lm1-misc-pile / 421m32b32b /421m32b32bpile /evaluation /rankeval /lm1-421m-32b-results_lm-eval_global_step60336_2023-01-22-18-55-49_0shots.json
Muennighoff's picture
Add
0461a88
{
"results": {
"anli_r1": {
"acc": 0.339,
"acc_stderr": 0.01497675877162034
},
"anli_r2": {
"acc": 0.342,
"acc_stderr": 0.015008706182121728
},
"anli_r3": {
"acc": 0.36666666666666664,
"acc_stderr": 0.013916893275819934
},
"cb": {
"acc": 0.39285714285714285,
"acc_stderr": 0.0658538889806635,
"f1": 0.20750000000000002
},
"copa": {
"acc": 0.63,
"acc_stderr": 0.04852365870939099
},
"hellaswag": {
"acc": 0.29944234216291576,
"acc_stderr": 0.004570777326263895,
"acc_norm": 0.3315076677952599,
"acc_norm_stderr": 0.004697929774670284
},
"rte": {
"acc": 0.5306859205776173,
"acc_stderr": 0.030039730592197812
},
"winogrande": {
"acc": 0.5224940805051302,
"acc_stderr": 0.014038257824059886
},
"storycloze_2016": {
"acc": 0.5954035275253875,
"acc_stderr": 0.011350002165791937
},
"boolq": {
"acc": 0.5948012232415902,
"acc_stderr": 0.008586427929715531
},
"arc_easy": {
"acc": 0.4722222222222222,
"acc_stderr": 0.010243938285881115,
"acc_norm": 0.4276094276094276,
"acc_norm_stderr": 0.010151683397430685
},
"arc_challenge": {
"acc": 0.19795221843003413,
"acc_stderr": 0.0116439909715734,
"acc_norm": 0.23378839590443687,
"acc_norm_stderr": 0.012368225378507137
},
"sciq": {
"acc": 0.803,
"acc_stderr": 0.01258369378796813,
"acc_norm": 0.717,
"acc_norm_stderr": 0.014251810906481737
},
"piqa": {
"acc": 0.6409140369967355,
"acc_stderr": 0.0111929490738441,
"acc_norm": 0.6376496191512514,
"acc_norm_stderr": 0.01121504021510457
}
},
"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
}
}