artifacts/reports/data_validation.json

{
  "clauses_ru": 477,
  "clauses_kz": 477,
  "train_pairs": 3786,
  "test_pairs": 699,
  "leakage_ids_count": 0,
  "missing_train_positive_ids_count": 0,
  "missing_test_positive_ids_count": 0,
  "leakage_sample": [],
  "missing_train_sample": [],
  "missing_test_sample": []
}