|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.334, |
|
"acc_stderr": 0.014922019523732967 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.325, |
|
"acc_stderr": 0.014818724459095527 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3441666666666667, |
|
"acc_stderr": 0.013720551062295756 |
|
}, |
|
"cb": { |
|
"acc": 0.4107142857142857, |
|
"acc_stderr": 0.0663363415035954, |
|
"f1": 0.1940928270042194 |
|
}, |
|
"copa": { |
|
"acc": 0.79, |
|
"acc_stderr": 0.040936018074033256 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.46415056761601275, |
|
"acc_stderr": 0.0049769393332400776, |
|
"acc_norm": 0.6052579167496515, |
|
"acc_norm_stderr": 0.0048779626449918555 |
|
}, |
|
"rte": { |
|
"acc": 0.5270758122743683, |
|
"acc_stderr": 0.0300523034631437 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5824782951854776, |
|
"acc_stderr": 0.013859978264440251 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.7151256012827365, |
|
"acc_stderr": 0.010437513986611718 |
|
}, |
|
"boolq": { |
|
"acc": 0.591131498470948, |
|
"acc_stderr": 0.008598573693259106 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5660774410774411, |
|
"acc_stderr": 0.010169795770462111, |
|
"acc_norm": 0.5084175084175084, |
|
"acc_norm_stderr": 0.010258329515226459 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.26023890784982934, |
|
"acc_stderr": 0.012821930225112568, |
|
"acc_norm": 0.2790102389078498, |
|
"acc_norm_stderr": 0.01310678488360133 |
|
}, |
|
"sciq": { |
|
"acc": 0.829, |
|
"acc_stderr": 0.011912216456264607, |
|
"acc_norm": 0.751, |
|
"acc_norm_stderr": 0.013681600278702301 |
|
}, |
|
"piqa": { |
|
"acc": 0.7404787812840044, |
|
"acc_stderr": 0.01022793988817392, |
|
"acc_norm": 0.7431991294885746, |
|
"acc_norm_stderr": 0.01019286480227804 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |