{ "timestamp": "2026-10-09 09:57", "run_name": "ft-scratch", "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-scratch/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-scratch", "init": "scratch", "n_layers": 24, "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": 0, "best_step": 5009, "num_labels": 3, "label_names": [ "Legitimate", "Phishing", "Spam" ], "binary_rollup_name": "Unwanted (phishing or spam)", "selection_metric": "val_f1_unwanted", "selection_value": 0.9874562778916898, "val_metrics": { "accuracy": 0.9863909971211725, "precision": 0.9863855421686747, "recall": 0.9885293407389519, "f1": 0.9874562778916898, "roc_auc": 0.9984844430897414, "pr_auc": 0.998618660839301, "tn": 6889, "fp": 113, "fn": 95, "tp": 8187, "threshold": 0.5, "f1_optimal_threshold": 0.6013138890266418, "f1_at_optimal_threshold": 0.9878557186876926, "f1_unwanted": 0.9874562778916898, "n_3way": 8105, "accuracy_3way": 0.9832202344231955, "macro_f1_3way": 0.9537815709229355, "precision_legitimate": 0.9979745370370371, "recall_legitimate": 0.9851471008283348, "f1_legitimate": 0.991519333045853, "precision_phishing": 0.9384164222873901, "recall_phishing": 0.9411764705882353, "f1_phishing": 0.9397944199706314, "precision_spam": 0.8814553990610329, "recall_spam": 0.9842726081258192, "f1_spam": 0.930030959752322, "cm3_ll": 6898, "cm3_lp": 20, "cm3_ls": 84, "cm3_pl": 3, "cm3_pp": 320, "cm3_ps": 17, "cm3_sl": 11, "cm3_sp": 1, "cm3_ss": 751, "n_unwanted_3way": 1103, "pvs_phish_as_phish": 322, "pvs_phish_as_spam": 18, "pvs_spam_as_phish": 1, "pvs_spam_as_spam": 762, "val_loss": 0.04709533672780773, "n": 15284, "eval_seconds": 48.1 }, "val_metric_sets": { "binary_unwanted": { "accuracy": 0.9863909971211725, "precision": 0.9863855421686747, "recall": 0.9885293407389519, "f1": 0.9874562778916898, "roc_auc": 0.9984844430897414, "pr_auc": 0.998618660839301, "tn": 6889, "fp": 113, "fn": 95, "tp": 8187, "threshold": 0.5, "f1_optimal_threshold": 0.6013138890266418, "f1_at_optimal_threshold": 0.9878557186876926, "n": 15284, "positive_class": "Unwanted (phishing or spam)" }, "three_way": { "n": 8105, "accuracy": 0.9832202344231955, "macro_f1": 0.9537815709229355, "per_class": { "Legitimate": { "precision": 0.9979745370370371, "recall": 0.9851471008283348, "f1": 0.991519333045853 }, "Phishing": { "precision": 0.9384164222873901, "recall": 0.9411764705882353, "f1": 0.9397944199706314 }, "Spam": { "precision": 0.8814553990610329, "recall": 0.9842726081258192, "f1": 0.930030959752322 } }, "confusion": { "order": [ "Legitimate", "Phishing", "Spam" ], "rows_true_cols_pred": [ [ 6898, 20, 84 ], [ 3, 320, 17 ], [ 11, 1, 751 ] ] }, "phish_vs_spam_on_true_unwanted": { "n": 1103, "order": [ "Phishing", "Spam" ], "rows_true_cols_pred": [ [ 322, 18 ], [ 1, 762 ] ] } } }, "thresholds": { "decision": 0.5, "decision_applies_to": "P(unwanted) = sum of non-legitimate probabilities", "val_f1_optimal": 0.6013138890266418, "val_f1_at_optimal": 0.9878557186876926 }, "init": "scratch", "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": 0.9822981366459628, "precision": 0.9762684124386252, "recall": 0.9770679770679771, "f1": 0.9766680311092918, "specificity": 0.9854927463731866, "false_positive_rate": 0.014507253626813406, "false_negative_rate": 0.02293202293202293, "confusion_matrix": { "tn": 1970, "fp": 29, "fn": 28, "tp": 1193 }, "n": 3220, "n_positive": 1221, "n_negative": 1999 }, "threshold_free": { "roc_auc": 0.9983431519199404, "pr_auc": 0.9974248605846625, "recall_at_fpr_1pct": { "fpr_budget": 0.01, "recall": 0.9672399672399672, "fpr": 0.0080040020010005, "threshold": 0.7805293202400208, "threshold_rule": "flag when p >= threshold" }, "recall_at_fpr_0_1pct": { "fpr_budget": 0.001, "recall": 0.8353808353808354, "fpr": 0.0005002501250625312, "threshold": 0.9868443012237549, "threshold_rule": "flag when p >= threshold" }, "best_f1": { "threshold": 0.365547776222229, "f1": 0.9775601795185639, "precision": 0.9739837398373984, "recall": 0.9811629811629812 } }, "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": 1193, "predicted_phishing": 485, "predicted_spam": 708 }, "false_positives_flagged": { "n": 29, "predicted_phishing": 3, "predicted_spam": 26 }, "missed_positives": { "n": 28, "predicted_phishing": 7, "predicted_spam": 21 }, "all_flagged": { "n": 1222, "predicted_phishing": 488, "predicted_spam": 734 }, "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": [ [ 1970, 3, 26 ], [ 9, 483, 29 ], [ 19, 2, 679 ] ], "cells": { "true_legitimate": { "pred_legitimate": 1970, "pred_phishing": 3, "pred_spam": 26 }, "true_phishing": { "pred_legitimate": 9, "pred_phishing": 483, "pred_spam": 29 }, "true_spam": { "pred_legitimate": 19, "pred_phishing": 2, "pred_spam": 679 } } }, "accuracy": 0.9726708074534162, "macro_f1": 0.9633747490819639, "macro_f1_present_classes": 0.9633747490819639, "classes_present": [ "Legitimate", "Phishing", "Spam" ], "per_class": { "Legitimate": { "precision": 0.985985985985986, "recall": 0.9854927463731866, "f1": 0.9857393044783588, "support": 1999 }, "Phishing": { "precision": 0.9897540983606558, "recall": 0.927063339731286, "f1": 0.9573835480673935, "support": 521 }, "Spam": { "precision": 0.9250681198910081, "recall": 0.97, "f1": 0.9470013947001394, "support": 700 } }, "argmax_rule": { "doc": "plain argmax over the three probabilities (secondary; can disagree with the binary verdict near the threshold)", "accuracy": 0.9729813664596273, "macro_f1": 0.9636795971999454, "per_class": { "Legitimate": { "precision": 0.9859929964982491, "recall": 0.9859929964982491, "f1": 0.9859929964982491, "support": 1999 }, "Phishing": { "precision": 0.9897540983606558, "recall": 0.927063339731286, "f1": 0.9573835480673935, "support": 521 }, "Spam": { "precision": 0.9263301500682128, "recall": 0.97, "f1": 0.947662247034194, "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": [ [ 489, 32 ], [ 3, 697 ] ], "cells": { "true_phishing": { "pred_phishing": 489, "pred_spam": 32 }, "true_spam": { "pred_phishing": 3, "pred_spam": 697 } }, "accuracy": 0.9713349713349714, "phishing_as_spam": 32, "spam_as_phishing": 3 }, "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": [ [ 9, 483, 29 ], [ 19, 2, 679 ] ], "missed_as_legitimate": { "phishing": 9, "spam": 19 } } }, "per_source": { "Assassin": { "n": 236, "counts": { "Legitimate": 164, "Phishing": 0, "Spam": 72 }, "accuracy": 0.940677966101695, "macro_f1": 0.6219893206089525, "macro_f1_present_classes": 0.9329839809134288, "per_class_recall": { "Legitimate": 0.9573170731707317, "Spam": 0.9027777777777778 } }, "CEAS-08": { "n": 736, "counts": { "Legitimate": 736, "Phishing": 0, "Spam": 0 }, "accuracy": 0.9796195652173914, "macro_f1": 0.3299016243422558, "macro_f1_present_classes": 0.9897048730267674, "per_class_recall": { "Legitimate": 0.9796195652173914 } }, "Enron": { "n": 628, "counts": { "Legitimate": 0, "Phishing": 0, "Spam": 628 }, "accuracy": 0.9777070063694268, "macro_f1": 0.3295759527643585, "macro_f1_present_classes": 0.9887278582930756, "per_class_recall": { "Spam": 0.9777070063694268 } }, "Nazario": { "n": 222, "counts": { "Legitimate": 0, "Phishing": 222, "Spam": 0 }, "accuracy": 0.8963963963963963, "macro_f1": 0.31512272367379257, "macro_f1_present_classes": 0.9453681710213777, "per_class_recall": { "Phishing": 0.8963963963963963 } }, "Nigerian_Fraud": { "n": 299, "counts": { "Legitimate": 0, "Phishing": 299, "Spam": 0 }, "accuracy": 0.9498327759197325, "macro_f1": 0.324757004002287, "macro_f1_present_classes": 0.9742710120068611, "per_class_recall": { "Phishing": 0.9498327759197325 } }, "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": 0.9563636363636364, "metrics": { "threshold": 0.5, "accuracy": 0.9927272727272727, "precision": 1.0, "recall": 0.9925373134328358, "f1": 0.9962546816479401, "specificity": 1.0, "false_positive_rate": 0.0, "false_negative_rate": 0.007462686567164179, "confusion_matrix": { "tn": 7, "fp": 0, "fn": 2, "tp": 266 }, "n": 275, "n_positive": 268, "n_negative": 7, "roc_auc": 1.0 } }, "per_source": { "Assassin": { "threshold": 0.5, "accuracy": 0.9491525423728814, "precision": 0.9054054054054054, "recall": 0.9305555555555556, "f1": 0.9178082191780821, "specificity": 0.9573170731707317, "false_positive_rate": 0.042682926829268296, "false_negative_rate": 0.06944444444444445, "confusion_matrix": { "tn": 157, "fp": 7, "fn": 5, "tp": 67 }, "n": 236, "n_positive": 72, "n_negative": 164, "roc_auc": 0.9881436314363145, "label3_counts": { "legit": 164, "phish": 0, "spam": 72, "unwanted": 0 } }, "CEAS-08": { "threshold": 0.5, "accuracy": 0.9796195652173914, "precision": 0.0, "recall": 0.0, "f1": 0.0, "specificity": 0.9796195652173914, "false_positive_rate": 0.020380434782608696, "false_negative_rate": 0.0, "confusion_matrix": { "tn": 721, "fp": 15, "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": 0.9777070063694268, "precision": 1.0, "recall": 0.9777070063694268, "f1": 0.9887278582930756, "specificity": 0.0, "false_positive_rate": 0.0, "false_negative_rate": 0.022292993630573247, "confusion_matrix": { "tn": 0, "fp": 0, "fn": 14, "tp": 614 }, "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": 0.9684684684684685, "precision": 1.0, "recall": 0.9684684684684685, "f1": 0.9839816933638443, "specificity": 0.0, "false_positive_rate": 0.0, "false_negative_rate": 0.03153153153153153, "confusion_matrix": { "tn": 0, "fp": 0, "fn": 7, "tp": 215 }, "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": 0.9933110367892977, "precision": 1.0, "recall": 0.9933110367892977, "f1": 0.9966442953020134, "specificity": 0.0, "false_positive_rate": 0.0, "false_negative_rate": 0.006688963210702341, "confusion_matrix": { "tn": 0, "fp": 0, "fn": 2, "tp": 297 }, "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": 1193, "mean_tokens_full": 614.9, "mean_tokens_fed": 279.6, "median_tokens_full": 243.0, "pct_truncated": 26.4 }, "tn": { "n": 1970, "mean_tokens_full": 733.2, "mean_tokens_fed": 358.4, "median_tokens_full": 392.5, "pct_truncated": 38.3 }, "fp": { "n": 29, "mean_tokens_full": 1182.1, "mean_tokens_fed": 368.0, "median_tokens_full": 462.0, "pct_truncated": 48.3 }, "fn": { "n": 28, "mean_tokens_full": 17044.3, "mean_tokens_fed": 291.4, "median_tokens_full": 291.0, "pct_truncated": 39.3 }, "correct": { "n": 3163, "mean_tokens_full": 688.5, "mean_tokens_fed": 328.7, "median_tokens_full": 338.0, "pct_truncated": 33.8 }, "wrong": { "n": 57, "mean_tokens_full": 8974.1, "mean_tokens_fed": 330.4, "median_tokens_full": 368.0, "pct_truncated": 43.9 } }, "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": 0.9191919191919192, "fpr": 0.06666666666666667, "accuracy": 0.9224806201550387 }, { "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": 0.9891304347826086, "fpr": 0.01182033096926714, "accuracy": 0.9885550786838341 }, { "bucket": "257-512", "n": 870, "n_positive": 268, "positive_rate": 0.3080459770114943, "recall": 0.9850746268656716, "fpr": 0.009966777408637873, "accuracy": 0.9885057471264368 }, { "bucket": ">512", "n": 1095, "n_positive": 326, "positive_rate": 0.29771689497716897, "recall": 0.9662576687116564, "fpr": 0.018205461638491547, "accuracy": 0.9771689497716894 } ] }, "inference": { "device": "cuda", "autocast_bf16": true, "batch_size": 64, "pad_to_multiple_of": 8, "num_labels": 3, "rows": 3220, "seconds": 13.56, "rows_per_s": 237.5, "padded_tokens": 1079936, "real_tokens": 1058490, "padded_tokens_per_s": 79640, "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": 10.06, "p50_ms": 8.92, "p95_ms": 13.84, "max_ms": 18.98, "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": 354.05, "p50_ms": 338.14, "p95_ms": 554.84, "max_ms": 606.24, "avg_s": 0.3541, "mean_tokens": 280.0, "ratio_to_benchmark": 4.784, "threads": 16, "estimated_full_run_s": 37.1 }, "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-scratch/best", "run_name": "ft-scratch", "params": 337444867, "timestamp": "2026-10-09 09:57", "num_labels": 3, "measured_once_for_splits": [ "test", "test3" ] }, "error_analysis": { "path": "reports/eval_ft-scratch/error_analysis_test3.md", "n_fn": 28, "n_fp": 29, "composition": { "fp": { "n": 29, "mailing_list_or_digest": 0.586, "html_heavy": 0.0, "very_short_lt20_tokens": 0.0, "truncated_gt512": 0.483, "lure_phrase": 0.0 }, "tn": { "n": 1970, "mailing_list_or_digest": 0.562, "html_heavy": 0.0, "very_short_lt20_tokens": 0.0, "truncated_gt512": 0.383, "lure_phrase": 0.004 }, "fn": { "n": 28, "mailing_list_or_digest": 0.25, "html_heavy": 0.0, "very_short_lt20_tokens": 0.107, "truncated_gt512": 0.393, "lure_phrase": 0.071 }, "tp": { "n": 1193, "mailing_list_or_digest": 0.083, "html_heavy": 0.0, "very_short_lt20_tokens": 0.005, "truncated_gt512": 0.264, "lure_phrase": 0.223 } }, "fn_vs_tp_tokens": [ { "token": "hoovers", "share_a": 0.107, "share_b": 0.0, "ratio": 293.14 }, { "token": "jason", "share_a": 0.107, "share_b": 0.0, "ratio": 293.14 }, { "token": "columbia", "share_a": 0.107, "share_b": 0.0, "ratio": 293.14 }, { "token": "chin", "share_a": 0.107, "share_b": 0.001, "ratio": 97.71 }, { "token": "simpson", "share_a": 0.107, "share_b": 0.001, "ratio": 97.71 }, { "token": "joe", "share_a": 0.107, "share_b": 0.001, "ratio": 97.71 }, { "token": "miami", "share_a": 0.107, "share_b": 0.001, "ratio": 97.71 }, { "token": "jennifer", "share_a": 0.107, "share_b": 0.001, "ratio": 97.71 }, { "token": "streams", "share_a": 0.143, "share_b": 0.002, "ratio": 75.38 }, { "token": "publishing", "share_a": 0.107, "share_b": 0.002, "ratio": 58.63 }, { "token": "cut", "share_a": 0.107, "share_b": 0.002, "ratio": 58.63 }, { "token": "economy", "share_a": 0.107, "share_b": 0.002, "ratio": 58.63 }, { "token": "zzzz", "share_a": 0.143, "share_b": 0.003, "ratio": 53.84 }, { "token": "invite", "share_a": 0.143, "share_b": 0.003, "ratio": 53.84 }, { "token": "event", "share_a": 0.179, "share_b": 0.004, "ratio": 41.88 }, { "token": "club", "share_a": 0.143, "share_b": 0.003, "ratio": 41.88 }, { "token": "tables", "share_a": 0.107, "share_b": 0.003, "ratio": 41.88 }, { "token": "comments", "share_a": 0.107, "share_b": 0.003, "ratio": 41.88 }, { "token": "environment", "share_a": 0.143, "share_b": 0.004, "ratio": 34.26 }, { "token": "url", "share_a": 0.143, "share_b": 0.004, "ratio": 34.26 } ], "fp_vs_tn_tokens": [ { "token": "promotional", "share_a": 0.138, "share_b": 0.001, "ratio": 200.39 }, { "token": "cook", "share_a": 0.103, "share_b": 0.001, "ratio": 93.52 }, { "token": "mill", "share_a": 0.103, "share_b": 0.001, "ratio": 93.52 }, { "token": "palm", "share_a": 0.103, "share_b": 0.002, "ratio": 66.8 }, { "token": "full-color", "share_a": 0.138, "share_b": 0.003, "ratio": 54.65 }, { "token": "rock", "share_a": 0.103, "share_b": 0.003, "ratio": 35.97 }, { "token": "gift", "share_a": 0.138, "share_b": 0.004, "ratio": 35.36 }, { "token": "frequently", "share_a": 0.103, "share_b": 0.004, "ratio": 31.17 }, { "token": "funny", "share_a": 0.103, "share_b": 0.004, "ratio": 31.17 }, { "token": "editors", "share_a": 0.103, "share_b": 0.004, "ratio": 31.17 }, { "token": "classic", "share_a": 0.103, "share_b": 0.004, "ratio": 27.5 }, { "token": "multi-part", "share_a": 0.138, "share_b": 0.006, "ratio": 26.14 }, { "token": "draw", "share_a": 0.103, "share_b": 0.005, "ratio": 24.61 }, { "token": "viewing", "share_a": 0.138, "share_b": 0.006, "ratio": 24.05 }, { "token": "powered", "share_a": 0.138, "share_b": 0.006, "ratio": 24.05 }, { "token": "deals", "share_a": 0.103, "share_b": 0.005, "ratio": 22.27 }, { "token": "serves", "share_a": 0.103, "share_b": 0.005, "ratio": 22.27 }, { "token": "guaranteed", "share_a": 0.103, "share_b": 0.005, "ratio": 22.27 }, { "token": "content-transfer-encoding", "share_a": 0.138, "share_b": 0.007, "ratio": 20.73 }, { "token": "content-disposition", "share_a": 0.103, "share_b": 0.006, "ratio": 20.33 } ], "top_fn_doc_ids": [ "primary:148887", "aura:Nazario:000097", "primary:181246", "primary:025244", "aura:Nazario:000551", "primary:148857", "primary:173930", "aura:Nazario:000643", "primary:007176", "aura:Nazario:000533", "primary:001939", "aura:Nazario:001540", "primary:129677", "primary:135631", "aura:Nigerian_Fraud:001032", "primary:046569", "primary:014300", "aura:Nazario:000299", "primary:181468", "primary:130516", "primary:164494", "primary:201972", "aura:Nazario:001468", "primary:157116", "primary:048857" ], "top_fp_doc_ids": [ "primary:156887", "primary:118434", "primary:188362", "primary:066021", "primary:199386", "primary:048756", "primary:109226", "primary:130385", "primary:027029", "primary:144048", "primary:200749", "primary:057514", "primary:152763", "primary:025142", "primary:153841", "primary:165228", "primary:024251", "primary:101377", "primary:021911", "primary:061178", "primary:012585", "primary:128544", "primary:103927", "primary:159406", "primary:059404" ], "threeway": { "n_phish_as_spam": 29, "n_spam_as_phish": 2, "top_phish_as_spam_doc_ids": [ "aura:Nazario:000401", "aura:Nazario:000832", "aura:Nigerian_Fraud:000262", "aura:Nigerian_Fraud:000824", "aura:Nazario:000328", "aura:Nigerian_Fraud:003000", "aura:Nigerian_Fraud:000266", "aura:Nigerian_Fraud:000337", "aura:Nazario:000946", "aura:Nigerian_Fraud:003049", "aura:Nazario:000105", "aura:Nazario:001179", "aura:Nazario:001170", "aura:Nazario:000214", "aura:Nazario:000879", "aura:Nazario:000104", "aura:Nazario:001290", "aura:Nigerian_Fraud:001100", "aura:Nigerian_Fraud:000101", "aura:Nazario:001287", "aura:Nigerian_Fraud:001783", "aura:Nigerian_Fraud:002955", "aura:Nazario:000020", "aura:Nazario:000426", "aura:Nigerian_Fraud:001698" ], "top_spam_as_phish_doc_ids": [ "primary:077835", "primary:197304" ], "phish_as_spam_tokens": [ { "token": "whatsapp", "share_a": 0.103, "share_b": 0.0, "ratio": 114.73 }, { "token": "nova", "share_a": 0.103, "share_b": 0.0, "ratio": 114.73 }, { "token": "abra", "share_a": 0.103, "share_b": 0.0, "ratio": 114.73 }, { "token": "content-type", "share_a": 0.103, "share_b": 0.0, "ratio": 114.73 }, { "token": "content-transfer-encoding", "share_a": 0.103, "share_b": 0.0, "ratio": 114.73 }, { "token": "para", "share_a": 0.138, "share_b": 0.002, "ratio": 49.17 }, { "token": "removed", "share_a": 0.172, "share_b": 0.004, "ratio": 36.06 }, { "token": "income", "share_a": 0.138, "share_b": 0.006, "ratio": 21.07 }, { "token": "los", "share_a": 0.103, "share_b": 0.006, "ratio": 16.39 }, { "token": "building", "share_a": 0.103, "share_b": 0.008, "ratio": 12.75 }, { "token": "plain", "share_a": 0.138, "share_b": 0.012, "ratio": 11.35 }, { "token": "disclaimer", "share_a": 0.103, "share_b": 0.01, "ratio": 10.43 }, { "token": "bit", "share_a": 0.103, "share_b": 0.012, "ratio": 8.83 }, { "token": "fill", "share_a": 0.103, "share_b": 0.012, "ratio": 8.83 }, { "token": "plus", "share_a": 0.103, "share_b": 0.012, "ratio": 8.83 }, { "token": "register", "share_a": 0.103, "share_b": 0.012, "ratio": 8.83 }, { "token": "return", "share_a": 0.138, "share_b": 0.017, "ratio": 8.68 }, { "token": "text", "share_a": 0.138, "share_b": 0.017, "ratio": 8.68 }, { "token": "plan", "share_a": 0.138, "share_b": 0.019, "ratio": 7.76 }, { "token": "links", "share_a": 0.103, "share_b": 0.014, "ratio": 7.65 } ], "spam_as_phish_tokens": [] } }, "plots": { "confusion_matrix": "reports/eval_ft-scratch/confusion_matrix_test3.png", "confusion_matrix3": "reports/eval_ft-scratch/confusion_matrix3_test3.png", "roc_curve": "reports/eval_ft-scratch/roc_curve_test3.png", "pr_curve": "reports/eval_ft-scratch/pr_curve_test3.png" } }