lm1-misc-pile / 221m60b60b /evaluation /rankeval /lm1-221m-60b-results_lm-eval_global_step115203_2023-01-24-13-57-03_3shots.json
Muennighoff's picture
Add
c305798
{
"results": {
"anli_r1": {
"acc": 0.327,
"acc_stderr": 0.014842213153411244
},
"anli_r2": {
"acc": 0.345,
"acc_stderr": 0.015039986742055238
},
"anli_r3": {
"acc": 0.33166666666666667,
"acc_stderr": 0.013596836729485164
},
"cb": {
"acc": 0.48214285714285715,
"acc_stderr": 0.0673769750864465,
"f1": 0.4053571428571429
},
"copa": {
"acc": 0.63,
"acc_stderr": 0.04852365870939099
},
"hellaswag": {
"acc": 0.2900816570404302,
"acc_stderr": 0.004528723951878255,
"acc_norm": 0.31866162119099783,
"acc_norm_stderr": 0.00465005215009441
},
"rte": {
"acc": 0.5090252707581228,
"acc_stderr": 0.030091559826331334
},
"winogrande": {
"acc": 0.5059194948697711,
"acc_stderr": 0.014051500838485807
},
"storycloze_2016": {
"acc": 0.5905932656333511,
"acc_stderr": 0.01137105952719707
},
"boolq": {
"acc": 0.5278287461773701,
"acc_stderr": 0.008731499445069572
},
"arc_easy": {
"acc": 0.4675925925925926,
"acc_stderr": 0.010238210368801893,
"acc_norm": 0.44612794612794615,
"acc_norm_stderr": 0.01020005782876501
},
"arc_challenge": {
"acc": 0.20819112627986347,
"acc_stderr": 0.011864866118448069,
"acc_norm": 0.2380546075085324,
"acc_norm_stderr": 0.012445770028026206
},
"sciq": {
"acc": 0.833,
"acc_stderr": 0.011800434324644591,
"acc_norm": 0.8,
"acc_norm_stderr": 0.012655439943366655
},
"piqa": {
"acc": 0.6322089227421109,
"acc_stderr": 0.011250616646678795,
"acc_norm": 0.6349292709466812,
"acc_norm_stderr": 0.01123302183055483
}
},
"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
}
}