sev / test_eval.json
minhleduc's picture
Mirror laya-typed-decisions-ce-1024 (CE-only, 1024/256) + model card
f9e4c79 verified
Raw
History Blame Contribute Delete
2.97 kB
{
"raw": {
"ece": 0.14405169022083278,
"brier": 0.049473914223986594,
"nll": 0.8580627283966169,
"accuracy": 0.7885,
"soft_accuracy": 0.5236424660123885,
"mean_confidence": 0.6444483368843794,
"mean_target_max": 0.6589462240487337,
"score_mae": 0.21151374208275228,
"n": 2000,
"by_type": {
"choice": {
"ece": 0.1381368541220824,
"brier": 0.0610927829263998,
"nll": 0.9818144658269982,
"accuracy": 0.755,
"soft_accuracy": 0.48078609759608903,
"mean_confidence": 0.6193696513772011,
"mean_target_max": 0.6345381752649943,
"score_mae": null,
"n": 600
},
"score": {
"ece": 0.1779335317760706,
"brier": 0.05114634511056351,
"nll": 1.03313795868773,
"accuracy": 0.75875,
"soft_accuracy": 0.4435949847009033,
"mean_confidence": 0.5816603348776698,
"mean_target_max": 0.5928848401084542,
"score_mae": 0.21151374208275228,
"n": 800
},
"noul": {
"ece": 0.10842230906089145,
"brier": 0.03562513767280417,
"nll": 0.5008773505780846,
"accuracy": 0.8616666666666667,
"soft_accuracy": 0.6732288095106681,
"mean_confidence": 0.7532443584005037,
"mean_target_max": 0.7714361180861791,
"score_mae": null,
"n": 600
}
}
},
"post_temperature": {
"ece": 0.16220938038825988,
"brier": 0.04794188590972476,
"nll": 0.8542706172754988,
"accuracy": 0.7885,
"soft_accuracy": 0.5147140698879957,
"mean_confidence": 0.6262906277328729,
"mean_target_max": 0.6589462240487337,
"score_mae": 0.21261174298007973,
"n": 2000,
"by_type": {
"choice": {
"ece": 0.16171381801366805,
"brier": 0.058598528968896064,
"nll": 0.9764881309494376,
"accuracy": 0.755,
"soft_accuracy": 0.46792497878273326,
"mean_confidence": 0.5932861614724,
"mean_target_max": 0.6345381752649943,
"score_mae": null,
"n": 600
},
"score": {
"ece": 0.19320389255881307,
"brier": 0.04962007356784852,
"nll": 1.0289345176471398,
"accuracy": 0.75875,
"soft_accuracy": 0.4367176624760032,
"mean_confidence": 0.5665761560201645,
"mean_target_max": 0.5928848401084542,
"score_mae": 0.21261174298007973,
"n": 800
},
"noul": {
"ece": 0.12275225609540938,
"brier": 0.035047659306388444,
"nll": 0.49916790310603876,
"accuracy": 0.8616666666666667,
"soft_accuracy": 0.6654983708759149,
"mean_confidence": 0.7389143896102905,
"mean_target_max": 0.7714361180861791,
"score_mae": null,
"n": 600
}
}
},
"fitted_temperature": {
"type0_bucket1": 1.116391658782959,
"type2_bucket0": 1.1198104619979858,
"type1_bucket1": 1.0700936317443848
}
}