minhleduc's picture
E2 run e2_rlce_sigma4_fixed_seed42 (epoch_4.pt)
72054f8 verified
Raw History Blame Contribute Delete
2.99 kB
{
"raw": {
"ece": 0.06247570636123419,
"brier": 0.07159885753310358,
"nll": 0.9871578481241773,
"accuracy": 0.774,
"soft_accuracy": 0.5550091580034933,
"mean_confidence": 0.7148323274552822,
"mean_target_max": 0.6589462240487337,
"score_mae": 0.24743149618079768,
"n": 2000,
"by_type": {
"choice": {
"ece": 0.08004063126941523,
"brier": 0.08437397119729698,
"nll": 1.1341199049664572,
"accuracy": 0.7616666666666667,
"soft_accuracy": 0.5161412421241403,
"mean_confidence": 0.6961774043738842,
"mean_target_max": 0.6345381752649943,
"score_mae": null,
"n": 600
},
"score": {
"ece": 0.06396819561719894,
"brier": 0.07845711318950861,
"nll": 1.1806772747822105,
"accuracy": 0.72,
"soft_accuracy": 0.4767965656411252,
"mean_confidence": 0.6601681255921722,
"mean_target_max": 0.5928848401084542,
"score_mae": 0.24743149618079768,
"n": 800
},
"noul": {
"ece": 0.0534882617990176,
"brier": 0.049679402993703485,
"nll": 0.5821698890711863,
"accuracy": 0.8583333333333333,
"soft_accuracy": 0.6981605303660036,
"mean_confidence": 0.806372853020827,
"mean_target_max": 0.7714361180861791,
"score_mae": null,
"n": 600
}
}
},
"post_temperature": {
"ece": 0.17336726085841658,
"brier": 0.05161821419496153,
"nll": 0.8642696282893885,
"accuracy": 0.774,
"soft_accuracy": 0.5073439120836556,
"mean_confidence": 0.6006327216774225,
"mean_target_max": 0.6589462240487337,
"score_mae": 0.21800018620619085,
"n": 2000,
"by_type": {
"choice": {
"ece": 0.19164921840031937,
"brier": 0.06163718613093541,
"nll": 0.9900163768736335,
"accuracy": 0.7616666666666667,
"soft_accuracy": 0.4636078991989295,
"mean_confidence": 0.5700174510975679,
"mean_target_max": 0.6345381752649943,
"score_mae": null,
"n": 600
},
"score": {
"ece": 0.182909285761416,
"brier": 0.053707796073395,
"nll": 1.0393080767360516,
"accuracy": 0.72,
"soft_accuracy": 0.42770247970707714,
"mean_confidence": 0.5374936549365521,
"mean_target_max": 0.5928848401084542,
"score_mae": 0.21800018620619085,
"n": 800
},
"noul": {
"ece": 0.14289991398652396,
"brier": 0.03881313308774302,
"nll": 0.5051382817762593,
"accuracy": 0.8583333333333333,
"soft_accuracy": 0.6572685014704863,
"mean_confidence": 0.7154334145784378,
"mean_target_max": 0.7714361180861791,
"score_mae": null,
"n": 600
}
}
},
"fitted_temperature": {
"type0_bucket1": 1.9356564283370972,
"type2_bucket0": 2.420105218887329,
"type1_bucket1": 1.9092248678207397
}
}