Muennighoff's picture
Add
d7c2560
raw
history blame
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.34,
"acc_stderr": 0.014987482264363935
},
"anli_r2": {
"acc": 0.347,
"acc_stderr": 0.015060472031706617
},
"anli_r3": {
"acc": 0.3325,
"acc_stderr": 0.01360541734571053
},
"cb": {
"acc": 0.32142857142857145,
"acc_stderr": 0.06297362289056341,
"f1": 0.1621621621621622
},
"copa": {
"acc": 0.82,
"acc_stderr": 0.038612291966536955
},
"hellaswag": {
"acc": 0.48008364867556264,
"acc_stderr": 0.0049858213361464,
"acc_norm": 0.6368253335988847,
"acc_norm_stderr": 0.00479931720990201
},
"rte": {
"acc": 0.5595667870036101,
"acc_stderr": 0.029882123363118716
},
"winogrande": {
"acc": 0.6179952644041041,
"acc_stderr": 0.013655578215970424
},
"storycloze_2016": {
"acc": 0.7279529663281668,
"acc_stderr": 0.010290888060871242
},
"boolq": {
"acc": 0.6214067278287462,
"acc_stderr": 0.00848334171802448
},
"arc_easy": {
"acc": 0.6477272727272727,
"acc_stderr": 0.009801753933112778,
"acc_norm": 0.6199494949494949,
"acc_norm_stderr": 0.009960175831493124
},
"arc_challenge": {
"acc": 0.30119453924914674,
"acc_stderr": 0.01340674176784762,
"acc_norm": 0.32337883959044367,
"acc_norm_stderr": 0.013669421630012123
},
"sciq": {
"acc": 0.918,
"acc_stderr": 0.008680515615523722,
"acc_norm": 0.914,
"acc_norm_stderr": 0.008870325962594766
},
"piqa": {
"acc": 0.7524483133841132,
"acc_stderr": 0.01006970396685711,
"acc_norm": 0.7747551686615887,
"acc_norm_stderr": 0.009746643471032136
}
},
"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
}
}