SafeAge-XLM-R-Base / evaluation /test_metrics.json
mehedi4's picture
Release original SafeAge-trained xlmr baseline checkpoint
3fb84d7 verified
Raw History Blame Contribute Delete
1.45 kB
{
"default_0_5": {
"rows": 1204,
"benign_rows": 756,
"attack_rows": 448,
"threshold": 0.5,
"accuracy": 0.9127906976744186,
"balanced_accuracy": 0.9000909391534392,
"macro_f1": 0.9053775802797357,
"attack_precision": 0.9093078758949881,
"attack_recall": 0.8504464285714286,
"attack_f1": 0.8788927335640139,
"benign_specificity": 0.9497354497354498,
"benign_false_positive_rate": 0.05026455026455026,
"attack_false_negative_rate": 0.14955357142857142,
"roc_auc": 0.970037320483749,
"average_precision": 0.9595743795979578,
"brier_score": 0.08266975804310862,
"log_loss": 0.5941776420834323,
"tn": 718,
"fp": 38,
"fn": 67,
"tp": 381
},
"validation_selected": {
"rows": 1204,
"benign_rows": 756,
"attack_rows": 448,
"threshold": 0.99,
"accuracy": 0.9102990033222591,
"balanced_accuracy": 0.8917410714285714,
"macro_f1": 0.9013842247522319,
"attack_precision": 0.9314720812182741,
"attack_recall": 0.8191964285714286,
"attack_f1": 0.8717339667458432,
"benign_specificity": 0.9642857142857143,
"benign_false_positive_rate": 0.03571428571428571,
"attack_false_negative_rate": 0.18080357142857142,
"roc_auc": 0.970037320483749,
"average_precision": 0.9595743795979578,
"brier_score": 0.08266975804310862,
"log_loss": 0.5941776420834323,
"tn": 729,
"fp": 27,
"fn": 81,
"tp": 367
}
}