|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.321, |
|
"acc_stderr": 0.01477082181793464 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.342, |
|
"acc_stderr": 0.01500870618212173 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.32083333333333336, |
|
"acc_stderr": 0.013480882752851552 |
|
}, |
|
"cb": { |
|
"acc": 0.5178571428571429, |
|
"acc_stderr": 0.06737697508644647, |
|
"f1": 0.35968427443837275 |
|
}, |
|
"copa": { |
|
"acc": 0.82, |
|
"acc_stderr": 0.038612291966536955 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.465345548695479, |
|
"acc_stderr": 0.004977782217582457, |
|
"acc_norm": 0.6182035451105358, |
|
"acc_norm_stderr": 0.004848341560492137 |
|
}, |
|
"rte": { |
|
"acc": 0.5595667870036101, |
|
"acc_stderr": 0.029882123363118712 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5753749013417522, |
|
"acc_stderr": 0.013891893150264224 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7242116515232496, |
|
"acc_stderr": 0.010334748387645672 |
|
}, |
|
"boolq": { |
|
"acc": 0.6125382262996942, |
|
"acc_stderr": 0.00852066653613694 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6224747474747475, |
|
"acc_stderr": 0.009947227833469432, |
|
"acc_norm": 0.601010101010101, |
|
"acc_norm_stderr": 0.010048240683798745 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.28071672354948807, |
|
"acc_stderr": 0.013131238126975588, |
|
"acc_norm": 0.3191126279863481, |
|
"acc_norm_stderr": 0.013621696119173297 |
|
}, |
|
"sciq": { |
|
"acc": 0.905, |
|
"acc_stderr": 0.009276910103103305, |
|
"acc_norm": 0.902, |
|
"acc_norm_stderr": 0.009406619184621235 |
|
}, |
|
"piqa": { |
|
"acc": 0.7464635473340587, |
|
"acc_stderr": 0.010150090834551782, |
|
"acc_norm": 0.7557127312295974, |
|
"acc_norm_stderr": 0.010024765172284256 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |