lm1-misc-pile / 421m32b32b /421m32b32bpile /evaluation /rankeval /lm1-421m-32b-results_lm-eval_global_step60336_2023-01-24-13-57-03_3shots.json
Muennighoff's picture
Add
0461a88
{
"results": {
"anli_r1": {
"acc": 0.318,
"acc_stderr": 0.014734079309311901
},
"anli_r2": {
"acc": 0.338,
"acc_stderr": 0.014965960710224473
},
"anli_r3": {
"acc": 0.3433333333333333,
"acc_stderr": 0.01371263383046586
},
"cb": {
"acc": 0.5,
"acc_stderr": 0.06741998624632421,
"f1": 0.43006045445069835
},
"copa": {
"acc": 0.64,
"acc_stderr": 0.04824181513244218
},
"hellaswag": {
"acc": 0.3004381597291376,
"acc_stderr": 0.0045751160939318854,
"acc_norm": 0.33120892252539336,
"acc_norm_stderr": 0.004696861625496918
},
"rte": {
"acc": 0.5054151624548736,
"acc_stderr": 0.03009469812323996
},
"winogrande": {
"acc": 0.5248618784530387,
"acc_stderr": 0.01403510288362775
},
"storycloze_2016": {
"acc": 0.589524318546232,
"acc_stderr": 0.011375585931640946
},
"boolq": {
"acc": 0.5412844036697247,
"acc_stderr": 0.00871519381578829
},
"arc_easy": {
"acc": 0.484006734006734,
"acc_stderr": 0.010254533589288182,
"acc_norm": 0.4617003367003367,
"acc_norm_stderr": 0.01022963982061052
},
"arc_challenge": {
"acc": 0.2090443686006826,
"acc_stderr": 0.011882746987406453,
"acc_norm": 0.22696245733788395,
"acc_norm_stderr": 0.012240491536132866
},
"sciq": {
"acc": 0.821,
"acc_stderr": 0.012128730605719118,
"acc_norm": 0.797,
"acc_norm_stderr": 0.01272607374459827
},
"piqa": {
"acc": 0.6398258977149075,
"acc_stderr": 0.011200375176667486,
"acc_norm": 0.6441784548422198,
"acc_norm_stderr": 0.01117029493465695
}
},
"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
}
}