Muennighoff's picture
Add
83391d7
raw
history blame
2.47 kB
{
"results": {
"anli_r1": {
"acc": 0.337,
"acc_stderr": 0.014955087918653607
},
"anli_r2": {
"acc": 0.362,
"acc_stderr": 0.015204840912919498
},
"anli_r3": {
"acc": 0.36583333333333334,
"acc_stderr": 0.013910212062701167
},
"cb": {
"acc": 0.5178571428571429,
"acc_stderr": 0.06737697508644647,
"f1": 0.27628205128205124
},
"copa": {
"acc": 0.67,
"acc_stderr": 0.04725815626252606
},
"hellaswag": {
"acc": 0.40619398526190004,
"acc_stderr": 0.004901178917900842,
"acc_norm": 0.5022903804023103,
"acc_norm_stderr": 0.004989729059957431
},
"rte": {
"acc": 0.5090252707581228,
"acc_stderr": 0.030091559826331334
},
"winogrande": {
"acc": 0.5280189423835833,
"acc_stderr": 0.01403040421340578
},
"storycloze_2016": {
"acc": 0.6606092998396579,
"acc_stderr": 0.010949682016358629
},
"boolq": {
"acc": 0.5409785932721712,
"acc_stderr": 0.008715635308774413
},
"arc_easy": {
"acc": 0.4903198653198653,
"acc_stderr": 0.010257860554461127,
"acc_norm": 0.47474747474747475,
"acc_norm_stderr": 0.010246690042583842
},
"arc_challenge": {
"acc": 0.24146757679180889,
"acc_stderr": 0.012506564839739434,
"acc_norm": 0.26621160409556316,
"acc_norm_stderr": 0.012915774781523214
},
"sciq": {
"acc": 0.761,
"acc_stderr": 0.013493000446937591,
"acc_norm": 0.726,
"acc_norm_stderr": 0.014111099288259588
},
"piqa": {
"acc": 0.7072905331882481,
"acc_stderr": 0.010616044462393092,
"acc_norm": 0.7072905331882481,
"acc_norm_stderr": 0.010616044462393094
}
},
"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
}
}