evaluation_results.json

{
  "model_info": {
    "base_model": "microsoft/deberta-v3-small",
    "model_type": "sequence-classification",
    "num_classes": 4,
    "class_names": [
      "NONE",
      "INTERNAL",
      "EXTERNAL",
      "BOTH"
    ]
  },
  "performance": {
    "accuracy": 0.7285643808584115,
    "f1_weighted": 0.7283043705111875,
    "f1_macro": 0.7275298614210632
  },
  "per_class_metrics": {
    "NONE": {
      "precision": 0.6973564266180492,
      "recall": 0.6132264529058116,
      "f1-score": 0.6525911708253359,
      "support": 2495.0
    },
    "INTERNAL": {
      "precision": 0.6770712909441233,
      "recall": 0.6833916763905096,
      "f1-score": 0.6802168021680217,
      "support": 2571.0
    },
    "EXTERNAL": {
      "precision": 0.8924773532886964,
      "recall": 0.882398753894081,
      "f1-score": 0.8874094380262385,
      "support": 2568.0
    },
    "BOTH": {
      "precision": 0.6522978268614179,
      "recall": 0.7321071571371451,
      "f1-score": 0.6899020346646572,
      "support": 2501.0
    }
  },
  "confusion_matrix": [
    [
      1530,
      388,
      160,
      417
    ],
    [
      323,
      1757,
      45,
      446
    ],
    [
      131,
      58,
      2266,
      113
    ],
    [
      210,
      392,
      68,
      1831
    ]
  ],
  "training_info": {
    "total_examples": 101348,
    "train_examples": 91213,
    "val_examples": 10135,
    "examples_per_class": 25337,
    "training_time_hours": 9.7,
    "final_epoch": 3.86
  }
}