test_metrics.json

{
  "test_loss": 0.01223407406359911,
  "test_precision": 0.9551368142202801,
  "test_recall": 0.9799216081310224,
  "test_f1": 0.9630685025439435,
  "test_LANG_precision": 0.9819929629539341,
  "test_LANG_recall": 1.0,
  "test_LANG_f1": 0.9908397325566001,
  "test_SKILL_precision": 0.9889449241719945,
  "test_SKILL_recall": 0.9904749295912962,
  "test_SKILL_f1": 0.9897093160099927,
  "test_CERT_precision": 0.8260869565217391,
  "test_CERT_recall": 0.9166666666666667,
  "test_CERT_f1": 0.8492822966507176,
  "test_SOFT_SKILL_precision": 0.9810121524462506,
  "test_SOFT_SKILL_recall": 0.9926311347792305,
  "test_SOFT_SKILL_f1": 0.9867712480908251,
  "test_EXPERIENCE_DURATION_precision": 0.9976470750074813,
  "test_EXPERIENCE_DURATION_recall": 0.9998353096179183,
  "test_EXPERIENCE_DURATION_f1": 0.9987399194115818,
  "test_runtime": 91.6905,
  "test_samples_per_second": 43.603,
  "test_steps_per_second": 5.453
}