Muennighoff's picture
Add eval
1aec95b
{
"results": {
"anli_r1": {
"acc": 0.339,
"acc_stderr": 0.014976758771620339
},
"anli_r2": {
"acc": 0.342,
"acc_stderr": 0.015008706182121728
},
"anli_r3": {
"acc": 0.37083333333333335,
"acc_stderr": 0.01394962856014431
},
"cb": {
"acc": 0.42857142857142855,
"acc_stderr": 0.06672848092813058,
"f1": 0.30272108843537415
},
"copa": {
"acc": 0.73,
"acc_stderr": 0.0446196043338474
},
"hellaswag": {
"acc": 0.4326827325234017,
"acc_stderr": 0.004944351065545858,
"acc_norm": 0.5660227046405099,
"acc_norm_stderr": 0.004946089230153027
},
"rte": {
"acc": 0.5415162454873647,
"acc_stderr": 0.02999253538537331
},
"winogrande": {
"acc": 0.5469613259668509,
"acc_stderr": 0.01399036663214809
},
"storycloze_2016": {
"acc": 0.6862640299305185,
"acc_stderr": 0.010730179119317625
},
"boolq": {
"acc": 0.6103975535168196,
"acc_stderr": 0.008529228894936293
},
"arc_easy": {
"acc": 0.5791245791245792,
"acc_stderr": 0.010130502164066342,
"acc_norm": 0.5357744107744108,
"acc_norm_stderr": 0.010233488709726539
},
"arc_challenge": {
"acc": 0.2687713310580205,
"acc_stderr": 0.01295506596371069,
"acc_norm": 0.2696245733788396,
"acc_norm_stderr": 0.012968040686869147
},
"sciq": {
"acc": 0.867,
"acc_stderr": 0.010743669132397332,
"acc_norm": 0.815,
"acc_norm_stderr": 0.012285191326386686
},
"piqa": {
"acc": 0.7366702937976061,
"acc_stderr": 0.010276185322196764,
"acc_norm": 0.7383025027203483,
"acc_norm_stderr": 0.010255630772708227
}
},
"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
}
}