Muennighoff's picture
Add
02384d6
raw
history blame contribute delete
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.325,
"acc_stderr": 0.014818724459095526
},
"anli_r2": {
"acc": 0.303,
"acc_stderr": 0.014539683710535246
},
"anli_r3": {
"acc": 0.3458333333333333,
"acc_stderr": 0.013736245342311014
},
"cb": {
"acc": 0.5,
"acc_stderr": 0.06741998624632421,
"f1": 0.3554421768707483
},
"copa": {
"acc": 0.77,
"acc_stderr": 0.04229525846816506
},
"hellaswag": {
"acc": 0.462158932483569,
"acc_stderr": 0.0049754706908671535,
"acc_norm": 0.6109340768771161,
"acc_norm_stderr": 0.0048654194682138914
},
"rte": {
"acc": 0.5451263537906137,
"acc_stderr": 0.029973636495415252
},
"winogrande": {
"acc": 0.5982636148382005,
"acc_stderr": 0.0137784392666495
},
"storycloze_2016": {
"acc": 0.7006948156066275,
"acc_stderr": 0.010590117252248798
},
"boolq": {
"acc": 0.5474006116207951,
"acc_stderr": 0.008705669190431184
},
"arc_easy": {
"acc": 0.6553030303030303,
"acc_stderr": 0.009752321586569784,
"acc_norm": 0.6435185185185185,
"acc_norm_stderr": 0.009828046544504438
},
"arc_challenge": {
"acc": 0.3148464163822526,
"acc_stderr": 0.01357265770308495,
"acc_norm": 0.32764505119453924,
"acc_norm_stderr": 0.013715847940719348
},
"sciq": {
"acc": 0.904,
"acc_stderr": 0.009320454434783219,
"acc_norm": 0.901,
"acc_norm_stderr": 0.009449248027662737
},
"piqa": {
"acc": 0.7535364526659413,
"acc_stderr": 0.010054810789671822,
"acc_norm": 0.7622415669205659,
"acc_norm_stderr": 0.009932525779525492
}
},
"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
}
}