Download presentation/reports/eval_ft-weighted/metrics.json from BuildITSystems/phishing-detector-encoder: direct link, hf CLI and curl.
- Browser
- Download file 27.2 kB
-
https://huggingface.co/BuildITSystems/phishing-detector-encoder/resolve/main/presentation/reports/eval_ft-weighted/metrics.json
- Command line
-
hf download hf://BuildITSystems/phishing-detector-encoder/presentation/reports/eval_ft-weighted/metrics.json
-
curl -L -o metrics.json https://huggingface.co/BuildITSystems/phishing-detector-encoder/resolve/main/presentation/reports/eval_ft-weighted/metrics.json
27.2 kB
| { | |
| "timestamp": "2026-10-09 05:55", | |
| "run_name": "ft-weighted", | |
| "split": "test", | |
| "split_file": "/home/nathank/BITS/dev/Phishing Model/data/processed/test_holdout.parquet", | |
| "split_title": "TREC-06 binary holdout", | |
| "limit_rows": null, | |
| "dev_run": false, | |
| "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-weighted/best", | |
| "splits_in_invocation": [ | |
| "test", | |
| "test3" | |
| ], | |
| "model_config": { | |
| "vocab_size": 32768, | |
| "max_seq_len": 512, | |
| "d_model": 1024, | |
| "n_layers": 24, | |
| "n_heads": 16, | |
| "d_ff": 4096, | |
| "dropout": 0.1, | |
| "attention_dropout": 0.1, | |
| "layer_norm_eps": 1e-05, | |
| "pad_token_id": 0, | |
| "tie_mlm_head": true, | |
| "grad_checkpointing": false, | |
| "num_labels": 3 | |
| }, | |
| "num_labels": 3, | |
| "params": 337444867, | |
| "checkpoint_config": { | |
| "tokenizer": "tokenizer.json", | |
| "finetune": { | |
| "run_name": "ft-weighted", | |
| "init": "pretrained:checkpoints/pretrain/large-24L/final", | |
| "n_layers": 24, | |
| "freeze_layers": 0, | |
| "loss": "weighted_cross_entropy", | |
| "focal_gamma": 2.0, | |
| "lr": 3e-05, | |
| "batch_size": 32, | |
| "micro_batch": 16, | |
| "epochs": 2, | |
| "max_steps": null, | |
| "eval_every": 1250, | |
| "log_every": 20, | |
| "eval_batch_size": 64, | |
| "warmup_fraction": 0.06, | |
| "weight_decay": 0.01, | |
| "betas": [ | |
| 0.9, | |
| 0.98 | |
| ], | |
| "eps": 1e-06, | |
| "grad_clip": 1.0, | |
| "patience": 2, | |
| "schedule": "linear_decay", | |
| "selection_metric": "val_f1_unwanted", | |
| "pooling": "cls", | |
| "num_labels": 3, | |
| "synthetic": "off", | |
| "limit_rows": null, | |
| "seed": 42, | |
| "cpu": false | |
| }, | |
| "best_epoch": 1, | |
| "best_step": 10000, | |
| "num_labels": 3, | |
| "label_names": [ | |
| "Legitimate", | |
| "Phishing", | |
| "Spam" | |
| ], | |
| "binary_rollup_name": "Unwanted (phishing or spam)", | |
| "selection_metric": "val_f1_unwanted", | |
| "selection_value": 0.99373795761079, | |
| "val_metrics": { | |
| "accuracy": 0.9931954985605862, | |
| "precision": 0.9911121787172712, | |
| "recall": 0.9963776865491427, | |
| "f1": 0.99373795761079, | |
| "roc_auc": 0.9997532357160727, | |
| "pr_auc": 0.9997920087331971, | |
| "tn": 6928, | |
| "fp": 74, | |
| "fn": 30, | |
| "tp": 8252, | |
| "threshold": 0.5, | |
| "f1_optimal_threshold": 0.8991281390190125, | |
| "f1_at_optimal_threshold": 0.9942622455758894, | |
| "f1_unwanted": 0.99373795761079, | |
| "n_3way": 8105, | |
| "accuracy_3way": 0.9902529302899444, | |
| "macro_f1_3way": 0.9774841428658321, | |
| "precision_legitimate": 0.9992789154888952, | |
| "recall_legitimate": 0.9895744073121965, | |
| "f1_legitimate": 0.9944029850746269, | |
| "precision_phishing": 0.9630681818181818, | |
| "recall_phishing": 0.9970588235294118, | |
| "f1_phishing": 0.9797687861271677, | |
| "precision_spam": 0.9255189255189256, | |
| "recall_spam": 0.9934469200524246, | |
| "f1_spam": 0.9582806573957017, | |
| "cm3_ll": 6929, | |
| "cm3_lp": 12, | |
| "cm3_ls": 61, | |
| "cm3_pl": 1, | |
| "cm3_pp": 339, | |
| "cm3_ps": 0, | |
| "cm3_sl": 4, | |
| "cm3_sp": 1, | |
| "cm3_ss": 758, | |
| "n_unwanted_3way": 1103, | |
| "pvs_phish_as_phish": 339, | |
| "pvs_phish_as_spam": 1, | |
| "pvs_spam_as_phish": 2, | |
| "pvs_spam_as_spam": 761, | |
| "val_loss": 0.025379083498832725, | |
| "n": 15284, | |
| "eval_seconds": 47.8 | |
| }, | |
| "val_metric_sets": { | |
| "binary_unwanted": { | |
| "accuracy": 0.9931954985605862, | |
| "precision": 0.9911121787172712, | |
| "recall": 0.9963776865491427, | |
| "f1": 0.99373795761079, | |
| "roc_auc": 0.9997532357160727, | |
| "pr_auc": 0.9997920087331971, | |
| "tn": 6928, | |
| "fp": 74, | |
| "fn": 30, | |
| "tp": 8252, | |
| "threshold": 0.5, | |
| "f1_optimal_threshold": 0.8991281390190125, | |
| "f1_at_optimal_threshold": 0.9942622455758894, | |
| "n": 15284, | |
| "positive_class": "Unwanted (phishing or spam)" | |
| }, | |
| "three_way": { | |
| "n": 8105, | |
| "accuracy": 0.9902529302899444, | |
| "macro_f1": 0.9774841428658321, | |
| "per_class": { | |
| "Legitimate": { | |
| "precision": 0.9992789154888952, | |
| "recall": 0.9895744073121965, | |
| "f1": 0.9944029850746269 | |
| }, | |
| "Phishing": { | |
| "precision": 0.9630681818181818, | |
| "recall": 0.9970588235294118, | |
| "f1": 0.9797687861271677 | |
| }, | |
| "Spam": { | |
| "precision": 0.9255189255189256, | |
| "recall": 0.9934469200524246, | |
| "f1": 0.9582806573957017 | |
| } | |
| }, | |
| "confusion": { | |
| "order": [ | |
| "Legitimate", | |
| "Phishing", | |
| "Spam" | |
| ], | |
| "rows_true_cols_pred": [ | |
| [ | |
| 6929, | |
| 12, | |
| 61 | |
| ], | |
| [ | |
| 1, | |
| 339, | |
| 0 | |
| ], | |
| [ | |
| 4, | |
| 1, | |
| 758 | |
| ] | |
| ] | |
| }, | |
| "phish_vs_spam_on_true_unwanted": { | |
| "n": 1103, | |
| "order": [ | |
| "Phishing", | |
| "Spam" | |
| ], | |
| "rows_true_cols_pred": [ | |
| [ | |
| 339, | |
| 1 | |
| ], | |
| [ | |
| 2, | |
| 761 | |
| ] | |
| ] | |
| } | |
| } | |
| }, | |
| "thresholds": { | |
| "decision": 0.5, | |
| "decision_applies_to": "P(unwanted) = sum of non-legitimate probabilities", | |
| "val_f1_optimal": 0.8991281390190125, | |
| "val_f1_at_optimal": 0.9942622455758894 | |
| }, | |
| "init": "pretrained:/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final", | |
| "params": { | |
| "total": 337444867, | |
| "trainable": 337444867, | |
| "embeddings": 34080768, | |
| "encoder_layers": 302309376, | |
| "final_norm": 2048, | |
| "head": 1052675 | |
| } | |
| }, | |
| "tokenizer": "/home/nathank/BITS/dev/Phishing Model/data/processed/tokenizer.json", | |
| "max_len": 512, | |
| "label_names": { | |
| "0": "Legitimate", | |
| "1": "Phishing", | |
| "2": "Spam" | |
| }, | |
| "binary_rollup": { | |
| "unwanted_name": "Unwanted (phishing or spam)", | |
| "classes": [ | |
| 1, | |
| 2 | |
| ], | |
| "rule": "P(unwanted) = sum of P(class) for class >= 1; flag when >= threshold" | |
| }, | |
| "split_sizes": { | |
| "rows": 16302, | |
| "positive": 3894, | |
| "negative": 12408, | |
| "positive_rate": 0.2389, | |
| "label3": { | |
| "legit": 12408, | |
| "phish": 0, | |
| "spam": 0, | |
| "unwanted": 3894 | |
| }, | |
| "by_source": { | |
| "TREC-06": { | |
| "rows": 16302, | |
| "positive": 3894, | |
| "label3": { | |
| "legit": 12408, | |
| "phish": 0, | |
| "spam": 0, | |
| "unwanted": 3894 | |
| } | |
| } | |
| }, | |
| "mean_tokens_full": 710.6, | |
| "pct_truncated": 21.93 | |
| }, | |
| "threshold": 0.5, | |
| "at_threshold": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9478591583854742, | |
| "precision": 0.8307257714037375, | |
| "recall": 0.9817668207498716, | |
| "f1": 0.8999529190207156, | |
| "specificity": 0.9372179239200515, | |
| "false_positive_rate": 0.06278207607994842, | |
| "false_negative_rate": 0.018233179250128403, | |
| "confusion_matrix": { | |
| "tn": 11629, | |
| "fp": 779, | |
| "fn": 71, | |
| "tp": 3823 | |
| }, | |
| "n": 16302, | |
| "n_positive": 3894, | |
| "n_negative": 12408 | |
| }, | |
| "threshold_free": { | |
| "roc_auc": 0.9942507931824557, | |
| "pr_auc": 0.9832765259772845, | |
| "recall_at_fpr_1pct": { | |
| "fpr_budget": 0.01, | |
| "recall": 0.8767334360554699, | |
| "fpr": 0.009912959381044487, | |
| "threshold": 0.9987348318099976, | |
| "threshold_rule": "flag when p >= threshold" | |
| }, | |
| "recall_at_fpr_0_1pct": { | |
| "fpr_budget": 0.001, | |
| "recall": 0.6335387776065742, | |
| "fpr": 0.0009671179883945841, | |
| "threshold": 0.9999274015426636, | |
| "threshold_rule": "flag when p >= threshold" | |
| }, | |
| "best_f1": { | |
| "threshold": 0.9889976382255554, | |
| "f1": 0.938343949044586, | |
| "precision": 0.9309908998988877, | |
| "recall": 0.945814072932717 | |
| } | |
| }, | |
| "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": 12408, | |
| "phish": 0, | |
| "spam": 0, | |
| "unwanted": 3894 | |
| }, | |
| "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": 3823, | |
| "predicted_phishing": 801, | |
| "predicted_spam": 3022 | |
| }, | |
| "false_positives_flagged": { | |
| "n": 779, | |
| "predicted_phishing": 302, | |
| "predicted_spam": 477 | |
| }, | |
| "missed_positives": { | |
| "n": 71, | |
| "predicted_phishing": 17, | |
| "predicted_spam": 54 | |
| }, | |
| "all_flagged": { | |
| "n": 4602, | |
| "predicted_phishing": 1103, | |
| "predicted_spam": 3499 | |
| }, | |
| "unsplit_unwanted_rows_flagged": { | |
| "n": 3823, | |
| "predicted_phishing": 801, | |
| "predicted_spam": 3022 | |
| } | |
| }, | |
| "rows_with_full_label": 12408, | |
| "rows_unwanted_only": 3894, | |
| "evaluated": false, | |
| "reason": "no rows labelled phishing or spam: every positive is unwanted-but-unsplit (no phishing-vs-spam ground truth)" | |
| }, | |
| "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": 129, | |
| "bank account": 78, | |
| "security alert": 70, | |
| "within 24 hours": 65, | |
| "urgently": 51, | |
| "paypal account": 20, | |
| "within 48 hours": 7, | |
| "verify your account": 7, | |
| "update your account": 6, | |
| "account will be suspended": 5, | |
| "ebay account": 5, | |
| "enter your password": 5, | |
| "wire transfer": 5, | |
| "unusual activity": 5, | |
| "confirm your identity": 4, | |
| "verify your identity": 4, | |
| "click here to verify": 3, | |
| "log in to your account": 2, | |
| "confirm your account": 2, | |
| "security notice": 1, | |
| "gift card": 1, | |
| "reset your password": 1, | |
| "account has been locked": 1, | |
| "update your information": 1, | |
| "account has been limited": 1, | |
| "login to your account": 1 | |
| }, | |
| "phrase_hits_by_label": { | |
| "verify your account": { | |
| "positive": 7, | |
| "negative": 0 | |
| }, | |
| "verify your identity": { | |
| "positive": 4, | |
| "negative": 0 | |
| }, | |
| "confirm your identity": { | |
| "positive": 4, | |
| "negative": 0 | |
| }, | |
| "confirm your account": { | |
| "positive": 2, | |
| "negative": 0 | |
| }, | |
| "enter your password": { | |
| "positive": 5, | |
| "negative": 0 | |
| }, | |
| "update your account": { | |
| "positive": 6, | |
| "negative": 0 | |
| }, | |
| "update your information": { | |
| "positive": 0, | |
| "negative": 1 | |
| }, | |
| "click here to verify": { | |
| "positive": 3, | |
| "negative": 0 | |
| }, | |
| "account has been limited": { | |
| "positive": 1, | |
| "negative": 0 | |
| }, | |
| "account will be suspended": { | |
| "positive": 4, | |
| "negative": 1 | |
| }, | |
| "account has been locked": { | |
| "positive": 1, | |
| "negative": 0 | |
| }, | |
| "unusual activity": { | |
| "positive": 2, | |
| "negative": 3 | |
| }, | |
| "paypal account": { | |
| "positive": 20, | |
| "negative": 0 | |
| }, | |
| "ebay account": { | |
| "positive": 5, | |
| "negative": 0 | |
| }, | |
| "reset your password": { | |
| "positive": 0, | |
| "negative": 1 | |
| }, | |
| "wire transfer": { | |
| "positive": 5, | |
| "negative": 0 | |
| }, | |
| "gift card": { | |
| "positive": 0, | |
| "negative": 1 | |
| }, | |
| "urgent": { | |
| "positive": 81, | |
| "negative": 48 | |
| }, | |
| "urgently": { | |
| "positive": 22, | |
| "negative": 29 | |
| }, | |
| "security alert": { | |
| "positive": 2, | |
| "negative": 68 | |
| }, | |
| "security notice": { | |
| "positive": 1, | |
| "negative": 0 | |
| }, | |
| "login to your account": { | |
| "positive": 1, | |
| "negative": 0 | |
| }, | |
| "log in to your account": { | |
| "positive": 2, | |
| "negative": 0 | |
| }, | |
| "bank account": { | |
| "positive": 71, | |
| "negative": 7 | |
| }, | |
| "within 24 hours": { | |
| "positive": 63, | |
| "negative": 2 | |
| }, | |
| "within 48 hours": { | |
| "positive": 4, | |
| "negative": 3 | |
| } | |
| }, | |
| "label_purity": 0.6106, | |
| "min_positives_for_comparison": 20, | |
| "label3_counts": { | |
| "legit": 155, | |
| "phish": 0, | |
| "spam": 0, | |
| "unwanted": 243 | |
| }, | |
| "threeway_accuracy": null, | |
| "metrics": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9698492462311558, | |
| "precision": 0.9565217391304348, | |
| "recall": 0.9958847736625515, | |
| "f1": 0.9758064516129034, | |
| "specificity": 0.9290322580645162, | |
| "false_positive_rate": 0.07096774193548387, | |
| "false_negative_rate": 0.00411522633744856, | |
| "confusion_matrix": { | |
| "tn": 144, | |
| "fp": 11, | |
| "fn": 1, | |
| "tp": 242 | |
| }, | |
| "n": 398, | |
| "n_positive": 243, | |
| "n_negative": 155, | |
| "roc_auc": 0.996973317403425 | |
| } | |
| }, | |
| "per_source": { | |
| "TREC-06": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9478591583854742, | |
| "precision": 0.8307257714037375, | |
| "recall": 0.9817668207498716, | |
| "f1": 0.8999529190207156, | |
| "specificity": 0.9372179239200515, | |
| "false_positive_rate": 0.06278207607994842, | |
| "false_negative_rate": 0.018233179250128403, | |
| "confusion_matrix": { | |
| "tn": 11629, | |
| "fp": 779, | |
| "fn": 71, | |
| "tp": 3823 | |
| }, | |
| "n": 16302, | |
| "n_positive": 3894, | |
| "n_negative": 12408, | |
| "roc_auc": 0.9942507931824557, | |
| "label3_counts": { | |
| "legit": 12408, | |
| "phish": 0, | |
| "spam": 0, | |
| "unwanted": 3894 | |
| } | |
| } | |
| }, | |
| "length_confound": { | |
| "by_outcome": { | |
| "tp": { | |
| "n": 3823, | |
| "mean_tokens_full": 284.4, | |
| "mean_tokens_fed": 232.2, | |
| "median_tokens_full": 207.0, | |
| "pct_truncated": 15.3 | |
| }, | |
| "tn": { | |
| "n": 11629, | |
| "mean_tokens_full": 781.6, | |
| "mean_tokens_fed": 294.6, | |
| "median_tokens_full": 269.0, | |
| "pct_truncated": 23.6 | |
| }, | |
| "fp": { | |
| "n": 779, | |
| "mean_tokens_full": 1778.7, | |
| "mean_tokens_fed": 280.1, | |
| "median_tokens_full": 256.0, | |
| "pct_truncated": 30.8 | |
| }, | |
| "fn": { | |
| "n": 71, | |
| "mean_tokens_full": 309.8, | |
| "mean_tokens_fed": 215.2, | |
| "median_tokens_full": 181.0, | |
| "pct_truncated": 15.5 | |
| }, | |
| "correct": { | |
| "n": 15452, | |
| "mean_tokens_full": 658.6, | |
| "mean_tokens_fed": 279.1, | |
| "median_tokens_full": 246.0, | |
| "pct_truncated": 21.5 | |
| }, | |
| "wrong": { | |
| "n": 850, | |
| "mean_tokens_full": 1656.0, | |
| "mean_tokens_fed": 274.7, | |
| "median_tokens_full": 229.5, | |
| "pct_truncated": 29.5 | |
| } | |
| }, | |
| "by_label": { | |
| "legitimate": { | |
| "n": 12408, | |
| "mean_tokens_full": 844.2, | |
| "mean_tokens_fed": 293.7, | |
| "median_tokens_full": 268.0, | |
| "pct_truncated": 24.0 | |
| }, | |
| "unwanted": { | |
| "n": 3894, | |
| "mean_tokens_full": 284.9, | |
| "mean_tokens_fed": 231.9, | |
| "median_tokens_full": 206.0, | |
| "pct_truncated": 15.3 | |
| } | |
| }, | |
| "by_class3": { | |
| "legit": { | |
| "n": 12408, | |
| "mean_tokens_full": 844.2, | |
| "mean_tokens_fed": 293.7, | |
| "median_tokens_full": 268.0, | |
| "pct_truncated": 24.0 | |
| }, | |
| "unwanted": { | |
| "n": 3894, | |
| "mean_tokens_full": 284.9, | |
| "mean_tokens_fed": 231.9, | |
| "median_tokens_full": 206.0, | |
| "pct_truncated": 15.3 | |
| } | |
| }, | |
| "by_length_bucket": [ | |
| { | |
| "bucket": "<=64", | |
| "n": 1363, | |
| "n_positive": 587, | |
| "positive_rate": 0.43066764490095377, | |
| "recall": 0.9863713798977853, | |
| "fpr": 0.17525773195876287, | |
| "accuracy": 0.8943506969919296 | |
| }, | |
| { | |
| "bucket": "65-128", | |
| "n": 2538, | |
| "n_positive": 736, | |
| "positive_rate": 0.2899921197793538, | |
| "recall": 0.96875, | |
| "fpr": 0.06714761376248612, | |
| "accuracy": 0.9432624113475178 | |
| }, | |
| { | |
| "bucket": "129-256", | |
| "n": 4594, | |
| "n_positive": 1196, | |
| "positive_rate": 0.260339573356552, | |
| "recall": 0.9816053511705686, | |
| "fpr": 0.039140670982931135, | |
| "accuracy": 0.9662603395733566 | |
| }, | |
| { | |
| "bucket": "257-512", | |
| "n": 4232, | |
| "n_positive": 780, | |
| "positive_rate": 0.1843100189035917, | |
| "recall": 0.9910256410256411, | |
| "fpr": 0.04316338354577057, | |
| "accuracy": 0.9631379962192816 | |
| }, | |
| { | |
| "bucket": ">512", | |
| "n": 3575, | |
| "n_positive": 595, | |
| "positive_rate": 0.16643356643356644, | |
| "recall": 0.9815126050420168, | |
| "fpr": 0.08053691275167785, | |
| "accuracy": 0.9297902097902098 | |
| } | |
| ] | |
| }, | |
| "inference": { | |
| "device": "cuda", | |
| "autocast_bf16": true, | |
| "batch_size": 64, | |
| "pad_to_multiple_of": 8, | |
| "num_labels": 3, | |
| "rows": 16302, | |
| "seconds": 57.53, | |
| "rows_per_s": 283.4, | |
| "padded_tokens": 4606544, | |
| "real_tokens": 4546874, | |
| "padded_tokens_per_s": 80074, | |
| "peak_vram_gb": 2.27 | |
| }, | |
| "latency": { | |
| "instructor_benchmark_ms": 74.0, | |
| "samples_requested": 100, | |
| "sample_split": "test", | |
| "max_len": 512, | |
| "gpu_bf16": { | |
| "n": 100, | |
| "avg_ms": 10.12, | |
| "p50_ms": 8.95, | |
| "p95_ms": 13.37, | |
| "max_ms": 19.01, | |
| "avg_s": 0.0101, | |
| "mean_tokens": 280.0, | |
| "ratio_to_benchmark": 0.137, | |
| "device": "NVIDIA GeForce RTX 3090 Ti" | |
| }, | |
| "cpu_fp32": { | |
| "n": 100, | |
| "avg_ms": 411.57, | |
| "p50_ms": 397.57, | |
| "p95_ms": 630.3, | |
| "max_ms": 674.98, | |
| "avg_s": 0.4116, | |
| "mean_tokens": 280.0, | |
| "ratio_to_benchmark": 5.562, | |
| "threads": 16, | |
| "estimated_full_run_s": 38.4 | |
| }, | |
| "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-weighted/best", | |
| "run_name": "ft-weighted", | |
| "params": 337444867, | |
| "timestamp": "2026-10-09 05:55", | |
| "num_labels": 3, | |
| "measured_once_for_splits": [ | |
| "test", | |
| "test3" | |
| ] | |
| }, | |
| "error_analysis": { | |
| "path": "reports/eval_ft-weighted/error_analysis.md", | |
| "n_fn": 71, | |
| "n_fp": 779, | |
| "composition": { | |
| "fp": { | |
| "n": 779, | |
| "mailing_list_or_digest": 0.225, | |
| "html_heavy": 0.001, | |
| "very_short_lt20_tokens": 0.026, | |
| "truncated_gt512": 0.308, | |
| "lure_phrase": 0.014 | |
| }, | |
| "tn": { | |
| "n": 11629, | |
| "mailing_list_or_digest": 0.297, | |
| "html_heavy": 0.002, | |
| "very_short_lt20_tokens": 0.004, | |
| "truncated_gt512": 0.236, | |
| "lure_phrase": 0.012 | |
| }, | |
| "fn": { | |
| "n": 71, | |
| "mailing_list_or_digest": 0.056, | |
| "html_heavy": 0.0, | |
| "very_short_lt20_tokens": 0.0, | |
| "truncated_gt512": 0.155, | |
| "lure_phrase": 0.014 | |
| }, | |
| "tp": { | |
| "n": 3823, | |
| "mailing_list_or_digest": 0.029, | |
| "html_heavy": 0.001, | |
| "very_short_lt20_tokens": 0.002, | |
| "truncated_gt512": 0.153, | |
| "lure_phrase": 0.063 | |
| } | |
| }, | |
| "fn_vs_tp_tokens": [ | |
| { | |
| "token": "blocki", | |
| "share_a": 0.169, | |
| "share_b": 0.0, | |
| "ratio": 1336.89 | |
| }, | |
| { | |
| "token": "scanmail", | |
| "share_a": 0.169, | |
| "share_b": 0.0, | |
| "ratio": 1336.89 | |
| }, | |
| { | |
| "token": "smailex", | |
| "share_a": 0.169, | |
| "share_b": 0.0, | |
| "ratio": 1336.89 | |
| }, | |
| { | |
| "token": "progra", | |
| "share_a": 0.169, | |
| "share_b": 0.0, | |
| "ratio": 1336.89 | |
| }, | |
| { | |
| "token": "scanning", | |
| "share_a": 0.169, | |
| "share_b": 0.0, | |
| "ratio": 1336.89 | |
| }, | |
| { | |
| "token": "matched", | |
| "share_a": 0.169, | |
| "share_b": 0.0, | |
| "ratio": 445.63 | |
| }, | |
| { | |
| "token": "kool", | |
| "share_a": 0.042, | |
| "share_b": 0.0, | |
| "ratio": 374.33 | |
| }, | |
| { | |
| "token": "tex-fonts", | |
| "share_a": 0.113, | |
| "share_b": 0.0, | |
| "ratio": 303.03 | |
| }, | |
| { | |
| "token": "blocking", | |
| "share_a": 0.183, | |
| "share_b": 0.001, | |
| "ratio": 288.77 | |
| }, | |
| { | |
| "token": "pattern", | |
| "share_a": 0.183, | |
| "share_b": 0.001, | |
| "ratio": 288.77 | |
| }, | |
| { | |
| "token": "exe", | |
| "share_a": 0.056, | |
| "share_b": 0.0, | |
| "ratio": 160.43 | |
| }, | |
| { | |
| "token": "setting", | |
| "share_a": 0.183, | |
| "share_b": 0.001, | |
| "ratio": 131.26 | |
| }, | |
| { | |
| "token": "overbehitchreveiw", | |
| "share_a": 0.042, | |
| "share_b": 0.0, | |
| "ratio": 124.78 | |
| }, | |
| { | |
| "token": "tex-font", | |
| "share_a": 0.056, | |
| "share_b": 0.001, | |
| "ratio": 96.26 | |
| }, | |
| { | |
| "token": "utah", | |
| "share_a": 0.169, | |
| "share_b": 0.002, | |
| "ratio": 89.13 | |
| }, | |
| { | |
| "token": "detected", | |
| "share_a": 0.169, | |
| "share_b": 0.002, | |
| "ratio": 89.13 | |
| }, | |
| { | |
| "token": "unhappy", | |
| "share_a": 0.042, | |
| "share_b": 0.001, | |
| "ratio": 74.87 | |
| }, | |
| { | |
| "token": "funny", | |
| "share_a": 0.042, | |
| "share_b": 0.001, | |
| "ratio": 74.87 | |
| }, | |
| { | |
| "token": "mobitel0", | |
| "share_a": 0.042, | |
| "share_b": 0.001, | |
| "ratio": 74.87 | |
| }, | |
| { | |
| "token": "mobitel", | |
| "share_a": 0.042, | |
| "share_b": 0.001, | |
| "ratio": 74.87 | |
| } | |
| ], | |
| "fp_vs_tn_tokens": [ | |
| { | |
| "token": "referring", | |
| "share_a": 0.05, | |
| "share_b": 0.007, | |
| "ratio": 7.6 | |
| }, | |
| { | |
| "token": "https", | |
| "share_a": 0.049, | |
| "share_b": 0.007, | |
| "ratio": 6.72 | |
| }, | |
| { | |
| "token": "inform", | |
| "share_a": 0.056, | |
| "share_b": 0.009, | |
| "ratio": 6.54 | |
| }, | |
| { | |
| "token": "forwarding", | |
| "share_a": 0.09, | |
| "share_b": 0.014, | |
| "ratio": 6.32 | |
| }, | |
| { | |
| "token": "coordinator", | |
| "share_a": 0.06, | |
| "share_b": 0.01, | |
| "ratio": 6.03 | |
| }, | |
| { | |
| "token": "todd", | |
| "share_a": 0.049, | |
| "share_b": 0.008, | |
| "ratio": 6.01 | |
| }, | |
| { | |
| "token": "official", | |
| "share_a": 0.062, | |
| "share_b": 0.012, | |
| "ratio": 5.26 | |
| }, | |
| { | |
| "token": "esmtp", | |
| "share_a": 0.074, | |
| "share_b": 0.014, | |
| "ratio": 5.18 | |
| }, | |
| { | |
| "token": "brought", | |
| "share_a": 0.054, | |
| "share_b": 0.011, | |
| "ratio": 5.13 | |
| }, | |
| { | |
| "token": "safe", | |
| "share_a": 0.059, | |
| "share_b": 0.012, | |
| "ratio": 5.12 | |
| }, | |
| { | |
| "token": "precedence", | |
| "share_a": 0.05, | |
| "share_b": 0.01, | |
| "ratio": 4.97 | |
| }, | |
| { | |
| "token": "hotmail", | |
| "share_a": 0.059, | |
| "share_b": 0.012, | |
| "ratio": 4.9 | |
| }, | |
| { | |
| "token": "friends", | |
| "share_a": 0.071, | |
| "share_b": 0.015, | |
| "ratio": 4.66 | |
| }, | |
| { | |
| "token": "private", | |
| "share_a": 0.071, | |
| "share_b": 0.016, | |
| "ratio": 4.49 | |
| }, | |
| { | |
| "token": "mime-version", | |
| "share_a": 0.081, | |
| "share_b": 0.018, | |
| "ratio": 4.46 | |
| }, | |
| { | |
| "token": "locate", | |
| "share_a": 0.051, | |
| "share_b": 0.012, | |
| "ratio": 4.46 | |
| }, | |
| { | |
| "token": "content-transfer-encoding", | |
| "share_a": 0.065, | |
| "share_b": 0.015, | |
| "ratio": 4.4 | |
| }, | |
| { | |
| "token": "decide", | |
| "share_a": 0.056, | |
| "share_b": 0.013, | |
| "ratio": 4.38 | |
| }, | |
| { | |
| "token": "sender", | |
| "share_a": 0.082, | |
| "share_b": 0.019, | |
| "ratio": 4.36 | |
| }, | |
| { | |
| "token": "international", | |
| "share_a": 0.087, | |
| "share_b": 0.021, | |
| "ratio": 4.2 | |
| } | |
| ], | |
| "top_fn_doc_ids": [ | |
| "primary:052869", | |
| "primary:020947", | |
| "primary:121268", | |
| "primary:086987", | |
| "primary:122099", | |
| "primary:161198", | |
| "primary:044992", | |
| "primary:145723", | |
| "primary:056767", | |
| "primary:129745", | |
| "primary:147887", | |
| "primary:173938", | |
| "primary:173636", | |
| "primary:160104", | |
| "primary:024565", | |
| "primary:063077", | |
| "primary:072993", | |
| "primary:017595", | |
| "primary:080991", | |
| "primary:076023", | |
| "primary:030013", | |
| "primary:186523", | |
| "primary:154489", | |
| "primary:071577", | |
| "primary:143065" | |
| ], | |
| "top_fp_doc_ids": [ | |
| "primary:174983", | |
| "primary:118028", | |
| "primary:143547", | |
| "primary:182736", | |
| "primary:070866", | |
| "primary:040048", | |
| "primary:049322", | |
| "primary:011014", | |
| "primary:051867", | |
| "primary:032159", | |
| "primary:015304", | |
| "primary:092217", | |
| "primary:052736", | |
| "primary:030534", | |
| "primary:158244", | |
| "primary:066681", | |
| "primary:202546", | |
| "primary:180285", | |
| "primary:129925", | |
| "primary:011118", | |
| "primary:189627", | |
| "primary:107132", | |
| "primary:194063", | |
| "primary:057266", | |
| "primary:170605" | |
| ], | |
| "threeway": null | |
| }, | |
| "plots": { | |
| "confusion_matrix": "reports/eval_ft-weighted/confusion_matrix.png", | |
| "roc_curve": "reports/eval_ft-weighted/roc_curve.png", | |
| "pr_curve": "reports/eval_ft-weighted/pr_curve.png" | |
| } | |
| } | |