final_test_results.json

{
  "test_set_metrics": {
    "0": {
      "confidence": 0.8835059073236253,
      "accuracy": 1.0,
      "correct": 9,
      "total": 9
    },
    "1": {
      "confidence": 0.9493008057276408,
      "accuracy": 1.0,
      "correct": 9,
      "total": 9
    },
    "2": {
      "confidence": 0.8486442342400551,
      "accuracy": 0.8888888888888888,
      "correct": 8,
      "total": 9
    },
    "3": {
      "confidence": 0.9468189279238383,
      "accuracy": 1.0,
      "correct": 9,
      "total": 9
    },
    "4": {
      "confidence": 0.870511029447828,
      "accuracy": 0.7777777777777778,
      "correct": 7,
      "total": 9
    }
  },
  "overall_metrics": {
    "avg_confidence": 0.8997561809325975,
    "avg_accuracy": 0.9333333333333333,
    "total_iterations": 4,
    "target_achieved": false
  }
}