lm1-misc-pile / 3b92b62b6 /evaluation /rankeval /lm1-3b9-26b-results_lm-eval_global_step24424_2023-01-22-13-12-25_0shots.json
Muennighoff's picture
Add
0461a88
{
"results": {
"anli_r1": {
"acc": 0.323,
"acc_stderr": 0.014794927843348633
},
"anli_r2": {
"acc": 0.333,
"acc_stderr": 0.014910846164229863
},
"anli_r3": {
"acc": 0.33166666666666667,
"acc_stderr": 0.013596836729485168
},
"cb": {
"acc": 0.2857142857142857,
"acc_stderr": 0.06091449038731724,
"f1": 0.15023474178403756
},
"copa": {
"acc": 0.7,
"acc_stderr": 0.046056618647183814
},
"hellaswag": {
"acc": 0.3355905198167696,
"acc_stderr": 0.004712314511950957,
"acc_norm": 0.39713204540928104,
"acc_norm_stderr": 0.004883037758919961
},
"rte": {
"acc": 0.51985559566787,
"acc_stderr": 0.030072723167317184
},
"winogrande": {
"acc": 0.4964483030781373,
"acc_stderr": 0.014052131146915864
},
"storycloze_2016": {
"acc": 0.6264029930518439,
"acc_stderr": 0.011186849693644694
},
"boolq": {
"acc": 0.5318042813455658,
"acc_stderr": 0.008727345583419182
},
"arc_easy": {
"acc": 0.515993265993266,
"acc_stderr": 0.010254533589288163,
"acc_norm": 0.4659090909090909,
"acc_norm_stderr": 0.010235908103438692
},
"arc_challenge": {
"acc": 0.1962457337883959,
"acc_stderr": 0.011606019881416286,
"acc_norm": 0.257679180887372,
"acc_norm_stderr": 0.01278077056276841
},
"sciq": {
"acc": 0.822,
"acc_stderr": 0.01210216767618359,
"acc_norm": 0.731,
"acc_norm_stderr": 0.014029819522568198
},
"piqa": {
"acc": 0.6605005440696409,
"acc_stderr": 0.011048455047173915,
"acc_norm": 0.6621327529923831,
"acc_norm_stderr": 0.011035474307853841
}
},
"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
}
}