|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.316, |
|
"acc_stderr": 0.014709193056057114 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.341, |
|
"acc_stderr": 0.014998131348402704 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3375, |
|
"acc_stderr": 0.013655897185463657 |
|
}, |
|
"cb": { |
|
"acc": 0.5178571428571429, |
|
"acc_stderr": 0.06737697508644647, |
|
"f1": 0.3271557271557271 |
|
}, |
|
"copa": { |
|
"acc": 0.75, |
|
"acc_stderr": 0.04351941398892446 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.47540330611431986, |
|
"acc_stderr": 0.0049837401452186075, |
|
"acc_norm": 0.6369249153555069, |
|
"acc_norm_stderr": 0.004799034356969407 |
|
}, |
|
"rte": { |
|
"acc": 0.555956678700361, |
|
"acc_stderr": 0.029907396333795983 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5832675611681136, |
|
"acc_stderr": 0.01385625007279632 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7247461250668092, |
|
"acc_stderr": 0.01032853840050057 |
|
}, |
|
"boolq": { |
|
"acc": 0.6394495412844037, |
|
"acc_stderr": 0.00839805483449795 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6342592592592593, |
|
"acc_stderr": 0.00988298806941883, |
|
"acc_norm": 0.6321548821548821, |
|
"acc_norm_stderr": 0.00989492346445519 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2960750853242321, |
|
"acc_stderr": 0.013340916085246266, |
|
"acc_norm": 0.32081911262798635, |
|
"acc_norm_stderr": 0.013640943091946528 |
|
}, |
|
"sciq": { |
|
"acc": 0.92, |
|
"acc_stderr": 0.008583336977753655, |
|
"acc_norm": 0.91, |
|
"acc_norm_stderr": 0.009054390204866442 |
|
}, |
|
"piqa": { |
|
"acc": 0.7546245919477693, |
|
"acc_stderr": 0.010039831320422396, |
|
"acc_norm": 0.7616974972796517, |
|
"acc_norm_stderr": 0.009940334245876224 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |