Muennighoff's picture
Add eval
d522938
raw
history blame contribute delete
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.331,
"acc_stderr": 0.014888272588203936
},
"anli_r2": {
"acc": 0.323,
"acc_stderr": 0.01479492784334864
},
"anli_r3": {
"acc": 0.3416666666666667,
"acc_stderr": 0.013696658778002508
},
"cb": {
"acc": 0.4107142857142857,
"acc_stderr": 0.06633634150359541,
"f1": 0.2674860989171788
},
"copa": {
"acc": 0.73,
"acc_stderr": 0.0446196043338474
},
"hellaswag": {
"acc": 0.4281019717187811,
"acc_stderr": 0.004937924326742572,
"acc_norm": 0.559151563433579,
"acc_norm_stderr": 0.004954740808837193
},
"rte": {
"acc": 0.5379061371841155,
"acc_stderr": 0.030009848912529117
},
"winogrande": {
"acc": 0.5509076558800315,
"acc_stderr": 0.013979459389140846
},
"storycloze_2016": {
"acc": 0.6857295563869589,
"acc_stderr": 0.010735132285108182
},
"boolq": {
"acc": 0.563914373088685,
"acc_stderr": 0.008673312776324923
},
"arc_easy": {
"acc": 0.5963804713804713,
"acc_stderr": 0.010067368960348216,
"acc_norm": 0.5673400673400674,
"acc_norm_stderr": 0.01016630793264287
},
"arc_challenge": {
"acc": 0.2696245733788396,
"acc_stderr": 0.012968040686869152,
"acc_norm": 0.2832764505119454,
"acc_norm_stderr": 0.013167478735134575
},
"sciq": {
"acc": 0.883,
"acc_stderr": 0.010169287802713329,
"acc_norm": 0.872,
"acc_norm_stderr": 0.010570133761108663
},
"piqa": {
"acc": 0.733949945593036,
"acc_stderr": 0.010310039263352831,
"acc_norm": 0.7334058759521219,
"acc_norm_stderr": 0.010316749863541365
}
},
"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
}
}