lm1-4b2-84b-c4seeds / 4b284b21bc4seed4 /evaluation /rankeval /4b284b21bc4seed4_3_lm-eval_global_step80108_2023-02-15-11-04-03_3shots_backup.json
Muennighoff's picture
Add
31b4221
raw history blame
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.319,
"acc_stderr": 0.014746404865473472
},
"anli_r2": {
"acc": 0.345,
"acc_stderr": 0.015039986742055238
},
"anli_r3": {
"acc": 0.355,
"acc_stderr": 0.013819249004047303
},
"cb": {
"acc": 0.4642857142857143,
"acc_stderr": 0.06724777654937658,
"f1": 0.3181222134801993
},
"copa": {
"acc": 0.77,
"acc_stderr": 0.04229525846816506
},
"hellaswag": {
"acc": 0.47779326827325236,
"acc_stderr": 0.004984857671187105,
"acc_norm": 0.6338378809002191,
"acc_norm_stderr": 0.004807699539973427
},
"rte": {
"acc": 0.5595667870036101,
"acc_stderr": 0.029882123363118723
},
"winogrande": {
"acc": 0.5651144435674822,
"acc_stderr": 0.013932814110418024
},
"storycloze_2016": {
"acc": 0.7231427044361304,
"acc_stderr": 0.010347112890276929
},
"boolq": {
"acc": 0.5865443425076453,
"acc_stderr": 0.008613059239942641
},
"arc_easy": {
"acc": 0.6308922558922558,
"acc_stderr": 0.00990198741024273,
"acc_norm": 0.6026936026936027,
"acc_norm_stderr": 0.010041053078884286
},
"arc_challenge": {
"acc": 0.2883959044368601,
"acc_stderr": 0.013238394422428182,
"acc_norm": 0.318259385665529,
"acc_norm_stderr": 0.013611993916971453
},
"sciq": {
"acc": 0.903,
"acc_stderr": 0.009363689373248114,
"acc_norm": 0.893,
"acc_norm_stderr": 0.009779910359847165
},
"piqa": {
"acc": 0.7584330794341676,
"acc_stderr": 0.009986718001804463,
"acc_norm": 0.764961915125136,
"acc_norm_stderr": 0.009893146688805308
}
},
"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
}
}