Muennighoff's picture
Add eval
d522938
raw
history blame contribute delete
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.321,
"acc_stderr": 0.014770821817934642
},
"anli_r2": {
"acc": 0.348,
"acc_stderr": 0.01507060460376841
},
"anli_r3": {
"acc": 0.3283333333333333,
"acc_stderr": 0.013562032919529024
},
"cb": {
"acc": 0.4107142857142857,
"acc_stderr": 0.0663363415035954,
"f1": 0.26246498599439777
},
"copa": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446
},
"hellaswag": {
"acc": 0.4303923521210914,
"acc_stderr": 0.00494119160731791,
"acc_norm": 0.5641306512646883,
"acc_norm_stderr": 0.004948567856373856
},
"rte": {
"acc": 0.5306859205776173,
"acc_stderr": 0.03003973059219781
},
"winogrande": {
"acc": 0.5556432517758485,
"acc_stderr": 0.013965196769083555
},
"storycloze_2016": {
"acc": 0.6910742918225548,
"acc_stderr": 0.01068485396626845
},
"boolq": {
"acc": 0.5770642201834862,
"acc_stderr": 0.008640558744656428
},
"arc_easy": {
"acc": 0.6001683501683501,
"acc_stderr": 0.010051788039412925,
"acc_norm": 0.5740740740740741,
"acc_norm_stderr": 0.010146568651002255
},
"arc_challenge": {
"acc": 0.26791808873720135,
"acc_stderr": 0.012942030195136438,
"acc_norm": 0.30631399317406144,
"acc_norm_stderr": 0.013470584417276513
},
"sciq": {
"acc": 0.888,
"acc_stderr": 0.009977753031397236,
"acc_norm": 0.871,
"acc_norm_stderr": 0.010605256784796572
},
"piqa": {
"acc": 0.7442872687704026,
"acc_stderr": 0.010178690109459857,
"acc_norm": 0.7513601741022851,
"acc_norm_stderr": 0.010084511234296855
}
},
"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
}
}