|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.341, |
|
"acc_stderr": 0.0149981313484027 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.328, |
|
"acc_stderr": 0.014853842487270336 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3425, |
|
"acc_stderr": 0.013704669762934725 |
|
}, |
|
"cb": { |
|
"acc": 0.375, |
|
"acc_stderr": 0.06527912098338669, |
|
"f1": 0.24603174603174607 |
|
}, |
|
"copa": { |
|
"acc": 0.77, |
|
"acc_stderr": 0.04229525846816506 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.45140410276837284, |
|
"acc_stderr": 0.004966158142645419, |
|
"acc_norm": 0.5957976498705437, |
|
"acc_norm_stderr": 0.004897340793314379 |
|
}, |
|
"rte": { |
|
"acc": 0.5090252707581228, |
|
"acc_stderr": 0.030091559826331334 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5706393054459353, |
|
"acc_stderr": 0.013911537499969165 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6958845537145911, |
|
"acc_stderr": 0.010638172655194796 |
|
}, |
|
"boolq": { |
|
"acc": 0.6192660550458715, |
|
"acc_stderr": 0.008492625561656213 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5917508417508418, |
|
"acc_stderr": 0.010085566195791248, |
|
"acc_norm": 0.5517676767676768, |
|
"acc_norm_stderr": 0.010204645126856942 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.2713310580204778, |
|
"acc_stderr": 0.0129938077275458, |
|
"acc_norm": 0.29436860068259385, |
|
"acc_norm_stderr": 0.013318528460539424 |
|
}, |
|
"sciq": { |
|
"acc": 0.877, |
|
"acc_stderr": 0.010391293421849874, |
|
"acc_norm": 0.83, |
|
"acc_norm_stderr": 0.01188449583454167 |
|
}, |
|
"piqa": { |
|
"acc": 0.7410228509249184, |
|
"acc_stderr": 0.01022096603140561, |
|
"acc_norm": 0.749727965179543, |
|
"acc_norm_stderr": 0.01010656188008977 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |