| { |
| "timestamp": "2026-10-09 10:46", |
| "run_name": "ft-focal", |
| "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-focal/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-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 |
| } |
| }, |
| "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": 0.989751552795031, |
| "precision": 0.9892915980230642, |
| "recall": 0.9836199836199836, |
| "f1": 0.986447638603696, |
| "specificity": 0.9934967483741871, |
| "false_positive_rate": 0.0065032516258129065, |
| "false_negative_rate": 0.01638001638001638, |
| "confusion_matrix": { |
| "tn": 1986, |
| "fp": 13, |
| "fn": 20, |
| "tp": 1201 |
| }, |
| "n": 3220, |
| "n_positive": 1221, |
| "n_negative": 1999 |
| }, |
| "threshold_free": { |
| "roc_auc": 0.9993325901279878, |
| "pr_auc": 0.9988537821967886, |
| "recall_at_fpr_1pct": { |
| "fpr_budget": 0.01, |
| "recall": 0.9868959868959869, |
| "fpr": 0.009004502251125562, |
| "threshold": 0.43377745151519775, |
| "threshold_rule": "flag when p >= threshold" |
| }, |
| "recall_at_fpr_0_1pct": { |
| "fpr_budget": 0.001, |
| "recall": 0.8787878787878788, |
| "fpr": 0.0005002501250625312, |
| "threshold": 0.9472352862358093, |
| "threshold_rule": "flag when p >= threshold" |
| }, |
| "best_f1": { |
| "threshold": 0.47499534487724304, |
| "f1": 0.9876948318293682, |
| "precision": 0.9893179950698439, |
| "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": 1201, |
| "predicted_phishing": 515, |
| "predicted_spam": 686 |
| }, |
| "false_positives_flagged": { |
| "n": 13, |
| "predicted_phishing": 1, |
| "predicted_spam": 12 |
| }, |
| "missed_positives": { |
| "n": 20, |
| "predicted_phishing": 3, |
| "predicted_spam": 17 |
| }, |
| "all_flagged": { |
| "n": 1214, |
| "predicted_phishing": 516, |
| "predicted_spam": 698 |
| }, |
| "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": [ |
| [ |
| 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 |
| } |
| } |
| }, |
| "accuracy": 0.9885093167701864, |
| "macro_f1": 0.9867305252015051, |
| "macro_f1_present_classes": 0.9867305252015051, |
| "classes_present": [ |
| "Legitimate", |
| "Phishing", |
| "Spam" |
| ], |
| "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 |
| } |
| }, |
| "argmax_rule": { |
| "doc": "plain argmax over the three probabilities (secondary; can disagree with the binary verdict near the threshold)", |
| "accuracy": 0.987888198757764, |
| "macro_f1": 0.9858185605052249, |
| "per_class": { |
| "Legitimate": { |
| "precision": 0.9880715705765407, |
| "recall": 0.9944972486243121, |
| "f1": 0.9912739965095986, |
| "support": 1999 |
| }, |
| "Phishing": { |
| "precision": 0.9980430528375733, |
| "recall": 0.9788867562380038, |
| "f1": 0.9883720930232558, |
| "support": 521 |
| }, |
| "Spam": { |
| "precision": 0.9799139167862266, |
| "recall": 0.9757142857142858, |
| "f1": 0.9778095919828204, |
| "support": 700 |
| } |
| }, |
| "rows_where_rules_differ": 6 |
| }, |
| "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": [ |
| [ |
| 517, |
| 4 |
| ], |
| [ |
| 1, |
| 699 |
| ] |
| ], |
| "cells": { |
| "true_phishing": { |
| "pred_phishing": 517, |
| "pred_spam": 4 |
| }, |
| "true_spam": { |
| "pred_phishing": 1, |
| "pred_spam": 699 |
| } |
| }, |
| "accuracy": 0.9959049959049959, |
| "phishing_as_spam": 4, |
| "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": [ |
| [ |
| 4, |
| 514, |
| 3 |
| ], |
| [ |
| 16, |
| 1, |
| 683 |
| ] |
| ], |
| "missed_as_legitimate": { |
| "phishing": 4, |
| "spam": 16 |
| } |
| } |
| }, |
| "per_source": { |
| "Assassin": { |
| "n": 236, |
| "counts": { |
| "Legitimate": 164, |
| "Phishing": 0, |
| "Spam": 72 |
| }, |
| "accuracy": 0.9533898305084746, |
| "macro_f1": 0.6305609284332688, |
| "macro_f1_present_classes": 0.9458413926499033, |
| "per_class_recall": { |
| "Legitimate": 0.975609756097561, |
| "Spam": 0.9027777777777778 |
| } |
| }, |
| "CEAS-08": { |
| "n": 736, |
| "counts": { |
| "Legitimate": 736, |
| "Phishing": 0, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9904891304347826, |
| "macro_f1": 0.331740614334471, |
| "macro_f1_present_classes": 0.995221843003413, |
| "per_class_recall": { |
| "Legitimate": 0.9904891304347826 |
| } |
| }, |
| "Enron": { |
| "n": 628, |
| "counts": { |
| "Legitimate": 0, |
| "Phishing": 0, |
| "Spam": 628 |
| }, |
| "accuracy": 0.9840764331210191, |
| "macro_f1": 0.3306581059390048, |
| "macro_f1_present_classes": 0.9919743178170144, |
| "per_class_recall": { |
| "Spam": 0.9840764331210191 |
| } |
| }, |
| "Nazario": { |
| "n": 222, |
| "counts": { |
| "Legitimate": 0, |
| "Phishing": 222, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9864864864864865, |
| "macro_f1": 0.3310657596371882, |
| "macro_f1_present_classes": 0.9931972789115646, |
| "per_class_recall": { |
| "Phishing": 0.9864864864864865 |
| } |
| }, |
| "Nigerian_Fraud": { |
| "n": 299, |
| "counts": { |
| "Legitimate": 0, |
| "Phishing": 299, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9866220735785953, |
| "macro_f1": 0.33108866442199775, |
| "macro_f1_present_classes": 0.9932659932659933, |
| "per_class_recall": { |
| "Phishing": 0.9866220735785953 |
| } |
| }, |
| "TREC-07": { |
| "n": 1099, |
| "counts": { |
| "Legitimate": 1099, |
| "Phishing": 0, |
| "Spam": 0 |
| }, |
| "accuracy": 0.9981801637852593, |
| "macro_f1": 0.33302975106253796, |
| "macro_f1_present_classes": 0.9990892531876139, |
| "per_class_recall": { |
| "Legitimate": 0.9981801637852593 |
| } |
| } |
| } |
| }, |
| "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": 0.9576271186440678, |
| "precision": 0.9428571428571428, |
| "recall": 0.9166666666666666, |
| "f1": 0.9295774647887323, |
| "specificity": 0.975609756097561, |
| "false_positive_rate": 0.024390243902439025, |
| "false_negative_rate": 0.08333333333333333, |
| "confusion_matrix": { |
| "tn": 160, |
| "fp": 4, |
| "fn": 6, |
| "tp": 66 |
| }, |
| "n": 236, |
| "n_positive": 72, |
| "n_negative": 164, |
| "roc_auc": 0.994579945799458, |
| "label3_counts": { |
| "legit": 164, |
| "phish": 0, |
| "spam": 72, |
| "unwanted": 0 |
| } |
| }, |
| "CEAS-08": { |
| "threshold": 0.5, |
| "accuracy": 0.9904891304347826, |
| "precision": 0.0, |
| "recall": 0.0, |
| "f1": 0.0, |
| "specificity": 0.9904891304347826, |
| "false_positive_rate": 0.009510869565217392, |
| "false_negative_rate": 0.0, |
| "confusion_matrix": { |
| "tn": 729, |
| "fp": 7, |
| "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": 0.9840764331210191, |
| "precision": 1.0, |
| "recall": 0.9840764331210191, |
| "f1": 0.9919743178170145, |
| "specificity": 0.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.01592356687898089, |
| "confusion_matrix": { |
| "tn": 0, |
| "fp": 0, |
| "fn": 10, |
| "tp": 618 |
| }, |
| "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": 0.9864864864864865, |
| "precision": 1.0, |
| "recall": 0.9864864864864865, |
| "f1": 0.9931972789115647, |
| "specificity": 0.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.013513513513513514, |
| "confusion_matrix": { |
| "tn": 0, |
| "fp": 0, |
| "fn": 3, |
| "tp": 219 |
| }, |
| "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": 0.9966555183946488, |
| "precision": 1.0, |
| "recall": 0.9966555183946488, |
| "f1": 0.998324958123953, |
| "specificity": 0.0, |
| "false_positive_rate": 0.0, |
| "false_negative_rate": 0.0033444816053511705, |
| "confusion_matrix": { |
| "tn": 0, |
| "fp": 0, |
| "fn": 1, |
| "tp": 298 |
| }, |
| "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": 0.9981801637852593, |
| "precision": 0.0, |
| "recall": 0.0, |
| "f1": 0.0, |
| "specificity": 0.9981801637852593, |
| "false_positive_rate": 0.0018198362147406734, |
| "false_negative_rate": 0.0, |
| "confusion_matrix": { |
| "tn": 1097, |
| "fp": 2, |
| "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": 1201, |
| "mean_tokens_full": 978.0, |
| "mean_tokens_fed": 279.8, |
| "median_tokens_full": 243.0, |
| "pct_truncated": 26.6 |
| }, |
| "tn": { |
| "n": 1986, |
| "mean_tokens_full": 732.6, |
| "mean_tokens_fed": 358.4, |
| "median_tokens_full": 392.5, |
| "pct_truncated": 38.3 |
| }, |
| "fp": { |
| "n": 13, |
| "mean_tokens_full": 1814.3, |
| "mean_tokens_fed": 377.2, |
| "median_tokens_full": 875.0, |
| "pct_truncated": 61.5 |
| }, |
| "fn": { |
| "n": 20, |
| "mean_tokens_full": 1807.8, |
| "mean_tokens_fed": 284.1, |
| "median_tokens_full": 291.0, |
| "pct_truncated": 35.0 |
| }, |
| "correct": { |
| "n": 3187, |
| "mean_tokens_full": 825.1, |
| "mean_tokens_fed": 328.8, |
| "median_tokens_full": 339.0, |
| "pct_truncated": 33.9 |
| }, |
| "wrong": { |
| "n": 33, |
| "mean_tokens_full": 1810.4, |
| "mean_tokens_fed": 320.8, |
| "median_tokens_full": 368.0, |
| "pct_truncated": 45.5 |
| } |
| }, |
| "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": 0.9494949494949495, |
| "fpr": 0.03333333333333333, |
| "accuracy": 0.9534883720930233 |
| }, |
| { |
| "bucket": "65-128", |
| "n": 427, |
| "n_positive": 252, |
| "positive_rate": 0.5901639344262295, |
| "recall": 0.9920634920634921, |
| "fpr": 0.011428571428571429, |
| "accuracy": 0.990632318501171 |
| }, |
| { |
| "bucket": "129-256", |
| "n": 699, |
| "n_positive": 276, |
| "positive_rate": 0.3948497854077253, |
| "recall": 0.9927536231884058, |
| "fpr": 0.0, |
| "accuracy": 0.9971387696709585 |
| }, |
| { |
| "bucket": "257-512", |
| "n": 870, |
| "n_positive": 268, |
| "positive_rate": 0.3080459770114943, |
| "recall": 0.9850746268656716, |
| "fpr": 0.0033222591362126247, |
| "accuracy": 0.993103448275862 |
| }, |
| { |
| "bucket": ">512", |
| "n": 1095, |
| "n_positive": 326, |
| "positive_rate": 0.29771689497716897, |
| "recall": 0.9785276073619632, |
| "fpr": 0.010403120936280884, |
| "accuracy": 0.9863013698630136 |
| } |
| ] |
| }, |
| "inference": { |
| "device": "cuda", |
| "autocast_bf16": true, |
| "batch_size": 64, |
| "pad_to_multiple_of": 8, |
| "num_labels": 3, |
| "rows": 3220, |
| "seconds": 13.55, |
| "rows_per_s": 237.6, |
| "padded_tokens": 1079936, |
| "real_tokens": 1058490, |
| "padded_tokens_per_s": 79672, |
| "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": 10.08, |
| "p50_ms": 8.9, |
| "p95_ms": 13.72, |
| "max_ms": 18.58, |
| "avg_s": 0.0101, |
| "mean_tokens": 280.0, |
| "ratio_to_benchmark": 0.136, |
| "device": "NVIDIA GeForce RTX 3090 Ti" |
| }, |
| "cpu_fp32": { |
| "n": 100, |
| "avg_ms": 458.57, |
| "p50_ms": 445.01, |
| "p95_ms": 701.07, |
| "max_ms": 828.65, |
| "avg_s": 0.4586, |
| "mean_tokens": 280.0, |
| "ratio_to_benchmark": 6.197, |
| "threads": 16, |
| "estimated_full_run_s": 41.8 |
| }, |
| "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-focal/best", |
| "run_name": "ft-focal", |
| "params": 337444867, |
| "timestamp": "2026-10-09 10:46", |
| "num_labels": 3, |
| "measured_once_for_splits": [ |
| "test", |
| "test3" |
| ] |
| }, |
| "error_analysis": { |
| "path": "/home/nathank/BITS/dev/Phishing Model/reports/error_analysis_test3.md", |
| "n_fn": 20, |
| "n_fp": 13, |
| "composition": { |
| "fp": { |
| "n": 13, |
| "mailing_list_or_digest": 0.462, |
| "html_heavy": 0.0, |
| "very_short_lt20_tokens": 0.0, |
| "truncated_gt512": 0.615, |
| "lure_phrase": 0.0 |
| }, |
| "tn": { |
| "n": 1986, |
| "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": 20, |
| "mailing_list_or_digest": 0.3, |
| "html_heavy": 0.0, |
| "very_short_lt20_tokens": 0.1, |
| "truncated_gt512": 0.35, |
| "lure_phrase": 0.0 |
| }, |
| "tp": { |
| "n": 1201, |
| "mailing_list_or_digest": 0.083, |
| "html_heavy": 0.0, |
| "very_short_lt20_tokens": 0.006, |
| "truncated_gt512": 0.266, |
| "lure_phrase": 0.223 |
| } |
| }, |
| "fn_vs_tp_tokens": [ |
| { |
| "token": "invite", |
| "share_a": 0.25, |
| "share_b": 0.002, |
| "ratio": 128.94 |
| }, |
| { |
| "token": "cut", |
| "share_a": 0.15, |
| "share_b": 0.002, |
| "ratio": 82.05 |
| }, |
| { |
| "token": "practical", |
| "share_a": 0.15, |
| "share_b": 0.002, |
| "ratio": 82.05 |
| }, |
| { |
| "token": "networking", |
| "share_a": 0.2, |
| "share_b": 0.002, |
| "ratio": 75.36 |
| }, |
| { |
| "token": "audience", |
| "share_a": 0.15, |
| "share_b": 0.003, |
| "ratio": 45.59 |
| }, |
| { |
| "token": "oct", |
| "share_a": 0.15, |
| "share_b": 0.003, |
| "ratio": 45.59 |
| }, |
| { |
| "token": "innovative", |
| "share_a": 0.15, |
| "share_b": 0.003, |
| "ratio": 45.59 |
| }, |
| { |
| "token": "event", |
| "share_a": 0.2, |
| "share_b": 0.005, |
| "ratio": 40.58 |
| }, |
| { |
| "token": "angeles", |
| "share_a": 0.15, |
| "share_b": 0.004, |
| "ratio": 37.3 |
| }, |
| { |
| "token": "anyway", |
| "share_a": 0.15, |
| "share_b": 0.004, |
| "ratio": 37.3 |
| }, |
| { |
| "token": "feature", |
| "share_a": 0.15, |
| "share_b": 0.005, |
| "ratio": 31.56 |
| }, |
| { |
| "token": "york", |
| "share_a": 0.15, |
| "share_b": 0.005, |
| "ratio": 31.56 |
| }, |
| { |
| "token": "subscription", |
| "share_a": 0.2, |
| "share_b": 0.007, |
| "ratio": 27.76 |
| }, |
| { |
| "token": "technologies", |
| "share_a": 0.15, |
| "share_b": 0.006, |
| "ratio": 27.35 |
| }, |
| { |
| "token": "entertainment", |
| "share_a": 0.15, |
| "share_b": 0.007, |
| "ratio": 24.13 |
| }, |
| { |
| "token": "staff", |
| "share_a": 0.2, |
| "share_b": 0.011, |
| "ratio": 19.54 |
| }, |
| { |
| "token": "association", |
| "share_a": 0.15, |
| "share_b": 0.008, |
| "ratio": 19.54 |
| }, |
| { |
| "token": "markets", |
| "share_a": 0.15, |
| "share_b": 0.009, |
| "ratio": 17.84 |
| }, |
| { |
| "token": "hosting", |
| "share_a": 0.15, |
| "share_b": 0.009, |
| "ratio": 17.84 |
| }, |
| { |
| "token": "mailman", |
| "share_a": 0.15, |
| "share_b": 0.009, |
| "ratio": 17.84 |
| } |
| ], |
| "fp_vs_tn_tokens": [ |
| { |
| "token": "outlets", |
| "share_a": 0.231, |
| "share_b": 0.001, |
| "ratio": 206.01 |
| }, |
| { |
| "token": "zzz-unspun", |
| "share_a": 0.231, |
| "share_b": 0.001, |
| "ratio": 206.01 |
| }, |
| { |
| "token": "czzz-unspun", |
| "share_a": 0.231, |
| "share_b": 0.001, |
| "ratio": 206.01 |
| }, |
| { |
| "token": "cook", |
| "share_a": 0.231, |
| "share_b": 0.001, |
| "ratio": 206.01 |
| }, |
| { |
| "token": "full-color", |
| "share_a": 0.385, |
| "share_b": 0.002, |
| "ratio": 179.85 |
| }, |
| { |
| "token": "muehlbauer", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "vanderkolk", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "eletra", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "loripatel", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "copyedited", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "jimduffy86", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "asbrand", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "patel", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "authoritatively", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "four-week", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "duffy", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "mediaunspun", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "savviest", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "dasbrand", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| }, |
| { |
| "token": "sendashtml", |
| "share_a": 0.231, |
| "share_b": 0.002, |
| "ratio": 147.15 |
| } |
| ], |
| "top_fn_doc_ids": [ |
| "primary:191966", |
| "primary:148887", |
| "aura:Nazario:000097", |
| "primary:010013", |
| "primary:007176", |
| "aura:Nazario:000643", |
| "primary:181246", |
| "primary:095405", |
| "primary:014300", |
| "primary:001939", |
| "primary:033220", |
| "primary:025244", |
| "primary:133074", |
| "aura:Nigerian_Fraud:003049", |
| "aura:Nazario:000299", |
| "primary:046569", |
| "primary:135631", |
| "primary:148857", |
| "primary:129677", |
| "primary:075760" |
| ], |
| "top_fp_doc_ids": [ |
| "primary:144048", |
| "primary:199386", |
| "primary:091801", |
| "primary:152763", |
| "primary:165228", |
| "primary:041713", |
| "primary:103927", |
| "primary:055965", |
| "primary:170237", |
| "primary:117398", |
| "primary:168120", |
| "primary:057514", |
| "primary:021911" |
| ], |
| "threeway": { |
| "n_phish_as_spam": 3, |
| "n_spam_as_phish": 1, |
| "top_phish_as_spam_doc_ids": [ |
| "aura:Nigerian_Fraud:001698", |
| "aura:Nigerian_Fraud:000337", |
| "aura:Nigerian_Fraud:000824" |
| ], |
| "top_spam_as_phish_doc_ids": [ |
| "primary:077835" |
| ], |
| "phish_as_spam_tokens": [ |
| { |
| "token": "join", |
| "share_a": 1.0, |
| "share_b": 0.019, |
| "ratio": 49.0 |
| }, |
| { |
| "token": "could", |
| "share_a": 1.0, |
| "share_b": 0.076, |
| "ratio": 13.03 |
| }, |
| { |
| "token": "www", |
| "share_a": 1.0, |
| "share_b": 0.15, |
| "ratio": 6.64 |
| }, |
| { |
| "token": "new", |
| "share_a": 1.0, |
| "share_b": 0.16, |
| "ratio": 6.24 |
| }, |
| { |
| "token": "http", |
| "share_a": 1.0, |
| "share_b": 0.193, |
| "ratio": 5.17 |
| }, |
| { |
| "token": "years", |
| "share_a": 1.0, |
| "share_b": 0.196, |
| "ratio": 5.07 |
| }, |
| { |
| "token": "get", |
| "share_a": 1.0, |
| "share_b": 0.202, |
| "ratio": 4.92 |
| }, |
| { |
| "token": "about", |
| "share_a": 1.0, |
| "share_b": 0.239, |
| "ratio": 4.17 |
| }, |
| { |
| "token": "after", |
| "share_a": 1.0, |
| "share_b": 0.278, |
| "ratio": 3.59 |
| }, |
| { |
| "token": "who", |
| "share_a": 1.0, |
| "share_b": 0.317, |
| "ratio": 3.15 |
| }, |
| { |
| "token": "into", |
| "share_a": 1.0, |
| "share_b": 0.323, |
| "ratio": 3.09 |
| }, |
| { |
| "token": "com", |
| "share_a": 1.0, |
| "share_b": 0.339, |
| "ratio": 2.95 |
| }, |
| { |
| "token": "which", |
| "share_a": 1.0, |
| "share_b": 0.362, |
| "ratio": 2.76 |
| }, |
| { |
| "token": "now", |
| "share_a": 1.0, |
| "share_b": 0.379, |
| "ratio": 2.63 |
| }, |
| { |
| "token": "can", |
| "share_a": 1.0, |
| "share_b": 0.467, |
| "ratio": 2.14 |
| }, |
| { |
| "token": "are", |
| "share_a": 1.0, |
| "share_b": 0.562, |
| "ratio": 1.78 |
| }, |
| { |
| "token": "from", |
| "share_a": 1.0, |
| "share_b": 0.644, |
| "ratio": 1.55 |
| }, |
| { |
| "token": "will", |
| "share_a": 1.0, |
| "share_b": 0.714, |
| "ratio": 1.4 |
| }, |
| { |
| "token": "for", |
| "share_a": 1.0, |
| "share_b": 0.8, |
| "ratio": 1.25 |
| }, |
| { |
| "token": "this", |
| "share_a": 1.0, |
| "share_b": 0.815, |
| "ratio": 1.23 |
| } |
| ], |
| "spam_as_phish_tokens": [] |
| } |
| }, |
| "plots": { |
| "confusion_matrix": "/home/nathank/BITS/dev/Phishing Model/reports/confusion_matrix_test3.png", |
| "confusion_matrix3": "/home/nathank/BITS/dev/Phishing Model/reports/confusion_matrix3_test3.png", |
| "roc_curve": "/home/nathank/BITS/dev/Phishing Model/reports/roc_curve_test3.png", |
| "pr_curve": "/home/nathank/BITS/dev/Phishing Model/reports/pr_curve_test3.png", |
| "eval_finetune_curves": "/home/nathank/BITS/dev/Phishing Model/reports/eval_finetune_curves_test3.png", |
| "eval_pretrain_curves": "/home/nathank/BITS/dev/Phishing Model/reports/eval_pretrain_curves_test3.png" |
| } |
| } |
|
|
