Download presentation/reports/eval_ft-ce/metrics.json from BuildITSystems/phishing-detector-encoder: direct link, hf CLI and curl.
- Browser
- Download file 27.1 kB
-
https://huggingface.co/BuildITSystems/phishing-detector-encoder/resolve/main/presentation/reports/eval_ft-ce/metrics.json
- Command line
-
hf download hf://BuildITSystems/phishing-detector-encoder/presentation/reports/eval_ft-ce/metrics.json
-
curl -L -o metrics.json https://huggingface.co/BuildITSystems/phishing-detector-encoder/resolve/main/presentation/reports/eval_ft-ce/metrics.json
27.1 kB
| { | |
| "timestamp": "2026-10-09 04:28", | |
| "run_name": "ft-ce", | |
| "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-ce/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-ce", | |
| "init": "pretrained:checkpoints/pretrain/large-24L/final", | |
| "n_layers": 24, | |
| "freeze_layers": 0, | |
| "loss": "cross_entropy", | |
| "focal_gamma": 2.0, | |
| "lr": 3e-05, | |
| "batch_size": 32, | |
| "micro_batch": 16, | |
| "epochs": 3, | |
| "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": 5000, | |
| "num_labels": 3, | |
| "label_names": [ | |
| "Legitimate", | |
| "Phishing", | |
| "Spam" | |
| ], | |
| "binary_rollup_name": "Unwanted (phishing or spam)", | |
| "selection_metric": "val_f1_unwanted", | |
| "selection_value": 0.992930086410055, | |
| "val_metrics": { | |
| "accuracy": 0.9923449358806595, | |
| "precision": 0.9938308939155679, | |
| "recall": 0.992030910408114, | |
| "f1": 0.992930086410055, | |
| "roc_auc": 0.9995503578823617, | |
| "pr_auc": 0.9996107014519675, | |
| "tn": 6951, | |
| "fp": 51, | |
| "fn": 66, | |
| "tp": 8216, | |
| "threshold": 0.5, | |
| "f1_optimal_threshold": 0.31750011444091797, | |
| "f1_at_optimal_threshold": 0.9931808581256412, | |
| "f1_unwanted": 0.992930086410055, | |
| "n_3way": 8105, | |
| "accuracy_3way": 0.9922270203578039, | |
| "macro_f1_3way": 0.9781799660145108, | |
| "precision_legitimate": 0.9988504095416008, | |
| "recall_legitimate": 0.9927163667523564, | |
| "f1_legitimate": 0.995773941694721, | |
| "precision_phishing": 0.9390581717451524, | |
| "recall_phishing": 0.9970588235294118, | |
| "f1_phishing": 0.9671897289586305, | |
| "precision_spam": 0.9579617834394905, | |
| "recall_spam": 0.9855832241153342, | |
| "f1_spam": 0.9715762273901809, | |
| "cm3_ll": 6951, | |
| "cm3_lp": 18, | |
| "cm3_ls": 33, | |
| "cm3_pl": 1, | |
| "cm3_pp": 339, | |
| "cm3_ps": 0, | |
| "cm3_sl": 7, | |
| "cm3_sp": 4, | |
| "cm3_ss": 752, | |
| "n_unwanted_3way": 1103, | |
| "pvs_phish_as_phish": 340, | |
| "pvs_phish_as_spam": 0, | |
| "pvs_spam_as_phish": 4, | |
| "pvs_spam_as_spam": 759, | |
| "val_loss": 0.027098098741997853, | |
| "n": 15284, | |
| "eval_seconds": 47.7 | |
| }, | |
| "val_metric_sets": { | |
| "binary_unwanted": { | |
| "accuracy": 0.9923449358806595, | |
| "precision": 0.9938308939155679, | |
| "recall": 0.992030910408114, | |
| "f1": 0.992930086410055, | |
| "roc_auc": 0.9995503578823617, | |
| "pr_auc": 0.9996107014519675, | |
| "tn": 6951, | |
| "fp": 51, | |
| "fn": 66, | |
| "tp": 8216, | |
| "threshold": 0.5, | |
| "f1_optimal_threshold": 0.31750011444091797, | |
| "f1_at_optimal_threshold": 0.9931808581256412, | |
| "n": 15284, | |
| "positive_class": "Unwanted (phishing or spam)" | |
| }, | |
| "three_way": { | |
| "n": 8105, | |
| "accuracy": 0.9922270203578039, | |
| "macro_f1": 0.9781799660145108, | |
| "per_class": { | |
| "Legitimate": { | |
| "precision": 0.9988504095416008, | |
| "recall": 0.9927163667523564, | |
| "f1": 0.995773941694721 | |
| }, | |
| "Phishing": { | |
| "precision": 0.9390581717451524, | |
| "recall": 0.9970588235294118, | |
| "f1": 0.9671897289586305 | |
| }, | |
| "Spam": { | |
| "precision": 0.9579617834394905, | |
| "recall": 0.9855832241153342, | |
| "f1": 0.9715762273901809 | |
| } | |
| }, | |
| "confusion": { | |
| "order": [ | |
| "Legitimate", | |
| "Phishing", | |
| "Spam" | |
| ], | |
| "rows_true_cols_pred": [ | |
| [ | |
| 6951, | |
| 18, | |
| 33 | |
| ], | |
| [ | |
| 1, | |
| 339, | |
| 0 | |
| ], | |
| [ | |
| 7, | |
| 4, | |
| 752 | |
| ] | |
| ] | |
| }, | |
| "phish_vs_spam_on_true_unwanted": { | |
| "n": 1103, | |
| "order": [ | |
| "Phishing", | |
| "Spam" | |
| ], | |
| "rows_true_cols_pred": [ | |
| [ | |
| 340, | |
| 0 | |
| ], | |
| [ | |
| 4, | |
| 759 | |
| ] | |
| ] | |
| } | |
| } | |
| }, | |
| "thresholds": { | |
| "decision": 0.5, | |
| "decision_applies_to": "P(unwanted) = sum of non-legitimate probabilities", | |
| "val_f1_optimal": 0.31750011444091797, | |
| "val_f1_at_optimal": 0.9931808581256412 | |
| }, | |
| "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": 0.9495153968838179, | |
| "precision": 0.8610392664001881, | |
| "recall": 0.9404211607601438, | |
| "f1": 0.8989812200810113, | |
| "specificity": 0.9523694390715667, | |
| "false_positive_rate": 0.04763056092843327, | |
| "false_negative_rate": 0.05957883923985619, | |
| "confusion_matrix": { | |
| "tn": 11817, | |
| "fp": 591, | |
| "fn": 232, | |
| "tp": 3662 | |
| }, | |
| "n": 16302, | |
| "n_positive": 3894, | |
| "n_negative": 12408 | |
| }, | |
| "threshold_free": { | |
| "roc_auc": 0.9874951859346837, | |
| "pr_auc": 0.9625515458938435, | |
| "recall_at_fpr_1pct": { | |
| "fpr_budget": 0.01, | |
| "recall": 0.7745249101181304, | |
| "fpr": 0.009993552546744036, | |
| "threshold": 0.9965154528617859, | |
| "threshold_rule": "flag when p >= threshold" | |
| }, | |
| "recall_at_fpr_0_1pct": { | |
| "fpr_budget": 0.001, | |
| "recall": 0.35285053929121724, | |
| "fpr": 0.0009671179883945841, | |
| "threshold": 0.9997650384902954, | |
| "threshold_rule": "flag when p >= threshold" | |
| }, | |
| "best_f1": { | |
| "threshold": 0.8211185932159424, | |
| "f1": 0.9089527668734962, | |
| "precision": 0.8965775668248813, | |
| "recall": 0.9216743708269132 | |
| } | |
| }, | |
| "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": 3662, | |
| "predicted_phishing": 1294, | |
| "predicted_spam": 2368 | |
| }, | |
| "false_positives_flagged": { | |
| "n": 591, | |
| "predicted_phishing": 374, | |
| "predicted_spam": 217 | |
| }, | |
| "missed_positives": { | |
| "n": 232, | |
| "predicted_phishing": 64, | |
| "predicted_spam": 168 | |
| }, | |
| "all_flagged": { | |
| "n": 4253, | |
| "predicted_phishing": 1668, | |
| "predicted_spam": 2585 | |
| }, | |
| "unsplit_unwanted_rows_flagged": { | |
| "n": 3662, | |
| "predicted_phishing": 1294, | |
| "predicted_spam": 2368 | |
| } | |
| }, | |
| "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": 0.9296482412060302, | |
| "precision": 0.8996282527881041, | |
| "recall": 0.9958847736625515, | |
| "f1": 0.9453124999999999, | |
| "specificity": 0.8258064516129032, | |
| "false_positive_rate": 0.17419354838709677, | |
| "false_negative_rate": 0.00411522633744856, | |
| "confusion_matrix": { | |
| "tn": 128, | |
| "fp": 27, | |
| "fn": 1, | |
| "tp": 242 | |
| }, | |
| "n": 398, | |
| "n_positive": 243, | |
| "n_negative": 155, | |
| "roc_auc": 0.9980087614496216 | |
| } | |
| }, | |
| "per_source": { | |
| "TREC-06": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9495153968838179, | |
| "precision": 0.8610392664001881, | |
| "recall": 0.9404211607601438, | |
| "f1": 0.8989812200810113, | |
| "specificity": 0.9523694390715667, | |
| "false_positive_rate": 0.04763056092843327, | |
| "false_negative_rate": 0.05957883923985619, | |
| "confusion_matrix": { | |
| "tn": 11817, | |
| "fp": 591, | |
| "fn": 232, | |
| "tp": 3662 | |
| }, | |
| "n": 16302, | |
| "n_positive": 3894, | |
| "n_negative": 12408, | |
| "roc_auc": 0.9874951859346837, | |
| "label3_counts": { | |
| "legit": 12408, | |
| "phish": 0, | |
| "spam": 0, | |
| "unwanted": 3894 | |
| } | |
| } | |
| }, | |
| "length_confound": { | |
| "by_outcome": { | |
| "tp": { | |
| "n": 3662, | |
| "mean_tokens_full": 286.7, | |
| "mean_tokens_fed": 234.3, | |
| "median_tokens_full": 211.0, | |
| "pct_truncated": 15.2 | |
| }, | |
| "tn": { | |
| "n": 11817, | |
| "mean_tokens_full": 848.2, | |
| "mean_tokens_fed": 293.0, | |
| "median_tokens_full": 266.0, | |
| "pct_truncated": 23.6 | |
| }, | |
| "fp": { | |
| "n": 591, | |
| "mean_tokens_full": 763.4, | |
| "mean_tokens_fed": 306.9, | |
| "median_tokens_full": 321.0, | |
| "pct_truncated": 31.5 | |
| }, | |
| "fn": { | |
| "n": 232, | |
| "mean_tokens_full": 256.2, | |
| "mean_tokens_fed": 194.3, | |
| "median_tokens_full": 121.5, | |
| "pct_truncated": 16.8 | |
| }, | |
| "correct": { | |
| "n": 15479, | |
| "mean_tokens_full": 715.4, | |
| "mean_tokens_fed": 279.1, | |
| "median_tokens_full": 246.0, | |
| "pct_truncated": 21.6 | |
| }, | |
| "wrong": { | |
| "n": 823, | |
| "mean_tokens_full": 620.4, | |
| "mean_tokens_fed": 275.1, | |
| "median_tokens_full": 237.0, | |
| "pct_truncated": 27.3 | |
| } | |
| }, | |
| "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": 0.9045996592844975, | |
| "fpr": 0.08376288659793814, | |
| "accuracy": 0.9112252384446075 | |
| }, | |
| { | |
| "bucket": "65-128", | |
| "n": 2538, | |
| "n_positive": 736, | |
| "positive_rate": 0.2899921197793538, | |
| "recall": 0.90625, | |
| "fpr": 0.039400665926748055, | |
| "accuracy": 0.9448384554767534 | |
| }, | |
| { | |
| "bucket": "129-256", | |
| "n": 4594, | |
| "n_positive": 1196, | |
| "positive_rate": 0.260339573356552, | |
| "recall": 0.9565217391304348, | |
| "fpr": 0.03384343731606827, | |
| "accuracy": 0.9636482368306487 | |
| }, | |
| { | |
| "bucket": "257-512", | |
| "n": 4232, | |
| "n_positive": 780, | |
| "positive_rate": 0.1843100189035917, | |
| "recall": 0.9794871794871794, | |
| "fpr": 0.044611819235225954, | |
| "accuracy": 0.9598298676748582 | |
| }, | |
| { | |
| "bucket": ">512", | |
| "n": 3575, | |
| "n_positive": 595, | |
| "positive_rate": 0.16643356643356644, | |
| "recall": 0.934453781512605, | |
| "fpr": 0.06241610738255034, | |
| "accuracy": 0.9370629370629371 | |
| } | |
| ] | |
| }, | |
| "inference": { | |
| "device": "cuda", | |
| "autocast_bf16": true, | |
| "batch_size": 64, | |
| "pad_to_multiple_of": 8, | |
| "num_labels": 3, | |
| "rows": 16302, | |
| "seconds": 57.19, | |
| "rows_per_s": 285.1, | |
| "padded_tokens": 4606544, | |
| "real_tokens": 4546874, | |
| "padded_tokens_per_s": 80548, | |
| "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": 9.95, | |
| "p50_ms": 8.72, | |
| "p95_ms": 13.58, | |
| "max_ms": 19.1, | |
| "avg_s": 0.0099, | |
| "mean_tokens": 280.0, | |
| "ratio_to_benchmark": 0.134, | |
| "device": "NVIDIA GeForce RTX 3090 Ti" | |
| }, | |
| "cpu_fp32": { | |
| "n": 100, | |
| "avg_ms": 514.07, | |
| "p50_ms": 526.19, | |
| "p95_ms": 724.38, | |
| "max_ms": 783.31, | |
| "avg_s": 0.5141, | |
| "mean_tokens": 280.0, | |
| "ratio_to_benchmark": 6.947, | |
| "threads": 16, | |
| "estimated_full_run_s": 51.3 | |
| }, | |
| "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-ce/best", | |
| "run_name": "ft-ce", | |
| "params": 337444867, | |
| "timestamp": "2026-10-09 04:28", | |
| "num_labels": 3, | |
| "measured_once_for_splits": [ | |
| "test", | |
| "test3" | |
| ] | |
| }, | |
| "error_analysis": { | |
| "path": "reports/eval_ft-ce/error_analysis.md", | |
| "n_fn": 232, | |
| "n_fp": 591, | |
| "composition": { | |
| "fp": { | |
| "n": 591, | |
| "mailing_list_or_digest": 0.284, | |
| "html_heavy": 0.002, | |
| "very_short_lt20_tokens": 0.024, | |
| "truncated_gt512": 0.315, | |
| "lure_phrase": 0.046 | |
| }, | |
| "tn": { | |
| "n": 11817, | |
| "mailing_list_or_digest": 0.293, | |
| "html_heavy": 0.002, | |
| "very_short_lt20_tokens": 0.004, | |
| "truncated_gt512": 0.236, | |
| "lure_phrase": 0.011 | |
| }, | |
| "fn": { | |
| "n": 232, | |
| "mailing_list_or_digest": 0.043, | |
| "html_heavy": 0.004, | |
| "very_short_lt20_tokens": 0.004, | |
| "truncated_gt512": 0.168, | |
| "lure_phrase": 0.004 | |
| }, | |
| "tp": { | |
| "n": 3662, | |
| "mailing_list_or_digest": 0.029, | |
| "html_heavy": 0.001, | |
| "very_short_lt20_tokens": 0.002, | |
| "truncated_gt512": 0.152, | |
| "lure_phrase": 0.066 | |
| } | |
| }, | |
| "fn_vs_tp_tokens": [ | |
| { | |
| "token": "blocki", | |
| "share_a": 0.052, | |
| "share_b": 0.0, | |
| "ratio": 393.82 | |
| }, | |
| { | |
| "token": "scanmail", | |
| "share_a": 0.052, | |
| "share_b": 0.0, | |
| "ratio": 393.82 | |
| }, | |
| { | |
| "token": "smailex", | |
| "share_a": 0.052, | |
| "share_b": 0.0, | |
| "ratio": 393.82 | |
| }, | |
| { | |
| "token": "progra", | |
| "share_a": 0.052, | |
| "share_b": 0.0, | |
| "ratio": 393.82 | |
| }, | |
| { | |
| "token": "scanning", | |
| "share_a": 0.052, | |
| "share_b": 0.0, | |
| "ratio": 393.82 | |
| }, | |
| { | |
| "token": "matched", | |
| "share_a": 0.052, | |
| "share_b": 0.0, | |
| "ratio": 131.27 | |
| }, | |
| { | |
| "token": "producing", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "nasdaq", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "fotis", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "usages", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "targeting", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "ibd", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "gannett", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "yhoo", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "ringing", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "twx", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "goog", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "greko's", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "gci", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| }, | |
| { | |
| "token": "e-marketing", | |
| "share_a": 0.099, | |
| "share_b": 0.001, | |
| "ratio": 105.77 | |
| } | |
| ], | |
| "fp_vs_tn_tokens": [ | |
| { | |
| "token": "ips", | |
| "share_a": 0.051, | |
| "share_b": 0.002, | |
| "ratio": 27.08 | |
| }, | |
| { | |
| "token": "noc's", | |
| "share_a": 0.051, | |
| "share_b": 0.002, | |
| "ratio": 23.9 | |
| }, | |
| { | |
| "token": "filtered", | |
| "share_a": 0.051, | |
| "share_b": 0.003, | |
| "ratio": 15.83 | |
| }, | |
| { | |
| "token": "tcpview", | |
| "share_a": 0.051, | |
| "share_b": 0.003, | |
| "ratio": 15.43 | |
| }, | |
| { | |
| "token": "procexp", | |
| "share_a": 0.051, | |
| "share_b": 0.003, | |
| "ratio": 15.43 | |
| }, | |
| { | |
| "token": "sysinternals", | |
| "share_a": 0.051, | |
| "share_b": 0.003, | |
| "ratio": 15.05 | |
| }, | |
| { | |
| "token": "atkins", | |
| "share_a": 0.051, | |
| "share_b": 0.004, | |
| "ratio": 14.34 | |
| }, | |
| { | |
| "token": "rogue", | |
| "share_a": 0.051, | |
| "share_b": 0.004, | |
| "ratio": 13.39 | |
| }, | |
| { | |
| "token": "editorial", | |
| "share_a": 0.051, | |
| "share_b": 0.004, | |
| "ratio": 12.07 | |
| }, | |
| { | |
| "token": "lsdepts", | |
| "share_a": 0.051, | |
| "share_b": 0.004, | |
| "ratio": 12.07 | |
| }, | |
| { | |
| "token": "csf", | |
| "share_a": 0.052, | |
| "share_b": 0.004, | |
| "ratio": 11.76 | |
| }, | |
| { | |
| "token": "csf-bounces", | |
| "share_a": 0.051, | |
| "share_b": 0.004, | |
| "ratio": 11.61 | |
| }, | |
| { | |
| "token": "aes256-sha", | |
| "share_a": 0.051, | |
| "share_b": 0.004, | |
| "ratio": 11.61 | |
| }, | |
| { | |
| "token": "oit", | |
| "share_a": 0.052, | |
| "share_b": 0.005, | |
| "ratio": 11.55 | |
| }, | |
| { | |
| "token": "irc", | |
| "share_a": 0.056, | |
| "share_b": 0.005, | |
| "ratio": 11.44 | |
| }, | |
| { | |
| "token": "list-post", | |
| "share_a": 0.051, | |
| "share_b": 0.004, | |
| "ratio": 11.39 | |
| }, | |
| { | |
| "token": "list-subscribe", | |
| "share_a": 0.051, | |
| "share_b": 0.004, | |
| "ratio": 11.39 | |
| }, | |
| { | |
| "token": "rebuilt", | |
| "share_a": 0.051, | |
| "share_b": 0.004, | |
| "ratio": 11.39 | |
| }, | |
| { | |
| "token": "list-archive", | |
| "share_a": 0.051, | |
| "share_b": 0.004, | |
| "ratio": 11.39 | |
| }, | |
| { | |
| "token": "ucsb", | |
| "share_a": 0.052, | |
| "share_b": 0.005, | |
| "ratio": 11.34 | |
| } | |
| ], | |
| "top_fn_doc_ids": [ | |
| "primary:052869", | |
| "primary:086987", | |
| "primary:044992", | |
| "primary:173636", | |
| "primary:080991", | |
| "primary:145723", | |
| "primary:143065", | |
| "primary:006031", | |
| "primary:019350", | |
| "primary:172278", | |
| "primary:033014", | |
| "primary:156328", | |
| "primary:009091", | |
| "primary:176328", | |
| "primary:076023", | |
| "primary:161198", | |
| "primary:122099", | |
| "primary:090853", | |
| "primary:160104", | |
| "primary:121268", | |
| "primary:024565", | |
| "primary:119133", | |
| "primary:020947", | |
| "primary:064709", | |
| "primary:171201" | |
| ], | |
| "top_fp_doc_ids": [ | |
| "primary:143547", | |
| "primary:163929", | |
| "primary:113500", | |
| "primary:118028", | |
| "primary:202546", | |
| "primary:113156", | |
| "primary:107132", | |
| "primary:126805", | |
| "primary:070866", | |
| "primary:062395", | |
| "primary:071954", | |
| "primary:069141", | |
| "primary:158244", | |
| "primary:040048", | |
| "primary:170605", | |
| "primary:106445", | |
| "primary:084432", | |
| "primary:124491", | |
| "primary:196901", | |
| "primary:101560", | |
| "primary:078484", | |
| "primary:049454", | |
| "primary:002284", | |
| "primary:068707", | |
| "primary:136688" | |
| ], | |
| "threeway": null | |
| }, | |
| "plots": { | |
| "confusion_matrix": "reports/eval_ft-ce/confusion_matrix.png", | |
| "roc_curve": "reports/eval_ft-ce/roc_curve.png", | |
| "pr_curve": "reports/eval_ft-ce/pr_curve.png" | |
| } | |
| } | |