[
  {
    "model": "beethogedeon/UltraFinBERT-150M",
    "accuracy": 0.9646017699115044,
    "balanced_accuracy": 0.9542543773362188,
    "macro_f1": 0.9615904929520475,
    "weighted_f1": 0.9641735110013125,
    "macro_precision": 0.9702531262693043,
    "macro_recall": 0.9542543773362188,
    "log_loss": 0.24856460459181326,
    "macro_f1_ci95_low": 0.9373423664558937,
    "macro_f1_ci95_high": 0.9814966497430953,
    "test_examples": 339,
    "truncation_rate": 0.0,
    "parameters": 151034883,
    "evaluation_dtype": "torch.float16",
    "revision": "local FP16 export",
    "training_overlap_note": "Held out from this fine-tuning run; upstream pretraining exposure not audited."
  },
  {
    "model": "ProsusAI/finbert",
    "accuracy": 0.9823008849557522,
    "balanced_accuracy": 0.9847408026755854,
    "macro_f1": 0.9775293265383634,
    "weighted_f1": 0.9823943729157764,
    "macro_precision": 0.9708343294286398,
    "macro_recall": 0.9847408026755854,
    "log_loss": 0.11372488239044834,
    "macro_f1_ci95_low": 0.9590552079097949,
    "macro_f1_ci95_high": 0.9945137250496199,
    "test_examples": 339,
    "truncation_rate": 0.0,
    "parameters": 109484547,
    "evaluation_dtype": "torch.float16",
    "revision": "0bc2ac10dda6929bcb1f77ccc43c7ec5c424f031",
    "training_overlap_note": "Previously fine-tuned on FinancialPhraseBank; overlap with this test is unknown and possible."
  },
  {
    "model": "beethogedeon/Modern-FinBERT-large",
    "accuracy": 0.9823008849557522,
    "balanced_accuracy": 0.9764705882352942,
    "macro_f1": 0.9748919274144381,
    "weighted_f1": 0.9821485315052908,
    "macro_precision": 0.9748525002418029,
    "macro_recall": 0.9764705882352942,
    "log_loss": 0.09822984893543157,
    "macro_f1_ci95_low": 0.9525722119021349,
    "macro_f1_ci95_high": 0.9916481561294743,
    "test_examples": 339,
    "truncation_rate": 0.0,
    "parameters": 395834371,
    "evaluation_dtype": "torch.float16",
    "revision": "a5dd04dae984a46e729698ca39f398181c9aaeea",
    "training_overlap_note": "Previously fine-tuned on FinancialPhraseBank; overlap with this test is unknown and possible."
  }
]