Muennighoff's picture
Add eval
b851397
raw
history blame
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.325,
"acc_stderr": 0.014818724459095524
},
"anli_r2": {
"acc": 0.336,
"acc_stderr": 0.014944140233795021
},
"anli_r3": {
"acc": 0.3233333333333333,
"acc_stderr": 0.013508372867300212
},
"cb": {
"acc": 0.39285714285714285,
"acc_stderr": 0.0658538889806635,
"f1": 0.3565868967138097
},
"copa": {
"acc": 0.81,
"acc_stderr": 0.03942772444036623
},
"hellaswag": {
"acc": 0.4790878311093408,
"acc_stderr": 0.004985415250690914,
"acc_norm": 0.634833698466441,
"acc_norm_stderr": 0.004804927608773137
},
"rte": {
"acc": 0.6064981949458483,
"acc_stderr": 0.029405839314203194
},
"winogrande": {
"acc": 0.585635359116022,
"acc_stderr": 0.013844846232268563
},
"storycloze_2016": {
"acc": 0.7295563869588455,
"acc_stderr": 0.010271810373331027
},
"boolq": {
"acc": 0.6241590214067279,
"acc_stderr": 0.008471147248160107
},
"arc_easy": {
"acc": 0.6372053872053872,
"acc_stderr": 0.009865936757013942,
"acc_norm": 0.6186868686868687,
"acc_norm_stderr": 0.009966542497171021
},
"arc_challenge": {
"acc": 0.30119453924914674,
"acc_stderr": 0.013406741767847624,
"acc_norm": 0.32337883959044367,
"acc_norm_stderr": 0.01366942163001213
},
"sciq": {
"acc": 0.91,
"acc_stderr": 0.00905439020486644,
"acc_norm": 0.897,
"acc_norm_stderr": 0.009616833339695796
},
"piqa": {
"acc": 0.7540805223068553,
"acc_stderr": 0.01004733186562519,
"acc_norm": 0.7687704026115343,
"acc_norm_stderr": 0.009837063180625334
}
},
"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
}
}