| { |
| "timestamp": "2026-10-09 05:55", |
| "run_name": "ft-weighted", |
| "split": "test3", |
| "split_file": "/home/nathank/BITS/dev/Phishing Model/data/processed/test_holdout3.parquet", |
| "split_title": "three-way holdout", |
| "limit_rows": null, |
| "dev_run": false, |
| "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-weighted/best", |
| "splits_in_invocation": [ |
| "test", |
| "test3" |
| ], |
| "model_config": { |
| "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, |
| "params": 337444867, |
| "checkpoint_config": { |
| "tokenizer": "tokenizer.json", |
| "finetune": { |
| "run_name": "ft-weighted", |
| "init": "pretrained:checkpoints/pretrain/large-24L/final", |
| "n_layers": 24, |
| "freeze_layers": 0, |
| "loss": "weighted_cross_entropy", |
| "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": 10000, |
| "num_labels": 3, |
| "label_names": [ |
| "Legitimate", |
| "Phishing", |
| "Spam" |
| ], |
| "binary_rollup_name": "Unwanted (phishing or spam)", |
| "selection_metric": "val_f1_unwanted", |
| "selection_value": 0.99373795761079, |
| "val_metrics": { |
| "accuracy": 0.9931954985605862, |
| "precision": 0.9911121787172712, |
| "recall": 0.9963776865491427, |
| "f1": 0.99373795761079, |
| "roc_auc": 0.9997532357160727, |
| "pr_auc": 0.9997920087331971, |
| "tn": 6928, |
| "fp": 74, |
| "fn": 30, |
| "tp": 8252, |
| "threshold": 0.5, |
| "f1_optimal_threshold": 0.8991281390190125, |
| "f1_at_optimal_threshold": 0.9942622455758894, |
| "f1_unwanted": 0.99373795761079, |
| "n_3way": 8105, |
| "accuracy_3way": 0.9902529302899444, |
| "macro_f1_3way": 0.9774841428658321, |
| "precision_legitimate": 0.9992789154888952, |
| "recall_legitimate": 0.9895744073121965, |
| "f1_legitimate": 0.9944029850746269, |
| "precision_phishing": 0.9630681818181818, |
| "recall_phishing": 0.9970588235294118, |
| "f1_phishing": 0.9797687861271677, |
| "precision_spam": 0.9255189255189256, |
| "recall_spam": 0.9934469200524246, |
| "f1_spam": 0.9582806573957017, |
| "cm3_ll": 6929, |
| "cm3_lp": 12, |
| "cm3_ls": 61, |
| "cm3_pl": 1, |
| "cm3_pp": 339, |
| "cm3_ps": 0, |
| "cm3_sl": 4, |
| "cm3_sp": 1, |
| "cm3_ss": 758, |
| "n_unwanted_3way": 1103, |
| "pvs_phish_as_phish": 339, |
| "pvs_phish_as_spam": 1, |
| "pvs_spam_as_phish": 2, |
| "pvs_spam_as_spam": 761, |
| "val_loss": 0.025379083498832725, |
| "n": 15284, |
| "eval_seconds": 47.8 |
| }, |
| "val_metric_sets": { |
| "binary_unwanted": { |
| "accuracy": 0.9931954985605862, |
| "precision": 0.9911121787172712, |
| "recall": 0.9963776865491427, |
| "f1": 0.99373795761079, |
| "roc_auc": 0.9997532357160727, |
| "pr_auc": 0.9997920087331971, |
| "tn": 6928, |
| "fp": 74, |
| "fn": 30, |
| "tp": 8252, |
| "threshold": 0.5, |
| "f1_optimal_threshold": 0.8991281390190125, |
| "f1_at_optimal_threshold": 0.9942622455758894, |
| "n": 15284, |
| "positive_class": "Unwanted (phishing or spam)" |
| }, |
| "three_way": { |
| "n": 8105, |
| "accuracy": 0.9902529302899444, |
| "macro_f1": 0.9774841428658321, |
| "per_class": { |
| "Legitimate": { |
| "precision": 0.9992789154888952, |
| "recall": 0.9895744073121965, |
| "f1": 0.9944029850746269 |
| }, |
| "Phishing": { |
| "precision": 0.9630681818181818, |
| "recall": 0.9970588235294118, |
| "f1": 0.9797687861271677 |
| }, |
| "Spam": { |
| "precision": 0.9255189255189256, |
| "recall": 0.9934469200524246, |
| "f1": 0.9582806573957017 |
| } |
| }, |
| "confusion": { |
| "order": [ |
| "Legitimate", |
| "Phishing", |
| "Spam" |
| ], |
| "rows_true_cols_pred": [ |
| [ |
| 6929, |
| 12, |
| 61 |
| ], |
| [ |
| 1, |
| 339, |
| 0 |
| ], |
| [ |
| 4, |
| 1, |
| 758 |
| ] |
| ] |
| }, |
| "phish_vs_spam_on_true_unwanted": { |
| "n": 1103, |
| "order": [ |
| "Phishing", |
| "Spam" |
| ], |
| "rows_true_cols_pred": [ |
| [ |
| 339, |
| 1 |
| ], |
| [ |
| 2, |
| 761 |
| ] |
| ] |
| } |
| } |
| }, |
| "thresholds": { |
| "decision": 0.5, |
| "decision_applies_to": "P(unwanted) = sum of non-legitimate probabilities", |
| "val_f1_optimal": 0.8991281390190125, |
| "val_f1_at_optimal": 0.9942622455758894 |
| }, |
| "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 |
| } |
| }, |
| "tokenizer": "/home/nathank/BITS/dev/Phishing Model/data/processed/tokenizer.json", |
| "max_len": 512, |
| "label_names": { |
| "0": "Legitimate", |
| "1": "Phishing", |
| "2": "Spam" |
| }, |
| "binary_rollup": { |
| "unwanted_name": "Unwanted (phishing or spam)", |
| "classes": [ |
| 1, |
| 2 |
| ], |
| "rule": "P(unwanted) = sum of P(class) for class >= 1; flag when >= threshold" |
| }, |
| "split_sizes": { |
| "rows": 3220, |
| "positive": 1221, |
| "negative": 1999, |
| "positive_rate": 0.3792, |
| "label3": { |
| "legit": 1999, |
| "phish": 521, |
| "spam": 700, |
| "unwanted": 0 |
| }, |
| "by_source": { |
| "Assassin": { |
| "rows": 236, |
| "positive": 72, |
| "label3": { |
| "legit": 164, |
| "phish": 0, |
| "spam": 72, |
| "unwanted": 0 |
| } |
| }, |
| "CEAS-08": { |
| "rows": 736, |
| "positive": 0, |
| "label3": { |
| "legit": 736, |
| "phish": 0, |
| "spam": 0, |
| "unwanted": 0 |
| } |
| }, |
| "Enron": { |
| "rows": 628, |
| "positive": 628, |
| "label3": { |
| "legit": 0, |
| "phish": 0, |
| "spam": 628, |
| "unwanted": 0 |
| } |
| }, |
| "Nazario": { |
| "rows": 222, |
| "positive": 222, |
| "label3": { |
| "legit": 0, |
| "phish": 222, |
| "spam": 0, |
| "unwanted": 0 |
| } |
| }, |
| "Nigerian_Fraud": { |
| "rows": 299, |
| "positive": 299, |
| "label3": { |
| "legit": 0, |
| "phish": 299, |
| "spam": 0, |
| "unwanted": 0 |
| } |
| }, |
| "TREC-07": { |
| "rows": 1099, |
| "positive": 0, |
| "label3": { |
| "legit": 1099, |
| "phish": 0, |
| "spam": 0, |
| "unwanted": 0 |
| } |
| } |
| }, |
| "mean_tokens_full": 835.2, |
| "pct_truncated": 34.01 |
| }, |
| "threshold": 0.5, |
| "at_threshold": { |
| "threshold": 0.5, |
| "accuracy": 0.9894409937888199, |
| "precision": 0.9790153349475383, |
| "recall": 0.9934479934479934, |
| "f1": 0.9861788617886179, |
| "specificity": 0.9869934967483742, |
| "false_positive_rate": 0.013006503251625813, |
| "false_negative_rate": 0.006552006552006552, |
| "confusion_matrix": { |
| "tn": 1973, |
| "fp": 26, |
| "fn": 8, |
| "tp": 1213 |
| }, |
| "n": 3220, |
| "n_positive": 1221, |
| "n_negative": 1999 |
| }, |
| "threshold_free": { |
| "roc_auc": 0.999348773485842, |
| "pr_auc": 0.9988435835907616, |
| "recall_at_fpr_1pct": { |
| "fpr_budget": 0.01, |
| "recall": 0.990990990990991, |
| "fpr": 0.009504752376188095, |
| "threshold": 0.7280054092407227, |
| "threshold_rule": "flag when p >= threshold" |
| }, |
| "recall_at_fpr_0_1pct": { |
| "fpr_budget": 0.001, |
| "recall": 0.7059787059787059, |
| "fpr": 0.0005002501250625312, |
| "threshold": 0.9999038577079773, |
| "threshold_rule": "flag when p >= threshold" |
| }, |
| "best_f1": { |
| "threshold": 0.7280054092407227, |
| "f1": 0.9877551020408163, |
| "precision": 0.9845402766476811, |
| "recall": 0.990990990990991 |
| } |
| }, |
| "threeway": { |
| "num_labels": 3, |
| "label_names": { |
| "0": "Legitimate", |
| "1": "Phishing", |
| "2": "Spam" |
| }, |
| "unwanted_name": "Unwanted (phishing or spam)", |
| "decision_rule": "rollup_then_argmax", |
| "decision_rule_doc": "unwanted iff P(phishing)+P(spam) >= threshold, then kind = argmax(P(phishing), P(spam)); the 3x3 matrix therefore collapses exactly onto the binary confusion matrix. argmax-of-3 reported alongside.", |
| "threshold": 0.5, |
| "label3_counts": { |
| "legit": 1999, |
| "phish": 521, |
| "spam": 700, |
| "unwanted": 0 |
| }, |
| "predicted_kind_breakdown": { |
| "note": "How the model's flagged rows split into predicted phishing vs spam (kind = argmax(P(phishing), P(spam))). Informational: for rows labelled -1/unwanted (all TREC-06 positives) there is NO phishing-vs-spam ground truth.", |
| "true_positives_flagged": { |
| "n": 1213, |
| "predicted_phishing": 515, |
| "predicted_spam": 698 |
| }, |
| "false_positives_flagged": { |
| "n": 26, |
| "predicted_phishing": 5, |
| "predicted_spam": 21 |
| }, |
| "missed_positives": { |
| "n": 8, |
| "predicted_phishing": 1, |
| "predicted_spam": 7 |
| }, |
| "all_flagged": { |
| "n": 1239, |
| "predicted_phishing": 520, |
| "predicted_spam": 719 |
| }, |
| "unsplit_unwanted_rows_flagged": { |
| "n": 0, |
| "predicted_phishing": 0, |
| "predicted_spam": 0 |
| } |
| }, |
| "rows_with_full_label": 3220, |
| "rows_unwanted_only": 0, |
| "evaluated": true, |
| "reason": null, |
| "confusion_matrix": { |
| "labels": [ |
| "Legitimate", |
| "Phishing", |
| "Spam" |
| ], |
| "matrix": [ |
| [ |
| 1973, |
| 5, |
| 21 |
| ], |
| [ |
| 2, |
| 514, |
| 5 |
| ], |
| [ |
| 6, |
| 1, |
| 693 |
| ] |
| ], |
| "cells": { |
| "true_legitimate": { |
| "pred_legitimate": 1973, |
| "pred_phishing": 5, |
| "pred_spam": 21 |
| }, |
| "true_phishing": { |
| "pred_legitimate": 2, |
| "pred_phishing": 514, |
| "pred_spam": 5 |
| }, |
| "true_spam": { |
| "pred_legitimate": 6, |
| "pred_phishing": 1, |
| "pred_spam": 693 |
| } |
| } |
| }, |
| "accuracy": 0.9875776397515528, |
| "macro_f1": 0.985237826721197, |
| "macro_f1_present_classes": 0.985237826721197, |
| "classes_present": [ |
| "Legitimate", |
| "Phishing", |
| "Spam" |
| ], |
| "per_class": { |
| "Legitimate": { |
| "precision": 0.9959616355376073, |
| "recall": 0.9869934967483742, |
| "f1": 0.9914572864321608, |
| "support": 1999 |
| }, |
| "Phishing": { |
| "precision": 0.9884615384615385, |
| "recall": 0.9865642994241842, |
| "f1": 0.9875120076849183, |
| "support": 521 |
| }, |
| "Spam": { |
| "precision": 0.9638386648122392, |
| "recall": 0.99, |
| "f1": 0.9767441860465116, |
| "support": 700 |
| } |
| }, |
| "argmax_rule": { |
| "doc": "plain argmax over the three probabilities (secondary; can disagree with the binary verdict near the threshold)", |
| "accuracy": 0.987888198757764, |
| "macro_f1": 0.9855518791290724, |
| "per_class": { |
| "Legitimate": { |
| "precision": 0.9959636730575177, |
| "recall": 0.9874937468734367, |
| "f1": 0.9917106254709872, |
| "support": 1999 |
| }, |
| "Phishing": { |
| "precision": 0.9884615384615385, |
| "recall": 0.9865642994241842, |
| "f1": 0.9875120076849183, |
| "support": 521 |
| }, |
| "Spam": { |
| "precision": 0.9651810584958217, |
| "recall": 0.99, |
| "f1": 0.9774330042313117, |
| "support": 700 |
| } |
| }, |
| "rows_where_rules_differ": 1 |
| }, |
| "phish_vs_spam_on_true_unwanted": { |
| "n_true_unwanted": 1221, |
| "kind_only": { |
| "doc": "given the row is unwanted, is argmax(P(phishing), P(spam)) right? (independent of the roll-up threshold)", |
| "labels": [ |
| "Phishing", |
| "Spam" |
| ], |
| "matrix": [ |
| [ |
| 515, |
| 6 |
| ], |
| [ |
| 1, |
| 699 |
| ] |
| ], |
| "cells": { |
| "true_phishing": { |
| "pred_phishing": 515, |
| "pred_spam": 6 |
| }, |
| "true_spam": { |
| "pred_phishing": 1, |
| "pred_spam": 699 |
| } |
| }, |
| "accuracy": 0.9942669942669943, |
| "phishing_as_spam": 6, |
| "spam_as_phishing": 1 |
| }, |
| "rollup_rule": { |
| "doc": "rows = true Phishing / Spam; columns = predicted Legitimate (missed) / Phishing / Spam under the roll-up rule", |
| "rows": [ |
| "Phishing", |
| "Spam" |
| ], |
| "columns": [ |
| "Legitimate", |
| "Phishing", |
| "Spam" |
| ], |
| "matrix": [ |
| [ |
| 2, |
| 514, |
| 5 |
| ], |
| [ |
| 6, |
| 1, |
| 693 |
| ] |
| ], |
| "missed_as_legitimate": { |
| "phishing": 2, |
| "spam": 6 |
| } |
| } |
| }, |
| "per_source": { |
| "Assassin": { |
| "n": 236, |
| "counts": { |
| "Legitimate": 164, |
| "Phishing": 0, |
| "Spam": 72 |
| }, |
| "accuracy": 0.961864406779661, |
| "macro_f1": 0.6401713738091211, |
| "macro_f1_present_classes": 0.9602570607136818, |
| "per_class_recall": { |
| "Legitimate": 0.9634146341463414, |
| "Spam": 0.9583333333333334 |
| } |
| }, |
| "CEAS-08": { |
| "n": 736, |
| "counts": { |
| "Legitimate": 736, |
| "Phishing": 0, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9823369565217391, |
| "macro_f1": 0.3303632625085675, |
| "macro_f1_present_classes": 0.9910897875257025, |
| "per_class_recall": { |
| "Legitimate": 0.9823369565217391 |
| } |
| }, |
| "Enron": { |
| "n": 628, |
| "counts": { |
| "Legitimate": 0, |
| "Phishing": 0, |
| "Spam": 628 |
| }, |
| "accuracy": 0.9936305732484076, |
| "macro_f1": 0.33226837060702874, |
| "macro_f1_present_classes": 0.9968051118210862, |
| "per_class_recall": { |
| "Spam": 0.9936305732484076 |
| } |
| }, |
| "Nazario": { |
| "n": 222, |
| "counts": { |
| "Legitimate": 0, |
| "Phishing": 222, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9819819819819819, |
| "macro_f1": 0.3303030303030303, |
| "macro_f1_present_classes": 0.990909090909091, |
| "per_class_recall": { |
| "Phishing": 0.9819819819819819 |
| } |
| }, |
| "Nigerian_Fraud": { |
| "n": 299, |
| "counts": { |
| "Legitimate": 0, |
| "Phishing": 299, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9899665551839465, |
| "macro_f1": 0.33165266106442576, |
| "macro_f1_present_classes": 0.9949579831932773, |
| "per_class_recall": { |
| "Phishing": 0.9899665551839465 |
| } |
| }, |
| "TREC-07": { |
| "n": 1099, |
| "counts": { |
| "Legitimate": 1099, |
| "Phishing": 0, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9936305732484076, |
| "macro_f1": 0.33226837060702874, |
| "macro_f1_present_classes": 0.9968051118210862, |
| "per_class_recall": { |
| "Legitimate": 0.9936305732484076 |
| } |
| } |
| } |
| }, |
| "credential_lure_slice": { |
| "n_phrases": 37, |
| "phrases": [ |
| "verify your account", |
| "verify your identity", |
| "confirm your identity", |
| "confirm your account", |
| "enter your password", |
| "update your account", |
| "update your information", |
| "update your billing", |
| "update your payment", |
| "click here to verify", |
| "click the link below to verify", |
| "account has been suspended", |
| "account has been limited", |
| "account will be suspended", |
| "account has been locked", |
| "unusual sign-in", |
| "unusual activity", |
| "suspicious activity", |
| "paypal account", |
| "ebay account", |
| "password expire", |
| "password will expire", |
| "reset your password", |
| "invoice attached", |
| "wire transfer", |
| "gift card", |
| "urgent", |
| "urgently", |
| "security alert", |
| "security notice", |
| "login to your account", |
| "log in to your account", |
| "sign in to your account", |
| "bank account", |
| "failure to verify", |
| "within 24 hours", |
| "within 48 hours" |
| ], |
| "match_rule": "whole-word match on NFKC-lowercased text with non-alphanumerics collapsed to spaces", |
| "phrase_hits": { |
| "urgent": 139, |
| "bank account": 91, |
| "urgently": 25, |
| "verify your account": 15, |
| "confirm your account": 9, |
| "update your account": 9, |
| "within 24 hours": 8, |
| "security alert": 8, |
| "paypal account": 7, |
| "password will expire": 7, |
| "click here to verify": 6, |
| "unusual activity": 4, |
| "wire transfer": 3, |
| "update your information": 3, |
| "gift card": 3, |
| "verify your identity": 2, |
| "unusual sign-in": 2, |
| "account will be suspended": 2, |
| "update your payment": 2, |
| "failure to verify": 2, |
| "within 48 hours": 2, |
| "confirm your identity": 2, |
| "enter your password": 1, |
| "update your billing": 1, |
| "reset your password": 1, |
| "suspicious activity": 1, |
| "security notice": 1, |
| "log in to your account": 1 |
| }, |
| "phrase_hits_by_label": { |
| "verify your account": { |
| "positive": 15, |
| "negative": 0 |
| }, |
| "verify your identity": { |
| "positive": 2, |
| "negative": 0 |
| }, |
| "confirm your identity": { |
| "positive": 2, |
| "negative": 0 |
| }, |
| "confirm your account": { |
| "positive": 9, |
| "negative": 0 |
| }, |
| "enter your password": { |
| "positive": 0, |
| "negative": 1 |
| }, |
| "update your account": { |
| "positive": 9, |
| "negative": 0 |
| }, |
| "update your information": { |
| "positive": 2, |
| "negative": 1 |
| }, |
| "update your billing": { |
| "positive": 1, |
| "negative": 0 |
| }, |
| "update your payment": { |
| "positive": 2, |
| "negative": 0 |
| }, |
| "click here to verify": { |
| "positive": 6, |
| "negative": 0 |
| }, |
| "account will be suspended": { |
| "positive": 2, |
| "negative": 0 |
| }, |
| "unusual sign-in": { |
| "positive": 2, |
| "negative": 0 |
| }, |
| "unusual activity": { |
| "positive": 4, |
| "negative": 0 |
| }, |
| "suspicious activity": { |
| "positive": 1, |
| "negative": 0 |
| }, |
| "paypal account": { |
| "positive": 7, |
| "negative": 0 |
| }, |
| "password will expire": { |
| "positive": 7, |
| "negative": 0 |
| }, |
| "reset your password": { |
| "positive": 1, |
| "negative": 0 |
| }, |
| "wire transfer": { |
| "positive": 2, |
| "negative": 1 |
| }, |
| "gift card": { |
| "positive": 3, |
| "negative": 0 |
| }, |
| "urgent": { |
| "positive": 133, |
| "negative": 6 |
| }, |
| "urgently": { |
| "positive": 25, |
| "negative": 0 |
| }, |
| "security alert": { |
| "positive": 8, |
| "negative": 0 |
| }, |
| "security notice": { |
| "positive": 1, |
| "negative": 0 |
| }, |
| "log in to your account": { |
| "positive": 1, |
| "negative": 0 |
| }, |
| "bank account": { |
| "positive": 91, |
| "negative": 0 |
| }, |
| "failure to verify": { |
| "positive": 2, |
| "negative": 0 |
| }, |
| "within 24 hours": { |
| "positive": 8, |
| "negative": 0 |
| }, |
| "within 48 hours": { |
| "positive": 2, |
| "negative": 0 |
| } |
| }, |
| "label_purity": 0.9745, |
| "min_positives_for_comparison": 20, |
| "label3_counts": { |
| "legit": 7, |
| "phish": 236, |
| "spam": 32, |
| "unwanted": 0 |
| }, |
| "threeway_accuracy": 0.9927272727272727, |
| "metrics": { |
| "threshold": 0.5, |
| "accuracy": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "f1": 1.0, |
| "specificity": 1.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.0, |
| "confusion_matrix": { |
| "tn": 7, |
| "fp": 0, |
| "fn": 0, |
| "tp": 268 |
| }, |
| "n": 275, |
| "n_positive": 268, |
| "n_negative": 7, |
| "roc_auc": 1.0 |
| } |
| }, |
| "per_source": { |
| "Assassin": { |
| "threshold": 0.5, |
| "accuracy": 0.9661016949152542, |
| "precision": 0.9210526315789473, |
| "recall": 0.9722222222222222, |
| "f1": 0.9459459459459458, |
| "specificity": 0.9634146341463414, |
| "false_positive_rate": 0.036585365853658534, |
| "false_negative_rate": 0.027777777777777776, |
| "confusion_matrix": { |
| "tn": 158, |
| "fp": 6, |
| "fn": 2, |
| "tp": 70 |
| }, |
| "n": 236, |
| "n_positive": 72, |
| "n_negative": 164, |
| "roc_auc": 0.9953421409214093, |
| "label3_counts": { |
| "legit": 164, |
| "phish": 0, |
| "spam": 72, |
| "unwanted": 0 |
| } |
| }, |
| "CEAS-08": { |
| "threshold": 0.5, |
| "accuracy": 0.9823369565217391, |
| "precision": 0.0, |
| "recall": 0.0, |
| "f1": 0.0, |
| "specificity": 0.9823369565217391, |
| "false_positive_rate": 0.017663043478260868, |
| "false_negative_rate": 0.0, |
| "confusion_matrix": { |
| "tn": 723, |
| "fp": 13, |
| "fn": 0, |
| "tp": 0 |
| }, |
| "n": 736, |
| "n_positive": 0, |
| "n_negative": 736, |
| "roc_auc": null, |
| "label3_counts": { |
| "legit": 736, |
| "phish": 0, |
| "spam": 0, |
| "unwanted": 0 |
| } |
| }, |
| "Enron": { |
| "threshold": 0.5, |
| "accuracy": 0.9936305732484076, |
| "precision": 1.0, |
| "recall": 0.9936305732484076, |
| "f1": 0.9968051118210862, |
| "specificity": 0.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.006369426751592357, |
| "confusion_matrix": { |
| "tn": 0, |
| "fp": 0, |
| "fn": 4, |
| "tp": 624 |
| }, |
| "n": 628, |
| "n_positive": 628, |
| "n_negative": 0, |
| "roc_auc": null, |
| "label3_counts": { |
| "legit": 0, |
| "phish": 0, |
| "spam": 628, |
| "unwanted": 0 |
| } |
| }, |
| "Nazario": { |
| "threshold": 0.5, |
| "accuracy": 0.990990990990991, |
| "precision": 1.0, |
| "recall": 0.990990990990991, |
| "f1": 0.9954751131221719, |
| "specificity": 0.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.009009009009009009, |
| "confusion_matrix": { |
| "tn": 0, |
| "fp": 0, |
| "fn": 2, |
| "tp": 220 |
| }, |
| "n": 222, |
| "n_positive": 222, |
| "n_negative": 0, |
| "roc_auc": null, |
| "label3_counts": { |
| "legit": 0, |
| "phish": 222, |
| "spam": 0, |
| "unwanted": 0 |
| } |
| }, |
| "Nigerian_Fraud": { |
| "threshold": 0.5, |
| "accuracy": 1.0, |
| "precision": 1.0, |
| "recall": 1.0, |
| "f1": 1.0, |
| "specificity": 0.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.0, |
| "confusion_matrix": { |
| "tn": 0, |
| "fp": 0, |
| "fn": 0, |
| "tp": 299 |
| }, |
| "n": 299, |
| "n_positive": 299, |
| "n_negative": 0, |
| "roc_auc": null, |
| "label3_counts": { |
| "legit": 0, |
| "phish": 299, |
| "spam": 0, |
| "unwanted": 0 |
| } |
| }, |
| "TREC-07": { |
| "threshold": 0.5, |
| "accuracy": 0.9936305732484076, |
| "precision": 0.0, |
| "recall": 0.0, |
| "f1": 0.0, |
| "specificity": 0.9936305732484076, |
| "false_positive_rate": 0.006369426751592357, |
| "false_negative_rate": 0.0, |
| "confusion_matrix": { |
| "tn": 1092, |
| "fp": 7, |
| "fn": 0, |
| "tp": 0 |
| }, |
| "n": 1099, |
| "n_positive": 0, |
| "n_negative": 1099, |
| "roc_auc": null, |
| "label3_counts": { |
| "legit": 1099, |
| "phish": 0, |
| "spam": 0, |
| "unwanted": 0 |
| } |
| } |
| }, |
| "length_confound": { |
| "by_outcome": { |
| "tp": { |
| "n": 1213, |
| "mean_tokens_full": 994.5, |
| "mean_tokens_fed": 279.6, |
| "median_tokens_full": 241.0, |
| "pct_truncated": 26.6 |
| }, |
| "tn": { |
| "n": 1973, |
| "mean_tokens_full": 729.2, |
| "mean_tokens_fed": 358.6, |
| "median_tokens_full": 393.0, |
| "pct_truncated": 38.3 |
| }, |
| "fp": { |
| "n": 26, |
| "mean_tokens_full": 1537.1, |
| "mean_tokens_fed": 356.2, |
| "median_tokens_full": 706.0, |
| "pct_truncated": 53.8 |
| }, |
| "fn": { |
| "n": 8, |
| "mean_tokens_full": 550.4, |
| "mean_tokens_fed": 326.4, |
| "median_tokens_full": 334.5, |
| "pct_truncated": 37.5 |
| }, |
| "correct": { |
| "n": 3186, |
| "mean_tokens_full": 830.2, |
| "mean_tokens_fed": 328.5, |
| "median_tokens_full": 338.0, |
| "pct_truncated": 33.8 |
| }, |
| "wrong": { |
| "n": 34, |
| "mean_tokens_full": 1304.9, |
| "mean_tokens_fed": 349.1, |
| "median_tokens_full": 485.5, |
| "pct_truncated": 50.0 |
| } |
| }, |
| "by_label": { |
| "legitimate": { |
| "n": 1999, |
| "mean_tokens_full": 739.7, |
| "mean_tokens_fed": 358.6, |
| "median_tokens_full": 393.0, |
| "pct_truncated": 38.5 |
| }, |
| "unwanted": { |
| "n": 1221, |
| "mean_tokens_full": 991.6, |
| "mean_tokens_fed": 279.9, |
| "median_tokens_full": 243.0, |
| "pct_truncated": 26.7 |
| } |
| }, |
| "by_class3": { |
| "legit": { |
| "n": 1999, |
| "mean_tokens_full": 739.7, |
| "mean_tokens_fed": 358.6, |
| "median_tokens_full": 393.0, |
| "pct_truncated": 38.5 |
| }, |
| "phish": { |
| "n": 521, |
| "mean_tokens_full": 1349.4, |
| "mean_tokens_fed": 355.1, |
| "median_tokens_full": 412.0, |
| "pct_truncated": 39.9 |
| }, |
| "spam": { |
| "n": 700, |
| "mean_tokens_full": 725.3, |
| "mean_tokens_fed": 223.9, |
| "median_tokens_full": 159.0, |
| "pct_truncated": 16.9 |
| } |
| }, |
| "by_length_bucket": [ |
| { |
| "bucket": "<=64", |
| "n": 129, |
| "n_positive": 99, |
| "positive_rate": 0.7674418604651163, |
| "recall": 0.98989898989899, |
| "fpr": 0.1, |
| "accuracy": 0.9689922480620154 |
| }, |
| { |
| "bucket": "65-128", |
| "n": 427, |
| "n_positive": 252, |
| "positive_rate": 0.5901639344262295, |
| "recall": 0.996031746031746, |
| "fpr": 0.011428571428571429, |
| "accuracy": 0.9929742388758782 |
| }, |
| { |
| "bucket": "129-256", |
| "n": 699, |
| "n_positive": 276, |
| "positive_rate": 0.3948497854077253, |
| "recall": 1.0, |
| "fpr": 0.0070921985815602835, |
| "accuracy": 0.9957081545064378 |
| }, |
| { |
| "bucket": "257-512", |
| "n": 870, |
| "n_positive": 268, |
| "positive_rate": 0.3080459770114943, |
| "recall": 0.9888059701492538, |
| "fpr": 0.006644518272425249, |
| "accuracy": 0.9919540229885058 |
| }, |
| { |
| "bucket": ">512", |
| "n": 1095, |
| "n_positive": 326, |
| "positive_rate": 0.29771689497716897, |
| "recall": 0.99079754601227, |
| "fpr": 0.018205461638491547, |
| "accuracy": 0.9844748858447488 |
| } |
| ] |
| }, |
| "inference": { |
| "device": "cuda", |
| "autocast_bf16": true, |
| "batch_size": 64, |
| "pad_to_multiple_of": 8, |
| "num_labels": 3, |
| "rows": 3220, |
| "seconds": 13.51, |
| "rows_per_s": 238.3, |
| "padded_tokens": 1079936, |
| "real_tokens": 1058490, |
| "padded_tokens_per_s": 79930, |
| "peak_vram_gb": 2.27 |
| }, |
| "latency": { |
| "instructor_benchmark_ms": 74.0, |
| "samples_requested": 100, |
| "sample_split": "test", |
| "max_len": 512, |
| "gpu_bf16": { |
| "n": 100, |
| "avg_ms": 10.12, |
| "p50_ms": 8.95, |
| "p95_ms": 13.37, |
| "max_ms": 19.01, |
| "avg_s": 0.0101, |
| "mean_tokens": 280.0, |
| "ratio_to_benchmark": 0.137, |
| "device": "NVIDIA GeForce RTX 3090 Ti" |
| }, |
| "cpu_fp32": { |
| "n": 100, |
| "avg_ms": 411.57, |
| "p50_ms": 397.57, |
| "p95_ms": 630.3, |
| "max_ms": 674.98, |
| "avg_s": 0.4116, |
| "mean_tokens": 280.0, |
| "ratio_to_benchmark": 5.562, |
| "threads": 16, |
| "estimated_full_run_s": 38.4 |
| }, |
| "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-weighted/best", |
| "run_name": "ft-weighted", |
| "params": 337444867, |
| "timestamp": "2026-10-09 05:55", |
| "num_labels": 3, |
| "measured_once_for_splits": [ |
| "test", |
| "test3" |
| ] |
| }, |
| "error_analysis": { |
| "path": "reports/eval_ft-weighted/error_analysis_test3.md", |
| "n_fn": 8, |
| "n_fp": 26, |
| "composition": { |
| "fp": { |
| "n": 26, |
| "mailing_list_or_digest": 0.577, |
| "html_heavy": 0.0, |
| "very_short_lt20_tokens": 0.0, |
| "truncated_gt512": 0.538, |
| "lure_phrase": 0.0 |
| }, |
| "tn": { |
| "n": 1973, |
| "mailing_list_or_digest": 0.563, |
| "html_heavy": 0.0, |
| "very_short_lt20_tokens": 0.0, |
| "truncated_gt512": 0.383, |
| "lure_phrase": 0.004 |
| }, |
| "fn": { |
| "n": 8, |
| "mailing_list_or_digest": 0.25, |
| "html_heavy": 0.0, |
| "very_short_lt20_tokens": 0.0, |
| "truncated_gt512": 0.375, |
| "lure_phrase": 0.0 |
| }, |
| "tp": { |
| "n": 1213, |
| "mailing_list_or_digest": 0.086, |
| "html_heavy": 0.0, |
| "very_short_lt20_tokens": 0.007, |
| "truncated_gt512": 0.266, |
| "lure_phrase": 0.221 |
| } |
| }, |
| "fn_vs_tp_tokens": [ |
| { |
| "token": "invite", |
| "share_a": 0.5, |
| "share_b": 0.002, |
| "ratio": 183.55 |
| }, |
| { |
| "token": "networking", |
| "share_a": 0.375, |
| "share_b": 0.003, |
| "ratio": 111.04 |
| }, |
| { |
| "token": "event", |
| "share_a": 0.5, |
| "share_b": 0.005, |
| "ratio": 98.84 |
| }, |
| { |
| "token": "angeles", |
| "share_a": 0.375, |
| "share_b": 0.004, |
| "ratio": 90.85 |
| }, |
| { |
| "token": "york", |
| "share_a": 0.375, |
| "share_b": 0.005, |
| "ratio": 76.87 |
| }, |
| { |
| "token": "technologies", |
| "share_a": 0.375, |
| "share_b": 0.006, |
| "ratio": 66.62 |
| }, |
| { |
| "token": "entertainment", |
| "share_a": 0.375, |
| "share_b": 0.007, |
| "ratio": 58.79 |
| }, |
| { |
| "token": "association", |
| "share_a": 0.375, |
| "share_b": 0.008, |
| "ratio": 47.59 |
| }, |
| { |
| "token": "hosting", |
| "share_a": 0.375, |
| "share_b": 0.009, |
| "ratio": 43.45 |
| }, |
| { |
| "token": "staff", |
| "share_a": 0.375, |
| "share_b": 0.012, |
| "ratio": 34.46 |
| }, |
| { |
| "token": "changes", |
| "share_a": 0.375, |
| "share_b": 0.012, |
| "ratio": 32.24 |
| }, |
| { |
| "token": "media", |
| "share_a": 0.375, |
| "share_b": 0.015, |
| "ratio": 27.01 |
| }, |
| { |
| "token": "cards", |
| "share_a": 0.375, |
| "share_b": 0.015, |
| "ratio": 27.01 |
| }, |
| { |
| "token": "leading", |
| "share_a": 0.375, |
| "share_b": 0.015, |
| "ratio": 27.01 |
| }, |
| { |
| "token": "los", |
| "share_a": 0.375, |
| "share_b": 0.016, |
| "ratio": 25.62 |
| }, |
| { |
| "token": "anyone", |
| "share_a": 0.375, |
| "share_b": 0.017, |
| "ratio": 23.24 |
| }, |
| { |
| "token": "simply", |
| "share_a": 0.5, |
| "share_b": 0.025, |
| "ratio": 21.06 |
| }, |
| { |
| "token": "browser", |
| "share_a": 0.5, |
| "share_b": 0.026, |
| "ratio": 19.77 |
| }, |
| { |
| "token": "friends", |
| "share_a": 0.375, |
| "share_b": 0.021, |
| "ratio": 18.86 |
| }, |
| { |
| "token": "paste", |
| "share_a": 0.375, |
| "share_b": 0.021, |
| "ratio": 18.86 |
| } |
| ], |
| "fp_vs_tn_tokens": [ |
| { |
| "token": "zzz-unspun", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 223.42 |
| }, |
| { |
| "token": "czzz-unspun", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 223.42 |
| }, |
| { |
| "token": "outlets", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 223.42 |
| }, |
| { |
| "token": "cowpokeproductions", |
| "share_a": 0.115, |
| "share_b": 0.001, |
| "ratio": 173.77 |
| }, |
| { |
| "token": "trinity", |
| "share_a": 0.115, |
| "share_b": 0.001, |
| "ratio": 173.77 |
| }, |
| { |
| "token": "cowpoke", |
| "share_a": 0.115, |
| "share_b": 0.001, |
| "ratio": 173.77 |
| }, |
| { |
| "token": "enron", |
| "share_a": 0.115, |
| "share_b": 0.001, |
| "ratio": 173.77 |
| }, |
| { |
| "token": "full-color", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 138.3 |
| }, |
| { |
| "token": "vineyard", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "patel", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "loripatel", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "englishmajor", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "comtm", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "asbrand", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "spins", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "unspun", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "savviest", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "mediaunspun", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "four-week", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| }, |
| { |
| "token": "authoritatively", |
| "share_a": 0.154, |
| "share_b": 0.001, |
| "ratio": 134.05 |
| } |
| ], |
| "top_fn_doc_ids": [ |
| "primary:148887", |
| "primary:191966", |
| "aura:Nazario:000643", |
| "primary:007176", |
| "aura:Nazario:000097", |
| "primary:001939", |
| "primary:046569", |
| "primary:014300" |
| ], |
| "top_fp_doc_ids": [ |
| "primary:091801", |
| "primary:144048", |
| "primary:199386", |
| "primary:103927", |
| "primary:055965", |
| "primary:165228", |
| "primary:152763", |
| "primary:048756", |
| "primary:168120", |
| "primary:041713", |
| "primary:069336", |
| "primary:057514", |
| "primary:146259", |
| "primary:156887", |
| "primary:116110", |
| "primary:132924", |
| "primary:156985", |
| "primary:115649", |
| "primary:153841", |
| "primary:117398", |
| "primary:021911", |
| "primary:003448", |
| "primary:025142", |
| "primary:113001", |
| "primary:027029" |
| ], |
| "threeway": { |
| "n_phish_as_spam": 5, |
| "n_spam_as_phish": 1, |
| "top_phish_as_spam_doc_ids": [ |
| "aura:Nigerian_Fraud:001698", |
| "aura:Nigerian_Fraud:000337", |
| "aura:Nigerian_Fraud:003049", |
| "aura:Nazario:001179", |
| "aura:Nazario:000532" |
| ], |
| "top_spam_as_phish_doc_ids": [ |
| "primary:129677" |
| ], |
| "phish_as_spam_tokens": [ |
| { |
| "token": "friends", |
| "share_a": 0.6, |
| "share_b": 0.016, |
| "ratio": 38.52 |
| }, |
| { |
| "token": "join", |
| "share_a": 0.6, |
| "share_b": 0.021, |
| "ratio": 28.47 |
| }, |
| { |
| "token": "complete", |
| "share_a": 0.6, |
| "share_b": 0.049, |
| "ratio": 12.84 |
| }, |
| { |
| "token": "don't", |
| "share_a": 0.8, |
| "share_b": 0.068, |
| "ratio": 11.86 |
| }, |
| { |
| "token": "visit", |
| "share_a": 0.6, |
| "share_b": 0.058, |
| "ratio": 10.73 |
| }, |
| { |
| "token": "every", |
| "share_a": 0.6, |
| "share_b": 0.068, |
| "ratio": 9.22 |
| }, |
| { |
| "token": "link", |
| "share_a": 0.6, |
| "share_b": 0.074, |
| "ratio": 8.5 |
| }, |
| { |
| "token": "read", |
| "share_a": 0.6, |
| "share_b": 0.084, |
| "ratio": 7.53 |
| }, |
| { |
| "token": "life", |
| "share_a": 0.6, |
| "share_b": 0.099, |
| "ratio": 6.36 |
| }, |
| { |
| "token": "www", |
| "share_a": 0.8, |
| "share_b": 0.148, |
| "ratio": 5.5 |
| }, |
| { |
| "token": "http", |
| "share_a": 0.8, |
| "share_b": 0.193, |
| "ratio": 4.23 |
| }, |
| { |
| "token": "new", |
| "share_a": 0.6, |
| "share_b": 0.161, |
| "ratio": 3.92 |
| }, |
| { |
| "token": "make", |
| "share_a": 0.6, |
| "share_b": 0.161, |
| "ratio": 3.92 |
| }, |
| { |
| "token": "get", |
| "share_a": 0.6, |
| "share_b": 0.202, |
| "ratio": 3.13 |
| }, |
| { |
| "token": "com", |
| "share_a": 1.0, |
| "share_b": 0.337, |
| "ratio": 2.97 |
| }, |
| { |
| "token": "message", |
| "share_a": 0.6, |
| "share_b": 0.214, |
| "ratio": 2.96 |
| }, |
| { |
| "token": "e-mail", |
| "share_a": 0.6, |
| "share_b": 0.218, |
| "ratio": 2.91 |
| }, |
| { |
| "token": "receive", |
| "share_a": 0.6, |
| "share_b": 0.218, |
| "ratio": 2.91 |
| }, |
| { |
| "token": "only", |
| "share_a": 0.6, |
| "share_b": 0.235, |
| "ratio": 2.69 |
| }, |
| { |
| "token": "about", |
| "share_a": 0.6, |
| "share_b": 0.239, |
| "ratio": 2.65 |
| } |
| ], |
| "spam_as_phish_tokens": [] |
| } |
| }, |
| "plots": { |
| "confusion_matrix": "reports/eval_ft-weighted/confusion_matrix_test3.png", |
| "confusion_matrix3": "reports/eval_ft-weighted/confusion_matrix3_test3.png", |
| "roc_curve": "reports/eval_ft-weighted/roc_curve_test3.png", |
| "pr_curve": "reports/eval_ft-weighted/pr_curve_test3.png" |
| } |
| } |
|
|
