gretel-pii-ready/evaluations/base_bert/eval_summary.json

{
  "model_name": "Base BERT",
  "dataset": "gretel-pii-ready",
  "seeds": [
    42,
    123,
    456,
    789,
    999
  ],
  "max_samples_per_seed": 1000,
  "avg_precision": 0.9133,
  "avg_recall": 0.9532,
  "avg_f1": 0.9314,
  "per_seed": {
    "42": {
      "precision": 0.9131,
      "recall": 0.9558,
      "f1": 0.9326
    },
    "123": {
      "precision": 0.9192,
      "recall": 0.9513,
      "f1": 0.9335
    },
    "456": {
      "precision": 0.9112,
      "recall": 0.9505,
      "f1": 0.9293
    },
    "789": {
      "precision": 0.9075,
      "recall": 0.9541,
      "f1": 0.9284
    },
    "999": {
      "precision": 0.9152,
      "recall": 0.9541,
      "f1": 0.9328
    }
  },
  "timestamp": "2026-04-08T04:03:29.970675"
}