|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.332, |
|
"acc_stderr": 0.014899597242811476 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.321, |
|
"acc_stderr": 0.014770821817934652 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3425, |
|
"acc_stderr": 0.013704669762934722 |
|
}, |
|
"cb": { |
|
"acc": 0.5, |
|
"acc_stderr": 0.06741998624632421, |
|
"f1": 0.3487553126897389 |
|
}, |
|
"copa": { |
|
"acc": 0.71, |
|
"acc_stderr": 0.04560480215720684 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4334793865763792, |
|
"acc_stderr": 0.004945424771611597, |
|
"acc_norm": 0.5631348336984664, |
|
"acc_norm_stderr": 0.004949842967331438 |
|
}, |
|
"rte": { |
|
"acc": 0.5667870036101083, |
|
"acc_stderr": 0.02982676408213828 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5509076558800315, |
|
"acc_stderr": 0.013979459389140848 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6835916622127205, |
|
"acc_stderr": 0.01075478009794089 |
|
}, |
|
"boolq": { |
|
"acc": 0.6012232415902141, |
|
"acc_stderr": 0.008563973987729913 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5698653198653199, |
|
"acc_stderr": 0.010159130445178492, |
|
"acc_norm": 0.5429292929292929, |
|
"acc_norm_stderr": 0.01022189756425604 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.24744027303754265, |
|
"acc_stderr": 0.01261035266329267, |
|
"acc_norm": 0.2738907849829352, |
|
"acc_norm_stderr": 0.013032004972989501 |
|
}, |
|
"sciq": { |
|
"acc": 0.88, |
|
"acc_stderr": 0.010281328012747394, |
|
"acc_norm": 0.844, |
|
"acc_norm_stderr": 0.011480235006122361 |
|
}, |
|
"piqa": { |
|
"acc": 0.733949945593036, |
|
"acc_stderr": 0.010310039263352831, |
|
"acc_norm": 0.7421109902067464, |
|
"acc_norm_stderr": 0.010206956662056245 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |