686686327 |
|
}, |
|
"rte": { |
|
"acc": 0.516245487364621, |
|
"acc_stderr": 0.030080573208738064 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5714285714285714, |
|
"acc_stderr": 0.013908353814606686 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6980224478888295, |
|
"acc_stderr": 0.010616985436073357 |
|
}, |
|
"boolq": { |
|
"acc": 0.617737003058104, |
|
"acc_stderr": 0.008499149690449272 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6043771043771043, |
|
"acc_stderr": 0.010033741393430986, |
|
"acc_norm": 0.5778619528619529, |
|
"acc_norm_stderr": 0.01013462052459227 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.27303754266211605, |
|
"acc_stderr": 0.01301933276263575, |
|
"acc_norm": 0.30119453924914674, |
|
"acc_norm_stderr": 0.013406741767847626 |
|
}, |
|
"sciq": { |
|
"acc": 0.896, |
|
"acc_stderr": 0.009658016218524305, |
|
"acc_norm": 0.863, |
|
"acc_norm_stderr": 0.010878848714333316 |
|
}, |
|
"piqa": { |
|
"acc": 0.7377584330794341, |
|
"acc_stderr": 0.01026250256517245, |
|
"acc_norm": 0.7442872687704026, |
|
"acc_norm_stderr": 0.01017869010945987 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |