Bauxi-23M / eval /evaluation.json
classifyre's picture
Bauxi 1.0.0: weights, graphs, evaluation
0746964 verified
Raw History Blame Contribute Delete
3.07 kB
{
"sealed_at": "2026-10-30T18:43:05+00:00",
"dev": {
"count": 660,
"accuracy": 0.9651515151515152,
"macro_f1": 0.9637706189656473,
"invalid_recall": 0.9181818181818182,
"false_safe": 15,
"false_safe_rate": 0.06818181818181818,
"per_class": {
"valid": {
"precision": 0.9285714285714286,
"recall": 0.975,
"f1": 0.951219512195122
},
"invalid": {
"precision": 0.9805825242718447,
"recall": 0.9181818181818182,
"f1": 0.9483568075117371
},
"unknown": {
"precision": 0.9836065573770492,
"recall": 1.0,
"f1": 0.9917355371900827
}
},
"confusion": {
"valid": {
"valid": 195,
"invalid": 4,
"unknown": 1
},
"invalid": {
"valid": 15,
"invalid": 202,
"unknown": 3
},
"unknown": {
"valid": 0,
"invalid": 0,
"unknown": 240
}
},
"nll": 0.1344972848892212,
"brier_score": 0.058700360175617486
},
"regression": {
"count": 888,
"accuracy": 0.9707207207207207,
"macro_f1": 0.9712798584457879,
"invalid_recall": 0.9222972972972973,
"false_safe": 5,
"false_safe_rate": 0.016891891891891893,
"per_class": {
"valid": {
"precision": 0.973384030418251,
"recall": 1.0,
"f1": 0.9865125240847785
},
"invalid": {
"precision": 0.9963503649635036,
"recall": 0.9222972972972973,
"f1": 0.9578947368421052
},
"unknown": {
"precision": 0.9487179487179487,
"recall": 0.9910714285714286,
"f1": 0.9694323144104804
}
},
"confusion": {
"valid": {
"valid": 256,
"invalid": 0,
"unknown": 0
},
"invalid": {
"valid": 5,
"invalid": 273,
"unknown": 18
},
"unknown": {
"valid": 2,
"invalid": 1,
"unknown": 333
}
},
"nll": 0.10553333908319473,
"brier_score": 0.04750689810961712
},
"holdout": {
"count": 150,
"accuracy": 0.9066666666666666,
"macro_f1": 0.906498599439776,
"invalid_recall": 0.9,
"false_safe": 5,
"false_safe_rate": 0.1,
"per_class": {
"valid": {
"precision": 0.875,
"recall": 0.84,
"f1": 0.8571428571428572
},
"invalid": {
"precision": 0.8653846153846154,
"recall": 0.9,
"f1": 0.8823529411764707
},
"unknown": {
"precision": 0.98,
"recall": 0.98,
"f1": 0.98
}
},
"confusion": {
"valid": {
"valid": 42,
"invalid": 7,
"unknown": 1
},
"invalid": {
"valid": 5,
"invalid": 45,
"unknown": 0
},
"unknown": {
"valid": 1,
"invalid": 0,
"unknown": 49
}
},
"nll": 0.34009185433387756,
"brier_score": 0.16805987150673973,
"accuracy_95_interval": [
0.8533333333333334,
0.9533333333333334
]
}
}