{
  "architecture": "EncoderForClassification",
  "model": {
    "vocab_size": 32768,
    "max_seq_len": 512,
    "d_model": 1024,
    "n_layers": 24,
    "n_heads": 16,
    "d_ff": 4096,
    "dropout": 0.1,
    "attention_dropout": 0.1,
    "layer_norm_eps": 1e-05,
    "pad_token_id": 0,
    "tie_mlm_head": true,
    "grad_checkpointing": false,
    "num_labels": 3
  },
  "num_labels": 3,
  "labels": {
    "0": "Legitimate",
    "1": "Phishing",
    "2": "Spam"
  },
  "binary_rollup": {
    "unwanted": [
      1,
      2
    ]
  },
  "unwanted_name": "Unwanted (phishing or spam)",
  "label_provenance": "Phishing = Nazario phishing corpus + Nigerian-fraud (advance-fee) corpus + synthetic BITS-style credential/BEC lures; Spam = SpamAssassin and Enron-Spam spam folders; the TREC-05 / TREC-07 / CEAS-08 positives never separated spam from phishing and were trained as 'unwanted' only (probability mass of phishing + spam), never as either class.",
  "max_seq_len": 512,
  "export_dtype": "bf16",
  "source_checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-focal/best",
  "exported": "2026-10-12T11:28:39",
  "tokenizer": "tokenizer.json",
  "model_input": "subject + \"\\n\\n\" + body",
  "finetune_checkpoint": {
    "tokenizer": "tokenizer.json",
    "finetune": {
      "run_name": "ft-focal",
      "init": "pretrained:checkpoints/pretrain/large-24L/final",
      "n_layers": 24,
      "freeze_layers": 0,
      "loss": "focal",
      "focal_gamma": 2.0,
      "lr": 3e-05,
      "batch_size": 32,
      "micro_batch": 16,
      "epochs": 2,
      "max_steps": null,
      "eval_every": 1250,
      "log_every": 20,
      "eval_batch_size": 64,
      "warmup_fraction": 0.06,
      "weight_decay": 0.01,
      "betas": [
        0.9,
        0.98
      ],
      "eps": 1e-06,
      "grad_clip": 1.0,
      "patience": 2,
      "schedule": "linear_decay",
      "selection_metric": "val_f1_unwanted",
      "pooling": "cls",
      "num_labels": 3,
      "synthetic": "off",
      "limit_rows": null,
      "seed": 42,
      "cpu": false
    },
    "best_epoch": 1,
    "best_step": 8750,
    "num_labels": 3,
    "label_names": [
      "Legitimate",
      "Phishing",
      "Spam"
    ],
    "binary_rollup_name": "Unwanted (phishing or spam)",
    "selection_metric": "val_f1_unwanted",
    "selection_value": 0.9951084002657166,
    "val_metrics": {
      "accuracy": 0.9947003402250719,
      "precision": 0.9954089646007007,
      "recall": 0.9948080173871046,
      "f1": 0.9951084002657166,
      "roc_auc": 0.9998186946414248,
      "pr_auc": 0.9998464119156345,
      "tn": 6964,
      "fp": 38,
      "fn": 43,
      "tp": 8239,
      "threshold": 0.5,
      "f1_optimal_threshold": 0.42074909806251526,
      "f1_at_optimal_threshold": 0.9952995058454863,
      "f1_unwanted": 0.9951084002657166,
      "n_3way": 8105,
      "accuracy_3way": 0.994694632942628,
      "macro_f1_3way": 0.9868751212108838,
      "precision_legitimate": 0.9988533753762362,
      "recall_legitimate": 0.99528706083976,
      "f1_legitimate": 0.9970670291151013,
      "precision_phishing": 0.9853372434017595,
      "recall_phishing": 0.9882352941176471,
      "f1_phishing": 0.986784140969163,
      "precision_spam": 0.9618805590851334,
      "recall_spam": 0.9921363040629095,
      "f1_spam": 0.9767741935483871,
      "cm3_ll": 6969,
      "cm3_lp": 4,
      "cm3_ls": 29,
      "cm3_pl": 3,
      "cm3_pp": 336,
      "cm3_ps": 1,
      "cm3_sl": 5,
      "cm3_sp": 1,
      "cm3_ss": 757,
      "n_unwanted_3way": 1103,
      "pvs_phish_as_phish": 339,
      "pvs_phish_as_spam": 1,
      "pvs_spam_as_phish": 1,
      "pvs_spam_as_spam": 762,
      "val_loss": 0.030296484990695233,
      "n": 15284,
      "eval_seconds": 48.0
    },
    "val_metric_sets": {
      "binary_unwanted": {
        "accuracy": 0.9947003402250719,
        "precision": 0.9954089646007007,
        "recall": 0.9948080173871046,
        "f1": 0.9951084002657166,
        "roc_auc": 0.9998186946414248,
        "pr_auc": 0.9998464119156345,
        "tn": 6964,
        "fp": 38,
        "fn": 43,
        "tp": 8239,
        "threshold": 0.5,
        "f1_optimal_threshold": 0.42074909806251526,
        "f1_at_optimal_threshold": 0.9952995058454863,
        "n": 15284,
        "positive_class": "Unwanted (phishing or spam)"
      },
      "three_way": {
        "n": 8105,
        "accuracy": 0.994694632942628,
        "macro_f1": 0.9868751212108838,
        "per_class": {
          "Legitimate": {
            "precision": 0.9988533753762362,
            "recall": 0.99528706083976,
            "f1": 0.9970670291151013
          },
          "Phishing": {
            "precision": 0.9853372434017595,
            "recall": 0.9882352941176471,
            "f1": 0.986784140969163
          },
          "Spam": {
            "precision": 0.9618805590851334,
            "recall": 0.9921363040629095,
            "f1": 0.9767741935483871
          }
        },
        "confusion": {
          "order": [
            "Legitimate",
            "Phishing",
            "Spam"
          ],
          "rows_true_cols_pred": [
            [
              6969,
              4,
              29
            ],
            [
              3,
              336,
              1
            ],
            [
              5,
              1,
              757
            ]
          ]
        },
        "phish_vs_spam_on_true_unwanted": {
          "n": 1103,
          "order": [
            "Phishing",
            "Spam"
          ],
          "rows_true_cols_pred": [
            [
              339,
              1
            ],
            [
              1,
              762
            ]
          ]
        }
      }
    },
    "thresholds": {
      "decision": 0.5,
      "decision_applies_to": "P(unwanted) = sum of non-legitimate probabilities",
      "val_f1_optimal": 0.42074909806251526,
      "val_f1_at_optimal": 0.9952995058454863
    },
    "init": "pretrained:/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final",
    "params": {
      "total": 337444867,
      "trainable": 337444867,
      "embeddings": 34080768,
      "encoder_layers": 302309376,
      "final_norm": 2048,
      "head": 1052675
    }
  },
  "finetune_init": "pretrained:/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final",
  "mlm_pretraining": "summary below",
  "metrics": {
    "split": "test",
    "split_file": "/home/nathank/BITS/dev/Phishing Model/data/processed/test_holdout.parquet",
    "n_rows": 16302,
    "dev_run": false,
    "threshold": 0.5,
    "timestamp": "2026-10-09 10:46",
    "num_labels": 3,
    "positive_class": "Unwanted (phishing or spam)",
    "accuracy": 0.9619065145380935,
    "precision": 0.8794342684906098,
    "recall": 0.9740626605033385,
    "f1": 0.9243328865602534,
    "specificity": 0.9580915538362347,
    "confusion_matrix": {
      "tn": 11888,
      "fp": 520,
      "fn": 101,
      "tp": 3793
    },
    "roc_auc": 0.9946343971962354,
    "pr_auc": 0.9847899987683836,
    "recall_at_fpr_1pct": 0.8954802259887006,
    "recall_at_fpr_0_1pct": 0.6497175141242938,
    "best_f1_threshold": 0.6815109252929688,
    "credential_lure_recall": 0.9958847736625515,
    "credential_lure_precision": 0.9758064516129032,
    "credential_lure_n": 398,
    "predicted_kind_of_flagged_true_positives": {
      "n": 3793,
      "predicted_phishing": 974,
      "predicted_spam": 2819
    },
    "latency_ms": {
      "gpu_bf16_avg": 10.08,
      "gpu_bf16_p50": 8.9,
      "cpu_fp32_avg": 458.57,
      "cpu_fp32_p50": 445.01,
      "cpu_threads": 16,
      "instructor_benchmark_ms": 74.0
    }
  },
  "metrics_source": "/home/nathank/BITS/dev/Phishing Model/reports/metrics.json",
  "metrics_checkpoint_matches": true,
  "metrics_mismatch": null,
  "metrics_threeway": {
    "split": "test3",
    "split_file": "/home/nathank/BITS/dev/Phishing Model/data/processed/test_holdout3.parquet",
    "n_rows": 3220,
    "dev_run": false,
    "threshold": 0.5,
    "timestamp": "2026-10-09 10:46",
    "rows_with_full_label": 3220,
    "label3_counts": {
      "legit": 1999,
      "phish": 521,
      "spam": 700,
      "unwanted": 0
    },
    "decision_rule": "rollup_then_argmax",
    "accuracy": 0.9885093167701864,
    "macro_f1": 0.9867305252015051,
    "per_class": {
      "Legitimate": {
        "precision": 0.9900299102691924,
        "recall": 0.9934967483741871,
        "f1": 0.9917602996254682,
        "support": 1999
      },
      "Phishing": {
        "precision": 0.9961240310077519,
        "recall": 0.9865642994241842,
        "f1": 0.991321118611379,
        "support": 521
      },
      "Spam": {
        "precision": 0.9785100286532952,
        "recall": 0.9757142857142858,
        "f1": 0.977110157367668,
        "support": 700
      }
    },
    "confusion_matrix": {
      "labels": [
        "Legitimate",
        "Phishing",
        "Spam"
      ],
      "matrix": [
        [
          1986,
          1,
          12
        ],
        [
          4,
          514,
          3
        ],
        [
          16,
          1,
          683
        ]
      ],
      "cells": {
        "true_legitimate": {
          "pred_legitimate": 1986,
          "pred_phishing": 1,
          "pred_spam": 12
        },
        "true_phishing": {
          "pred_legitimate": 4,
          "pred_phishing": 514,
          "pred_spam": 3
        },
        "true_spam": {
          "pred_legitimate": 16,
          "pred_phishing": 1,
          "pred_spam": 683
        }
      }
    },
    "kind_accuracy_on_true_unwanted": 0.9959049959049959,
    "phishing_as_spam": 4,
    "spam_as_phishing": 1,
    "n_true_unwanted": 1221,
    "per_source": {
      "Assassin": {
        "n": 236,
        "counts": {
          "Legitimate": 164,
          "Phishing": 0,
          "Spam": 72
        },
        "accuracy": 0.9533898305084746
      },
      "CEAS-08": {
        "n": 736,
        "counts": {
          "Legitimate": 736,
          "Phishing": 0,
          "Spam": 0
        },
        "accuracy": 0.9904891304347826
      },
      "Enron": {
        "n": 628,
        "counts": {
          "Legitimate": 0,
          "Phishing": 0,
          "Spam": 628
        },
        "accuracy": 0.9840764331210191
      },
      "Nazario": {
        "n": 222,
        "counts": {
          "Legitimate": 0,
          "Phishing": 222,
          "Spam": 0
        },
        "accuracy": 0.9864864864864865
      },
      "Nigerian_Fraud": {
        "n": 299,
        "counts": {
          "Legitimate": 0,
          "Phishing": 299,
          "Spam": 0
        },
        "accuracy": 0.9866220735785953
      },
      "TREC-07": {
        "n": 1099,
        "counts": {
          "Legitimate": 1099,
          "Phishing": 0,
          "Spam": 0
        },
        "accuracy": 0.9981801637852593
      }
    },
    "binary_rollup_on_this_split": {
      "recall": 0.9836199836199836,
      "precision": 0.9892915980230642,
      "f1": 0.986447638603696,
      "accuracy": 0.989751552795031
    }
  },
  "metrics_threeway_source": "/home/nathank/BITS/dev/Phishing Model/reports/metrics_test3.json",
  "metrics_threeway_reason": null,
  "metrics_threeway_checkpoint_matches": true,
  "metrics_threeway_mismatch": null,
  "training": {
    "run_name": "large-24L",
    "status": "complete",
    "source_checkpoint": "step-0009552",
    "steps": 9552,
    "total_steps_planned": 9552,
    "steps_per_epoch": 796,
    "epochs_planned": 12,
    "epochs_completed": 12.0,
    "tokens_seen": 1291124736,
    "total_training_seconds": 54185.9,
    "total_training_time": "15h 03m 05s",
    "final_loss": 1.523698394948786,
    "val_loss": 1.9862932266429436,
    "val_masked_acc": 0.6291136684837473,
    "peak_vram_reserved_gb": 17.939,
    "peak_vram_allocated_gb": 17.494,
    "micro_batch": 24,
    "grad_accumulation": 11,
    "effective_batch": 264,
    "precision": "bf16_autocast",
    "optimizer": "AdamW(fused) {\"lr\": 0.00015, \"betas\": [0.9, 0.98], \"eps\": 1e-06, \"weight_decay\": 0.01, \"grad_clip\": 1.0, \"mlm_probability\": 0.15, \"mask_replace_probs\": [0.8, 0.1, 0.1], \"schedule\": \"cosine_to_10pct\", \"effective_batch_sequences\": 256}",
    "schedule": {
      "kind": "cosine",
      "peak_lr": 0.00015,
      "warmup_steps": 573,
      "total_steps": 9552,
      "floor_ratio": 0.1
    },
    "mean_tokens_per_s": 23889,
    "data": {
      "n_windows": 210368,
      "n_val_windows": 1999,
      "tokenizer_sha1": "9f50c5e775089d2ca3efc82e100cd6b3396ed7e7",
      "n_docs": 226273,
      "limit_docs": null,
      "window": "[CLS] + 511 stream tokens"
    },
    "weights_dtype": "float32",
    "exported_at": "2026-10-09T03:31:14"
  },
  "training_source": "/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final/config.json",
  "from_scratch": true,
  "external_pretrained_weights_used": "none"
}