{ "agreement_threshold": 0.15, "best_eval_loss": 21.752999266554905, "eval_history_length": 4, "eval_metrics": { "avg_margin_violation": null, "contradiction_rate": null, "coverage_f1": 0.09190465965213657, "coverage_precision": 0.7157190635451505, "coverage_recall": 0.04910509407985315, "coverage_source": "logits", "coverage_support": 117723.0, "eval_loss": 70.75614915129924, "nli_pair_count": 0, "redundancy_index": 0.00012577735405615995, "redundancy_pair_count": 85866 }, "generated_at": "2025-12-07T15:14:33.566756+00:00", "global_step": 50000, "stage": 3, "train_history_length": 1100, "train_metrics": { "coverage_f1": { "count": 1000, "last": 0.0, "max": 0.5, "mean": 0.0034451770451770455, "min": 0.0 }, "coverage_precision": { "count": 1000, "last": 0.0, "max": 1.0, "mean": 0.0029482174688057043, "min": 0.0 }, "coverage_recall": { "count": 1000, "last": 0.0, "max": 1.0, "mean": 0.010866666666666667, "min": 0.0 }, "kd_ce_ratio": { "count": 1100, "last": 6.771889053472952e-07, "max": 1.993265237894144e-06, "mean": 2.7301640674022355e-07, "min": -2.044742390260858e-06 }, "loss": { "count": 1100, "last": 432.0, "max": 604.0336303710938, "mean": 405.4652520197088, "min": 216.2018280029297 }, "repair_error_rate": { "count": 3, "last": 0.0, "max": 0.0, "mean": 0.0, "min": 0.0 }, "repair_margin": { "count": 3, "last": 224.0, "max": 294.0, "mean": 261.3333333333333, "min": 224.0 }, "rollback_kl": { "count": 3, "last": 0.0, "max": 0.0, "mean": 0.0, "min": 0.0 }, "stability_error_rate": { "count": 3, "last": 0.0, "max": 0.0, "mean": 0.0, "min": 0.0 }, "stability_kl": { "count": 3, "last": 0.0, "max": 2.837623469531536e-09, "mean": -1.8531864043325186e-07, "min": -5.587935447692871e-07 }, "stability_margin": { "count": 3, "last": 235.0, "max": 258.0, "mean": 246.33333333333334, "min": 235.0 }, "stage": { "last": 3.0 }, "usage_loss": { "count": 1100, "last": 0.0, "max": 0.0, "mean": 0.0, "min": 0.0 } } }