|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.309, |
|
"acc_stderr": 0.014619600977206493 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.325, |
|
"acc_stderr": 0.014818724459095524 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.32916666666666666, |
|
"acc_stderr": 0.013570806258433625 |
|
}, |
|
"cb": { |
|
"acc": 0.48214285714285715, |
|
"acc_stderr": 0.0673769750864465, |
|
"f1": 0.3338164251207729 |
|
}, |
|
"copa": { |
|
"acc": 0.79, |
|
"acc_stderr": 0.040936018074033256 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4766978689504083, |
|
"acc_stderr": 0.004984359669951929, |
|
"acc_norm": 0.6308504282015535, |
|
"acc_norm_stderr": 0.004815882719278398 |
|
}, |
|
"rte": { |
|
"acc": 0.5054151624548736, |
|
"acc_stderr": 0.030094698123239966 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5832675611681136, |
|
"acc_stderr": 0.013856250072796318 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7252805986103688, |
|
"acc_stderr": 0.010322309878339504 |
|
}, |
|
"boolq": { |
|
"acc": 0.6305810397553517, |
|
"acc_stderr": 0.008441557531799614 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6292087542087542, |
|
"acc_stderr": 0.009911292822056923, |
|
"acc_norm": 0.617003367003367, |
|
"acc_norm_stderr": 0.009974920384536482 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.27986348122866894, |
|
"acc_stderr": 0.01311904089772592, |
|
"acc_norm": 0.3191126279863481, |
|
"acc_norm_stderr": 0.013621696119173304 |
|
}, |
|
"sciq": { |
|
"acc": 0.902, |
|
"acc_stderr": 0.009406619184621252, |
|
"acc_norm": 0.885, |
|
"acc_norm_stderr": 0.01009340759490462 |
|
}, |
|
"piqa": { |
|
"acc": 0.7611534276387377, |
|
"acc_stderr": 0.009948120385337494, |
|
"acc_norm": 0.7665941240478781, |
|
"acc_norm_stderr": 0.009869247889520993 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |