lm1-2b8-55b-c4-dedup / evaluation /rankeval /lm1-2b8-55b-nodups_5.json
Muennighoff's picture
add
874e9d6
{
"results": {
"anli_r1": {
"acc": 0.32,
"acc_stderr": 0.014758652303574876
},
"anli_r2": {
"acc": 0.34,
"acc_stderr": 0.014987482264363937
},
"anli_r3": {
"acc": 0.345,
"acc_stderr": 0.013728421539454881
},
"cb": {
"acc": 0.44642857142857145,
"acc_stderr": 0.06703189227942397,
"f1": 0.42175558247707934
},
"copa": {
"acc": 0.8,
"acc_stderr": 0.040201512610368445
},
"hellaswag": {
"acc": 0.4334793865763792,
"acc_stderr": 0.004945424771611596,
"acc_norm": 0.5747858992232623,
"acc_norm_stderr": 0.004933650697000599
},
"rte": {
"acc": 0.5342960288808665,
"acc_stderr": 0.030025579819366426
},
"winogrande": {
"acc": 0.5619573796369376,
"acc_stderr": 0.013944181296470804
},
"storycloze_2016": {
"acc": 0.7145911277391769,
"acc_stderr": 0.010443395884062106
},
"boolq": {
"acc": 0.4853211009174312,
"acc_stderr": 0.00874128556866792
},
"arc_easy": {
"acc": 0.577020202020202,
"acc_stderr": 0.010137328382209097,
"acc_norm": 0.5538720538720538,
"acc_norm_stderr": 0.01020005782876501
},
"arc_challenge": {
"acc": 0.2525597269624573,
"acc_stderr": 0.01269672898020771,
"acc_norm": 0.2790102389078498,
"acc_norm_stderr": 0.013106784883601343
},
"sciq": {
"acc": 0.868,
"acc_stderr": 0.010709373963528031,
"acc_norm": 0.85,
"acc_norm_stderr": 0.011297239823409296
},
"piqa": {
"acc": 0.7464635473340587,
"acc_stderr": 0.010150090834551786,
"acc_norm": 0.7584330794341676,
"acc_norm_stderr": 0.00998671800180446
}
},
"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
}
}