|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.356, |
|
"acc_stderr": 0.01514904265930663 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.363, |
|
"acc_stderr": 0.015213890444671285 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3625, |
|
"acc_stderr": 0.01388303787422552 |
|
}, |
|
"cb": { |
|
"acc": 0.5, |
|
"acc_stderr": 0.06741998624632421, |
|
"f1": 0.3261261261261261 |
|
}, |
|
"copa": { |
|
"acc": 0.65, |
|
"acc_stderr": 0.047937248544110196 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.39075881298546106, |
|
"acc_stderr": 0.0048692327581033226, |
|
"acc_norm": 0.4880501892053376, |
|
"acc_norm_stderr": 0.004988356146499007 |
|
}, |
|
"rte": { |
|
"acc": 0.5090252707581228, |
|
"acc_stderr": 0.030091559826331334 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5153906866614049, |
|
"acc_stderr": 0.014045826789783663 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6461785141635489, |
|
"acc_stderr": 0.011057260832171067 |
|
}, |
|
"boolq": { |
|
"acc": 0.5339449541284403, |
|
"acc_stderr": 0.008724878548525217 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.4852693602693603, |
|
"acc_stderr": 0.010255329977562098, |
|
"acc_norm": 0.47769360269360267, |
|
"acc_norm_stderr": 0.01024956840455565 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2363481228668942, |
|
"acc_stderr": 0.012414960524301836, |
|
"acc_norm": 0.26706484641638223, |
|
"acc_norm_stderr": 0.012928933196496357 |
|
}, |
|
"sciq": { |
|
"acc": 0.763, |
|
"acc_stderr": 0.01345407046257795, |
|
"acc_norm": 0.733, |
|
"acc_norm_stderr": 0.013996674851796275 |
|
}, |
|
"piqa": { |
|
"acc": 0.6996735582154516, |
|
"acc_stderr": 0.010695225308183133, |
|
"acc_norm": 0.6926006528835691, |
|
"acc_norm_stderr": 0.010765602506939061 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |