|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.341, |
|
"acc_stderr": 0.014998131348402707 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.343, |
|
"acc_stderr": 0.015019206922356953 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.32666666666666666, |
|
"acc_stderr": 0.013544340907003665 |
|
}, |
|
"cb": { |
|
"acc": 0.25, |
|
"acc_stderr": 0.058387420812114225, |
|
"f1": 0.2075098814229249 |
|
}, |
|
"copa": { |
|
"acc": 0.73, |
|
"acc_stderr": 0.044619604333847394 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.40728938458474406, |
|
"acc_stderr": 0.0049032542641776235, |
|
"acc_norm": 0.5259908384783908, |
|
"acc_norm_stderr": 0.004983035420235712 |
|
}, |
|
"rte": { |
|
"acc": 0.5054151624548736, |
|
"acc_stderr": 0.030094698123239966 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5516969218626677, |
|
"acc_stderr": 0.013977171307126345 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6675574559059326, |
|
"acc_stderr": 0.010893860778343539 |
|
}, |
|
"boolq": { |
|
"acc": 0.5795107033639144, |
|
"acc_stderr": 0.008633775332463619 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6031144781144782, |
|
"acc_stderr": 0.010039236800583206, |
|
"acc_norm": 0.5858585858585859, |
|
"acc_norm_stderr": 0.01010738767300251 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.25853242320819114, |
|
"acc_stderr": 0.012794553754288692, |
|
"acc_norm": 0.29948805460750855, |
|
"acc_norm_stderr": 0.013385021637313572 |
|
}, |
|
"sciq": { |
|
"acc": 0.902, |
|
"acc_stderr": 0.00940661918462124, |
|
"acc_norm": 0.9, |
|
"acc_norm_stderr": 0.009491579957525044 |
|
}, |
|
"piqa": { |
|
"acc": 0.7219804134929271, |
|
"acc_stderr": 0.010453117358332795, |
|
"acc_norm": 0.7236126224156693, |
|
"acc_norm_stderr": 0.010434162388275608 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |