Muennighoff's picture
Add eval
d522938
raw
history blame
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.357,
"acc_stderr": 0.015158521721486773
},
"anli_r2": {
"acc": 0.361,
"acc_stderr": 0.015195720118175118
},
"anli_r3": {
"acc": 0.3525,
"acc_stderr": 0.013797164918918362
},
"cb": {
"acc": 0.4642857142857143,
"acc_stderr": 0.06724777654937658,
"f1": 0.33484504913076335
},
"copa": {
"acc": 0.76,
"acc_stderr": 0.04292346959909283
},
"hellaswag": {
"acc": 0.4325831507667795,
"acc_stderr": 0.004944215937021392,
"acc_norm": 0.5673172674765983,
"acc_norm_stderr": 0.004944351065545863
},
"rte": {
"acc": 0.5306859205776173,
"acc_stderr": 0.03003973059219781
},
"winogrande": {
"acc": 0.569060773480663,
"acc_stderr": 0.01391779662333597
},
"storycloze_2016": {
"acc": 0.6873329770176376,
"acc_stderr": 0.010720223172953168
},
"boolq": {
"acc": 0.6055045871559633,
"acc_stderr": 0.008548152025770934
},
"arc_easy": {
"acc": 0.5862794612794613,
"acc_stderr": 0.010105878530238137,
"acc_norm": 0.5622895622895623,
"acc_norm_stderr": 0.010179856486006897
},
"arc_challenge": {
"acc": 0.2815699658703072,
"acc_stderr": 0.013143376735009024,
"acc_norm": 0.2909556313993174,
"acc_norm_stderr": 0.013273077865907597
},
"sciq": {
"acc": 0.889,
"acc_stderr": 0.009938701010583726,
"acc_norm": 0.886,
"acc_norm_stderr": 0.010055103435823328
},
"piqa": {
"acc": 0.7372143634385201,
"acc_stderr": 0.010269354068140767,
"acc_norm": 0.7372143634385201,
"acc_norm_stderr": 0.010269354068140777
}
},
"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
}
}