| { |
| "timestamp": "2026-10-09 08:54", |
| "run_name": "ft-12L", |
| "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-12L/best", |
| "splits_in_invocation": [ |
| "test", |
| "test3" |
| ], |
| "model_config": { |
| "vocab_size": 32768, |
| "max_seq_len": 512, |
| "d_model": 1024, |
| "n_layers": 12, |
| "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": 186290179, |
| "checkpoint_config": { |
| "tokenizer": "tokenizer.json", |
| "finetune": { |
| "run_name": "ft-12L", |
| "init": "pretrained:checkpoints/pretrain/large-24L/final", |
| "n_layers": 12, |
| "freeze_layers": 0, |
| "loss": "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": 6250, |
| "num_labels": 3, |
| "label_names": [ |
| "Legitimate", |
| "Phishing", |
| "Spam" |
| ], |
| "binary_rollup_name": "Unwanted (phishing or spam)", |
| "selection_metric": "val_f1_unwanted", |
| "selection_value": 0.9925057415689592, |
| "val_metrics": { |
| "accuracy": 0.9918869405914682, |
| "precision": 0.9935866408518877, |
| "recall": 0.9914271914996378, |
| "f1": 0.9925057415689592, |
| "roc_auc": 0.9995007118744352, |
| "pr_auc": 0.9995737781814353, |
| "tn": 6949, |
| "fp": 53, |
| "fn": 71, |
| "tp": 8211, |
| "threshold": 0.5, |
| "f1_optimal_threshold": 0.17105858027935028, |
| "f1_at_optimal_threshold": 0.9928829915560917, |
| "f1_unwanted": 0.9925057415689592, |
| "n_3way": 8105, |
| "accuracy_3way": 0.9916101172115978, |
| "macro_f1_3way": 0.9774079655816474, |
| "precision_legitimate": 0.9984195402298851, |
| "recall_legitimate": 0.9924307340759783, |
| "f1_legitimate": 0.9954161294943418, |
| "precision_phishing": 0.9570200573065902, |
| "recall_phishing": 0.9823529411764705, |
| "f1_phishing": 0.969521044992743, |
| "precision_spam": 0.9472361809045227, |
| "recall_spam": 0.9882044560943644, |
| "f1_spam": 0.9672867222578576, |
| "cm3_ll": 6949, |
| "cm3_lp": 13, |
| "cm3_ls": 40, |
| "cm3_pl": 4, |
| "cm3_pp": 334, |
| "cm3_ps": 2, |
| "cm3_sl": 7, |
| "cm3_sp": 2, |
| "cm3_ss": 754, |
| "n_unwanted_3way": 1103, |
| "pvs_phish_as_phish": 338, |
| "pvs_phish_as_spam": 2, |
| "pvs_spam_as_phish": 2, |
| "pvs_spam_as_spam": 761, |
| "val_loss": 0.035248381216093624, |
| "n": 15284, |
| "eval_seconds": 22.8 |
| }, |
| "val_metric_sets": { |
| "binary_unwanted": { |
| "accuracy": 0.9918869405914682, |
| "precision": 0.9935866408518877, |
| "recall": 0.9914271914996378, |
| "f1": 0.9925057415689592, |
| "roc_auc": 0.9995007118744352, |
| "pr_auc": 0.9995737781814353, |
| "tn": 6949, |
| "fp": 53, |
| "fn": 71, |
| "tp": 8211, |
| "threshold": 0.5, |
| "f1_optimal_threshold": 0.17105858027935028, |
| "f1_at_optimal_threshold": 0.9928829915560917, |
| "n": 15284, |
| "positive_class": "Unwanted (phishing or spam)" |
| }, |
| "three_way": { |
| "n": 8105, |
| "accuracy": 0.9916101172115978, |
| "macro_f1": 0.9774079655816474, |
| "per_class": { |
| "Legitimate": { |
| "precision": 0.9984195402298851, |
| "recall": 0.9924307340759783, |
| "f1": 0.9954161294943418 |
| }, |
| "Phishing": { |
| "precision": 0.9570200573065902, |
| "recall": 0.9823529411764705, |
| "f1": 0.969521044992743 |
| }, |
| "Spam": { |
| "precision": 0.9472361809045227, |
| "recall": 0.9882044560943644, |
| "f1": 0.9672867222578576 |
| } |
| }, |
| "confusion": { |
| "order": [ |
| "Legitimate", |
| "Phishing", |
| "Spam" |
| ], |
| "rows_true_cols_pred": [ |
| [ |
| 6949, |
| 13, |
| 40 |
| ], |
| [ |
| 4, |
| 334, |
| 2 |
| ], |
| [ |
| 7, |
| 2, |
| 754 |
| ] |
| ] |
| }, |
| "phish_vs_spam_on_true_unwanted": { |
| "n": 1103, |
| "order": [ |
| "Phishing", |
| "Spam" |
| ], |
| "rows_true_cols_pred": [ |
| [ |
| 338, |
| 2 |
| ], |
| [ |
| 2, |
| 761 |
| ] |
| ] |
| } |
| } |
| }, |
| "thresholds": { |
| "decision": 0.5, |
| "decision_applies_to": "P(unwanted) = sum of non-legitimate probabilities", |
| "val_f1_optimal": 0.17105858027935028, |
| "val_f1_at_optimal": 0.9928829915560917 |
| }, |
| "init": "pretrained:/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final", |
| "params": { |
| "total": 186290179, |
| "trainable": 186290179, |
| "embeddings": 34080768, |
| "encoder_layers": 151154688, |
| "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": 0.9866459627329193, |
| "precision": 0.985973597359736, |
| "recall": 0.9787059787059788, |
| "f1": 0.9823263460748048, |
| "specificity": 0.991495747873937, |
| "false_positive_rate": 0.008504252126063032, |
| "false_negative_rate": 0.021294021294021293, |
| "confusion_matrix": { |
| "tn": 1982, |
| "fp": 17, |
| "fn": 26, |
| "tp": 1195 |
| }, |
| "n": 3220, |
| "n_positive": 1221, |
| "n_negative": 1999 |
| }, |
| "threshold_free": { |
| "roc_auc": 0.9990709933181169, |
| "pr_auc": 0.9983252258043704, |
| "recall_at_fpr_1pct": { |
| "fpr_budget": 0.01, |
| "recall": 0.9795249795249795, |
| "fpr": 0.009504752376188095, |
| "threshold": 0.4533155560493469, |
| "threshold_rule": "flag when p >= threshold" |
| }, |
| "recall_at_fpr_0_1pct": { |
| "fpr_budget": 0.001, |
| "recall": 0.7747747747747747, |
| "fpr": 0.0005002501250625312, |
| "threshold": 0.9997867345809937, |
| "threshold_rule": "flag when p >= threshold" |
| }, |
| "best_f1": { |
| "threshold": 0.16916866600513458, |
| "f1": 0.9848670756646216, |
| "precision": 0.9836601307189542, |
| "recall": 0.9860769860769861 |
| } |
| }, |
| "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": 1195, |
| "predicted_phishing": 508, |
| "predicted_spam": 687 |
| }, |
| "false_positives_flagged": { |
| "n": 17, |
| "predicted_phishing": 5, |
| "predicted_spam": 12 |
| }, |
| "missed_positives": { |
| "n": 26, |
| "predicted_phishing": 4, |
| "predicted_spam": 22 |
| }, |
| "all_flagged": { |
| "n": 1212, |
| "predicted_phishing": 513, |
| "predicted_spam": 699 |
| }, |
| "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": [ |
| [ |
| 1982, |
| 5, |
| 12 |
| ], |
| [ |
| 7, |
| 507, |
| 7 |
| ], |
| [ |
| 19, |
| 1, |
| 680 |
| ] |
| ], |
| "cells": { |
| "true_legitimate": { |
| "pred_legitimate": 1982, |
| "pred_phishing": 5, |
| "pred_spam": 12 |
| }, |
| "true_phishing": { |
| "pred_legitimate": 7, |
| "pred_phishing": 507, |
| "pred_spam": 7 |
| }, |
| "true_spam": { |
| "pred_legitimate": 19, |
| "pred_phishing": 1, |
| "pred_spam": 680 |
| } |
| } |
| }, |
| "accuracy": 0.9841614906832298, |
| "macro_f1": 0.9806831216094775, |
| "macro_f1_present_classes": 0.9806831216094775, |
| "classes_present": [ |
| "Legitimate", |
| "Phishing", |
| "Spam" |
| ], |
| "per_class": { |
| "Legitimate": { |
| "precision": 0.9870517928286853, |
| "recall": 0.991495747873937, |
| "f1": 0.9892687796356376, |
| "support": 1999 |
| }, |
| "Phishing": { |
| "precision": 0.9883040935672515, |
| "recall": 0.9731285988483686, |
| "f1": 0.9806576402321083, |
| "support": 521 |
| }, |
| "Spam": { |
| "precision": 0.9728183118741058, |
| "recall": 0.9714285714285714, |
| "f1": 0.9721229449606862, |
| "support": 700 |
| } |
| }, |
| "argmax_rule": { |
| "doc": "plain argmax over the three probabilities (secondary; can disagree with the binary verdict near the threshold)", |
| "accuracy": 0.9841614906832298, |
| "macro_f1": 0.9806831216094775, |
| "per_class": { |
| "Legitimate": { |
| "precision": 0.9870517928286853, |
| "recall": 0.991495747873937, |
| "f1": 0.9892687796356376, |
| "support": 1999 |
| }, |
| "Phishing": { |
| "precision": 0.9883040935672515, |
| "recall": 0.9731285988483686, |
| "f1": 0.9806576402321083, |
| "support": 521 |
| }, |
| "Spam": { |
| "precision": 0.9728183118741058, |
| "recall": 0.9714285714285714, |
| "f1": 0.9721229449606862, |
| "support": 700 |
| } |
| }, |
| "rows_where_rules_differ": 0 |
| }, |
| "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": [ |
| [ |
| 511, |
| 10 |
| ], |
| [ |
| 1, |
| 699 |
| ] |
| ], |
| "cells": { |
| "true_phishing": { |
| "pred_phishing": 511, |
| "pred_spam": 10 |
| }, |
| "true_spam": { |
| "pred_phishing": 1, |
| "pred_spam": 699 |
| } |
| }, |
| "accuracy": 0.990990990990991, |
| "phishing_as_spam": 10, |
| "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": [ |
| [ |
| 7, |
| 507, |
| 7 |
| ], |
| [ |
| 19, |
| 1, |
| 680 |
| ] |
| ], |
| "missed_as_legitimate": { |
| "phishing": 7, |
| "spam": 19 |
| } |
| } |
| }, |
| "per_source": { |
| "Assassin": { |
| "n": 236, |
| "counts": { |
| "Legitimate": 164, |
| "Phishing": 0, |
| "Spam": 72 |
| }, |
| "accuracy": 0.961864406779661, |
| "macro_f1": 0.6370518043396608, |
| "macro_f1_present_classes": 0.9555777065094913, |
| "per_class_recall": { |
| "Legitimate": 0.9878048780487805, |
| "Spam": 0.9027777777777778 |
| } |
| }, |
| "CEAS-08": { |
| "n": 736, |
| "counts": { |
| "Legitimate": 736, |
| "Phishing": 0, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9864130434782609, |
| "macro_f1": 0.33105335157318744, |
| "macro_f1_present_classes": 0.9931600547195623, |
| "per_class_recall": { |
| "Legitimate": 0.9864130434782609 |
| } |
| }, |
| "Enron": { |
| "n": 628, |
| "counts": { |
| "Legitimate": 0, |
| "Phishing": 0, |
| "Spam": 628 |
| }, |
| "accuracy": 0.9792993630573248, |
| "macro_f1": 0.32984714400643605, |
| "macro_f1_present_classes": 0.9895414320193081, |
| "per_class_recall": { |
| "Spam": 0.9792993630573248 |
| } |
| }, |
| "Nazario": { |
| "n": 222, |
| "counts": { |
| "Legitimate": 0, |
| "Phishing": 222, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9684684684684685, |
| "macro_f1": 0.32799389778794813, |
| "macro_f1_present_classes": 0.9839816933638444, |
| "per_class_recall": { |
| "Phishing": 0.9684684684684685 |
| } |
| }, |
| "Nigerian_Fraud": { |
| "n": 299, |
| "counts": { |
| "Legitimate": 0, |
| "Phishing": 299, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9765886287625418, |
| "macro_f1": 0.329385222786238, |
| "macro_f1_present_classes": 0.988155668358714, |
| "per_class_recall": { |
| "Phishing": 0.9765886287625418 |
| } |
| }, |
| "TREC-07": { |
| "n": 1099, |
| "counts": { |
| "Legitimate": 1099, |
| "Phishing": 0, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9954504094631483, |
| "macro_f1": 0.3325733394132847, |
| "macro_f1_present_classes": 0.9977200182398541, |
| "per_class_recall": { |
| "Legitimate": 0.9954504094631483 |
| } |
| } |
| } |
| }, |
| "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": 0.9781818181818182, |
| "metrics": { |
| "threshold": 0.5, |
| "accuracy": 0.9890909090909091, |
| "precision": 1.0, |
| "recall": 0.9888059701492538, |
| "f1": 0.9943714821763603, |
| "specificity": 1.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.011194029850746268, |
| "confusion_matrix": { |
| "tn": 7, |
| "fp": 0, |
| "fn": 3, |
| "tp": 265 |
| }, |
| "n": 275, |
| "n_positive": 268, |
| "n_negative": 7, |
| "roc_auc": 1.0 |
| } |
| }, |
| "per_source": { |
| "Assassin": { |
| "threshold": 0.5, |
| "accuracy": 0.9661016949152542, |
| "precision": 0.9705882352941176, |
| "recall": 0.9166666666666666, |
| "f1": 0.9428571428571428, |
| "specificity": 0.9878048780487805, |
| "false_positive_rate": 0.012195121951219513, |
| "false_negative_rate": 0.08333333333333333, |
| "confusion_matrix": { |
| "tn": 162, |
| "fp": 2, |
| "fn": 6, |
| "tp": 66 |
| }, |
| "n": 236, |
| "n_positive": 72, |
| "n_negative": 164, |
| "roc_auc": 0.9961890243902439, |
| "label3_counts": { |
| "legit": 164, |
| "phish": 0, |
| "spam": 72, |
| "unwanted": 0 |
| } |
| }, |
| "CEAS-08": { |
| "threshold": 0.5, |
| "accuracy": 0.9864130434782609, |
| "precision": 0.0, |
| "recall": 0.0, |
| "f1": 0.0, |
| "specificity": 0.9864130434782609, |
| "false_positive_rate": 0.01358695652173913, |
| "false_negative_rate": 0.0, |
| "confusion_matrix": { |
| "tn": 726, |
| "fp": 10, |
| "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": 0.9792993630573248, |
| "precision": 1.0, |
| "recall": 0.9792993630573248, |
| "f1": 0.9895414320193081, |
| "specificity": 0.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.020700636942675158, |
| "confusion_matrix": { |
| "tn": 0, |
| "fp": 0, |
| "fn": 13, |
| "tp": 615 |
| }, |
| "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": 0.9819819819819819, |
| "precision": 1.0, |
| "recall": 0.9819819819819819, |
| "f1": 0.9909090909090909, |
| "specificity": 0.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.018018018018018018, |
| "confusion_matrix": { |
| "tn": 0, |
| "fp": 0, |
| "fn": 4, |
| "tp": 218 |
| }, |
| "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": 0.9899665551839465, |
| "precision": 1.0, |
| "recall": 0.9899665551839465, |
| "f1": 0.9949579831932773, |
| "specificity": 0.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.010033444816053512, |
| "confusion_matrix": { |
| "tn": 0, |
| "fp": 0, |
| "fn": 3, |
| "tp": 296 |
| }, |
| "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": 0.9954504094631483, |
| "precision": 0.0, |
| "recall": 0.0, |
| "f1": 0.0, |
| "specificity": 0.9954504094631483, |
| "false_positive_rate": 0.004549590536851683, |
| "false_negative_rate": 0.0, |
| "confusion_matrix": { |
| "tn": 1094, |
| "fp": 5, |
| "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": 1195, |
| "mean_tokens_full": 1003.6, |
| "mean_tokens_fed": 280.3, |
| "median_tokens_full": 243.0, |
| "pct_truncated": 26.5 |
| }, |
| "tn": { |
| "n": 1982, |
| "mean_tokens_full": 733.4, |
| "mean_tokens_fed": 358.3, |
| "median_tokens_full": 392.5, |
| "pct_truncated": 38.3 |
| }, |
| "fp": { |
| "n": 17, |
| "mean_tokens_full": 1469.5, |
| "mean_tokens_fed": 384.9, |
| "median_tokens_full": 875.0, |
| "pct_truncated": 58.8 |
| }, |
| "fn": { |
| "n": 26, |
| "mean_tokens_full": 443.6, |
| "mean_tokens_fed": 260.9, |
| "median_tokens_full": 177.0, |
| "pct_truncated": 34.6 |
| }, |
| "correct": { |
| "n": 3177, |
| "mean_tokens_full": 835.0, |
| "mean_tokens_fed": 329.0, |
| "median_tokens_full": 339.0, |
| "pct_truncated": 33.9 |
| }, |
| "wrong": { |
| "n": 43, |
| "mean_tokens_full": 849.2, |
| "mean_tokens_fed": 309.9, |
| "median_tokens_full": 340.0, |
| "pct_truncated": 44.2 |
| } |
| }, |
| "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": 0.9393939393939394, |
| "fpr": 0.03333333333333333, |
| "accuracy": 0.9457364341085271 |
| }, |
| { |
| "bucket": "65-128", |
| "n": 427, |
| "n_positive": 252, |
| "positive_rate": 0.5901639344262295, |
| "recall": 0.9880952380952381, |
| "fpr": 0.005714285714285714, |
| "accuracy": 0.990632318501171 |
| }, |
| { |
| "bucket": "129-256", |
| "n": 699, |
| "n_positive": 276, |
| "positive_rate": 0.3948497854077253, |
| "recall": 0.9818840579710145, |
| "fpr": 0.004728132387706856, |
| "accuracy": 0.9899856938483548 |
| }, |
| { |
| "bucket": "257-512", |
| "n": 870, |
| "n_positive": 268, |
| "positive_rate": 0.3080459770114943, |
| "recall": 0.9888059701492538, |
| "fpr": 0.0049833887043189366, |
| "accuracy": 0.993103448275862 |
| }, |
| { |
| "bucket": ">512", |
| "n": 1095, |
| "n_positive": 326, |
| "positive_rate": 0.29771689497716897, |
| "recall": 0.9723926380368099, |
| "fpr": 0.013003901170351105, |
| "accuracy": 0.982648401826484 |
| } |
| ] |
| }, |
| "inference": { |
| "device": "cuda", |
| "autocast_bf16": true, |
| "batch_size": 64, |
| "pad_to_multiple_of": 8, |
| "num_labels": 3, |
| "rows": 3220, |
| "seconds": 6.42, |
| "rows_per_s": 501.6, |
| "padded_tokens": 1079936, |
| "real_tokens": 1058490, |
| "padded_tokens_per_s": 168244, |
| "peak_vram_gb": 1.7 |
| }, |
| "latency": { |
| "instructor_benchmark_ms": 74.0, |
| "samples_requested": 100, |
| "sample_split": "test", |
| "max_len": 512, |
| "gpu_bf16": { |
| "n": 100, |
| "avg_ms": 5.05, |
| "p50_ms": 4.42, |
| "p95_ms": 6.98, |
| "max_ms": 12.33, |
| "avg_s": 0.0051, |
| "mean_tokens": 280.0, |
| "ratio_to_benchmark": 0.068, |
| "device": "NVIDIA GeForce RTX 3090 Ti" |
| }, |
| "cpu_fp32": { |
| "n": 100, |
| "avg_ms": 246.62, |
| "p50_ms": 242.67, |
| "p95_ms": 356.11, |
| "max_ms": 389.87, |
| "avg_s": 0.2466, |
| "mean_tokens": 280.0, |
| "ratio_to_benchmark": 3.333, |
| "threads": 16, |
| "estimated_full_run_s": 27.1 |
| }, |
| "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-12L/best", |
| "run_name": "ft-12L", |
| "params": 186290179, |
| "timestamp": "2026-10-09 08:54", |
| "num_labels": 3, |
| "measured_once_for_splits": [ |
| "test", |
| "test3" |
| ] |
| }, |
| "error_analysis": { |
| "path": "reports/eval_ft-12L/error_analysis_test3.md", |
| "n_fn": 26, |
| "n_fp": 17, |
| "composition": { |
| "fp": { |
| "n": 17, |
| "mailing_list_or_digest": 0.588, |
| "html_heavy": 0.0, |
| "very_short_lt20_tokens": 0.0, |
| "truncated_gt512": 0.588, |
| "lure_phrase": 0.0 |
| }, |
| "tn": { |
| "n": 1982, |
| "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": 26, |
| "mailing_list_or_digest": 0.269, |
| "html_heavy": 0.0, |
| "very_short_lt20_tokens": 0.115, |
| "truncated_gt512": 0.346, |
| "lure_phrase": 0.115 |
| }, |
| "tp": { |
| "n": 1195, |
| "mailing_list_or_digest": 0.083, |
| "html_heavy": 0.0, |
| "very_short_lt20_tokens": 0.005, |
| "truncated_gt512": 0.265, |
| "lure_phrase": 0.222 |
| } |
| }, |
| "fn_vs_tp_tokens": [ |
| { |
| "token": "invite", |
| "share_a": 0.115, |
| "share_b": 0.003, |
| "ratio": 35.09 |
| }, |
| { |
| "token": "oct", |
| "share_a": 0.115, |
| "share_b": 0.003, |
| "ratio": 35.09 |
| }, |
| { |
| "token": "association", |
| "share_a": 0.192, |
| "share_b": 0.007, |
| "ratio": 29.19 |
| }, |
| { |
| "token": "angeles", |
| "share_a": 0.115, |
| "share_b": 0.004, |
| "ratio": 28.71 |
| }, |
| { |
| "token": "xent", |
| "share_a": 0.115, |
| "share_b": 0.004, |
| "ratio": 28.71 |
| }, |
| { |
| "token": "fork", |
| "share_a": 0.115, |
| "share_b": 0.004, |
| "ratio": 28.71 |
| }, |
| { |
| "token": "mailman", |
| "share_a": 0.192, |
| "share_b": 0.008, |
| "ratio": 26.12 |
| }, |
| { |
| "token": "environment", |
| "share_a": 0.115, |
| "share_b": 0.005, |
| "ratio": 24.29 |
| }, |
| { |
| "token": "york", |
| "share_a": 0.115, |
| "share_b": 0.005, |
| "ratio": 24.29 |
| }, |
| { |
| "token": "community", |
| "share_a": 0.115, |
| "share_b": 0.005, |
| "ratio": 24.29 |
| }, |
| { |
| "token": "listinfo", |
| "share_a": 0.231, |
| "share_b": 0.01, |
| "ratio": 23.46 |
| }, |
| { |
| "token": "subscription", |
| "share_a": 0.154, |
| "share_b": 0.008, |
| "ratio": 21.37 |
| }, |
| { |
| "token": "event", |
| "share_a": 0.115, |
| "share_b": 0.006, |
| "ratio": 21.05 |
| }, |
| { |
| "token": "technologies", |
| "share_a": 0.115, |
| "share_b": 0.006, |
| "ratio": 21.05 |
| }, |
| { |
| "token": "eleven", |
| "share_a": 0.115, |
| "share_b": 0.006, |
| "ratio": 21.05 |
| }, |
| { |
| "token": "entertainment", |
| "share_a": 0.115, |
| "share_b": 0.007, |
| "ratio": 18.58 |
| }, |
| { |
| "token": "wonderful", |
| "share_a": 0.115, |
| "share_b": 0.007, |
| "ratio": 18.58 |
| }, |
| { |
| "token": "wants", |
| "share_a": 0.115, |
| "share_b": 0.008, |
| "ratio": 16.62 |
| }, |
| { |
| "token": "wanted", |
| "share_a": 0.115, |
| "share_b": 0.009, |
| "ratio": 13.73 |
| }, |
| { |
| "token": "sound", |
| "share_a": 0.115, |
| "share_b": 0.011, |
| "ratio": 11.7 |
| } |
| ], |
| "fp_vs_tn_tokens": [ |
| { |
| "token": "heid", |
| "share_a": 0.176, |
| "share_b": 0.0, |
| "ratio": 793.0 |
| }, |
| { |
| "token": "dreamweaver", |
| "share_a": 0.176, |
| "share_b": 0.0, |
| "ratio": 793.0 |
| }, |
| { |
| "token": "stylesheets", |
| "share_a": 0.176, |
| "share_b": 0.0, |
| "ratio": 793.0 |
| }, |
| { |
| "token": "rias", |
| "share_a": 0.176, |
| "share_b": 0.001, |
| "ratio": 264.33 |
| }, |
| { |
| "token": "ears", |
| "share_a": 0.176, |
| "share_b": 0.001, |
| "ratio": 158.6 |
| }, |
| { |
| "token": "stewart", |
| "share_a": 0.176, |
| "share_b": 0.001, |
| "ratio": 158.6 |
| }, |
| { |
| "token": "untitled", |
| "share_a": 0.176, |
| "share_b": 0.001, |
| "ratio": 158.6 |
| }, |
| { |
| "token": "handheld", |
| "share_a": 0.176, |
| "share_b": 0.001, |
| "ratio": 158.6 |
| }, |
| { |
| "token": "css", |
| "share_a": 0.176, |
| "share_b": 0.002, |
| "ratio": 113.29 |
| }, |
| { |
| "token": "keynote", |
| "share_a": 0.176, |
| "share_b": 0.002, |
| "ratio": 113.29 |
| }, |
| { |
| "token": "inspire", |
| "share_a": 0.176, |
| "share_b": 0.002, |
| "ratio": 113.29 |
| }, |
| { |
| "token": "dollars", |
| "share_a": 0.235, |
| "share_b": 0.003, |
| "ratio": 92.69 |
| }, |
| { |
| "token": "rock", |
| "share_a": 0.235, |
| "share_b": 0.003, |
| "ratio": 92.69 |
| }, |
| { |
| "token": "ajax", |
| "share_a": 0.176, |
| "share_b": 0.002, |
| "ratio": 88.11 |
| }, |
| { |
| "token": "ridge", |
| "share_a": 0.176, |
| "share_b": 0.002, |
| "ratio": 88.11 |
| }, |
| { |
| "token": "commitment", |
| "share_a": 0.176, |
| "share_b": 0.003, |
| "ratio": 72.09 |
| }, |
| { |
| "token": "ted", |
| "share_a": 0.176, |
| "share_b": 0.003, |
| "ratio": 72.09 |
| }, |
| { |
| "token": "front-end", |
| "share_a": 0.176, |
| "share_b": 0.003, |
| "ratio": 72.09 |
| }, |
| { |
| "token": "historic", |
| "share_a": 0.176, |
| "share_b": 0.003, |
| "ratio": 61.0 |
| }, |
| { |
| "token": "adobe", |
| "share_a": 0.176, |
| "share_b": 0.003, |
| "ratio": 61.0 |
| } |
| ], |
| "top_fn_doc_ids": [ |
| "aura:Nigerian_Fraud:001032", |
| "primary:007176", |
| "aura:Nazario:000097", |
| "primary:112100", |
| "primary:001939", |
| "primary:148887", |
| "primary:135631", |
| "aura:Nazario:000643", |
| "primary:010013", |
| "primary:102650", |
| "aura:Nazario:001540", |
| "primary:025244", |
| "primary:148857", |
| "aura:Nazario:000551", |
| "primary:061572", |
| "primary:107809", |
| "primary:046569", |
| "primary:181246", |
| "aura:Nigerian_Fraud:000534", |
| "aura:Nigerian_Fraud:000495", |
| "primary:025024", |
| "primary:150100", |
| "primary:191966", |
| "primary:157116", |
| "primary:197304" |
| ], |
| "top_fp_doc_ids": [ |
| "primary:144048", |
| "primary:164457", |
| "primary:153841", |
| "primary:091801", |
| "primary:156985", |
| "primary:003448", |
| "primary:041713", |
| "primary:152763", |
| "primary:156887", |
| "primary:057514", |
| "primary:199386", |
| "primary:055965", |
| "primary:168120", |
| "primary:024251", |
| "primary:089923", |
| "primary:016587", |
| "primary:021911" |
| ], |
| "threeway": { |
| "n_phish_as_spam": 7, |
| "n_spam_as_phish": 1, |
| "top_phish_as_spam_doc_ids": [ |
| "aura:Nazario:000532", |
| "aura:Nigerian_Fraud:000824", |
| "aura:Nazario:000328", |
| "aura:Nigerian_Fraud:001698", |
| "aura:Nigerian_Fraud:003049", |
| "aura:Nigerian_Fraud:000337", |
| "aura:Nazario:000401" |
| ], |
| "top_spam_as_phish_doc_ids": [ |
| "primary:077835" |
| ], |
| "phish_as_spam_tokens": [ |
| { |
| "token": "join", |
| "share_a": 0.571, |
| "share_b": 0.02, |
| "ratio": 29.0 |
| }, |
| { |
| "token": "friends", |
| "share_a": 0.429, |
| "share_b": 0.016, |
| "ratio": 27.86 |
| }, |
| { |
| "token": "complete", |
| "share_a": 0.429, |
| "share_b": 0.049, |
| "ratio": 9.29 |
| }, |
| { |
| "token": "link", |
| "share_a": 0.571, |
| "share_b": 0.073, |
| "ratio": 8.12 |
| }, |
| { |
| "token": "don't", |
| "share_a": 0.429, |
| "share_b": 0.067, |
| "ratio": 6.86 |
| }, |
| { |
| "token": "could", |
| "share_a": 0.429, |
| "share_b": 0.077, |
| "ratio": 6.0 |
| }, |
| { |
| "token": "http", |
| "share_a": 0.857, |
| "share_b": 0.189, |
| "ratio": 4.56 |
| }, |
| { |
| "token": "www", |
| "share_a": 0.571, |
| "share_b": 0.15, |
| "ratio": 3.98 |
| }, |
| { |
| "token": "new", |
| "share_a": 0.429, |
| "share_b": 0.164, |
| "ratio": 2.84 |
| }, |
| { |
| "token": "click", |
| "share_a": 0.429, |
| "share_b": 0.176, |
| "ratio": 2.65 |
| }, |
| { |
| "token": "years", |
| "share_a": 0.429, |
| "share_b": 0.195, |
| "ratio": 2.38 |
| }, |
| { |
| "token": "get", |
| "share_a": 0.429, |
| "share_b": 0.203, |
| "ratio": 2.29 |
| }, |
| { |
| "token": "com", |
| "share_a": 0.714, |
| "share_b": 0.335, |
| "ratio": 2.18 |
| }, |
| { |
| "token": "message", |
| "share_a": 0.429, |
| "share_b": 0.213, |
| "ratio": 2.18 |
| }, |
| { |
| "token": "about", |
| "share_a": 0.429, |
| "share_b": 0.241, |
| "ratio": 1.93 |
| }, |
| { |
| "token": "who", |
| "share_a": 0.571, |
| "share_b": 0.316, |
| "ratio": 1.9 |
| }, |
| { |
| "token": "after", |
| "share_a": 0.429, |
| "share_b": 0.278, |
| "ratio": 1.67 |
| }, |
| { |
| "token": "are", |
| "share_a": 0.857, |
| "share_b": 0.562, |
| "ratio": 1.54 |
| }, |
| { |
| "token": "into", |
| "share_a": 0.429, |
| "share_b": 0.325, |
| "ratio": 1.43 |
| }, |
| { |
| "token": "which", |
| "share_a": 0.429, |
| "share_b": 0.361, |
| "ratio": 1.29 |
| } |
| ], |
| "spam_as_phish_tokens": [] |
| } |
| }, |
| "plots": { |
| "confusion_matrix": "reports/eval_ft-12L/confusion_matrix_test3.png", |
| "confusion_matrix3": "reports/eval_ft-12L/confusion_matrix3_test3.png", |
| "roc_curve": "reports/eval_ft-12L/roc_curve_test3.png", |
| "pr_curve": "reports/eval_ft-12L/pr_curve_test3.png" |
| } |
| } |
|
|
