Download presentation/reports/eval_ft-12L/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-12L/metrics.json
- Command line
-
hf download hf://BuildITSystems/phishing-detector-encoder/presentation/reports/eval_ft-12L/metrics.json
-
curl -L -o metrics.json https://huggingface.co/BuildITSystems/phishing-detector-encoder/resolve/main/presentation/reports/eval_ft-12L/metrics.json
27.1 kB
| { | |
| "timestamp": "2026-10-09 08:54", | |
| "run_name": "ft-12L", | |
| "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-12L/best", | |
| "splits_in_invocation": [ | |
| "test", | |
| "test3" | |
| ], | |
| "model_config": { | |
| "vocab_size": 32768, | |
| "max_seq_len": 512, | |
| "d_model": 1024, | |
| "n_layers": 12, | |
| "n_heads": 16, | |
| "d_ff": 4096, | |
| "dropout": 0.1, | |
| "attention_dropout": 0.1, | |
| "layer_norm_eps": 1e-05, | |
| "pad_token_id": 0, | |
| "tie_mlm_head": true, | |
| "grad_checkpointing": false, | |
| "num_labels": 3 | |
| }, | |
| "num_labels": 3, | |
| "params": 186290179, | |
| "checkpoint_config": { | |
| "tokenizer": "tokenizer.json", | |
| "finetune": { | |
| "run_name": "ft-12L", | |
| "init": "pretrained:checkpoints/pretrain/large-24L/final", | |
| "n_layers": 12, | |
| "freeze_layers": 0, | |
| "loss": "cross_entropy", | |
| "focal_gamma": 2.0, | |
| "lr": 3e-05, | |
| "batch_size": 32, | |
| "micro_batch": 16, | |
| "epochs": 2, | |
| "max_steps": null, | |
| "eval_every": 1250, | |
| "log_every": 20, | |
| "eval_batch_size": 64, | |
| "warmup_fraction": 0.06, | |
| "weight_decay": 0.01, | |
| "betas": [ | |
| 0.9, | |
| 0.98 | |
| ], | |
| "eps": 1e-06, | |
| "grad_clip": 1.0, | |
| "patience": 2, | |
| "schedule": "linear_decay", | |
| "selection_metric": "val_f1_unwanted", | |
| "pooling": "cls", | |
| "num_labels": 3, | |
| "synthetic": "off", | |
| "limit_rows": null, | |
| "seed": 42, | |
| "cpu": false | |
| }, | |
| "best_epoch": 1, | |
| "best_step": 6250, | |
| "num_labels": 3, | |
| "label_names": [ | |
| "Legitimate", | |
| "Phishing", | |
| "Spam" | |
| ], | |
| "binary_rollup_name": "Unwanted (phishing or spam)", | |
| "selection_metric": "val_f1_unwanted", | |
| "selection_value": 0.9925057415689592, | |
| "val_metrics": { | |
| "accuracy": 0.9918869405914682, | |
| "precision": 0.9935866408518877, | |
| "recall": 0.9914271914996378, | |
| "f1": 0.9925057415689592, | |
| "roc_auc": 0.9995007118744352, | |
| "pr_auc": 0.9995737781814353, | |
| "tn": 6949, | |
| "fp": 53, | |
| "fn": 71, | |
| "tp": 8211, | |
| "threshold": 0.5, | |
| "f1_optimal_threshold": 0.17105858027935028, | |
| "f1_at_optimal_threshold": 0.9928829915560917, | |
| "f1_unwanted": 0.9925057415689592, | |
| "n_3way": 8105, | |
| "accuracy_3way": 0.9916101172115978, | |
| "macro_f1_3way": 0.9774079655816474, | |
| "precision_legitimate": 0.9984195402298851, | |
| "recall_legitimate": 0.9924307340759783, | |
| "f1_legitimate": 0.9954161294943418, | |
| "precision_phishing": 0.9570200573065902, | |
| "recall_phishing": 0.9823529411764705, | |
| "f1_phishing": 0.969521044992743, | |
| "precision_spam": 0.9472361809045227, | |
| "recall_spam": 0.9882044560943644, | |
| "f1_spam": 0.9672867222578576, | |
| "cm3_ll": 6949, | |
| "cm3_lp": 13, | |
| "cm3_ls": 40, | |
| "cm3_pl": 4, | |
| "cm3_pp": 334, | |
| "cm3_ps": 2, | |
| "cm3_sl": 7, | |
| "cm3_sp": 2, | |
| "cm3_ss": 754, | |
| "n_unwanted_3way": 1103, | |
| "pvs_phish_as_phish": 338, | |
| "pvs_phish_as_spam": 2, | |
| "pvs_spam_as_phish": 2, | |
| "pvs_spam_as_spam": 761, | |
| "val_loss": 0.035248381216093624, | |
| "n": 15284, | |
| "eval_seconds": 22.8 | |
| }, | |
| "val_metric_sets": { | |
| "binary_unwanted": { | |
| "accuracy": 0.9918869405914682, | |
| "precision": 0.9935866408518877, | |
| "recall": 0.9914271914996378, | |
| "f1": 0.9925057415689592, | |
| "roc_auc": 0.9995007118744352, | |
| "pr_auc": 0.9995737781814353, | |
| "tn": 6949, | |
| "fp": 53, | |
| "fn": 71, | |
| "tp": 8211, | |
| "threshold": 0.5, | |
| "f1_optimal_threshold": 0.17105858027935028, | |
| "f1_at_optimal_threshold": 0.9928829915560917, | |
| "n": 15284, | |
| "positive_class": "Unwanted (phishing or spam)" | |
| }, | |
| "three_way": { | |
| "n": 8105, | |
| "accuracy": 0.9916101172115978, | |
| "macro_f1": 0.9774079655816474, | |
| "per_class": { | |
| "Legitimate": { | |
| "precision": 0.9984195402298851, | |
| "recall": 0.9924307340759783, | |
| "f1": 0.9954161294943418 | |
| }, | |
| "Phishing": { | |
| "precision": 0.9570200573065902, | |
| "recall": 0.9823529411764705, | |
| "f1": 0.969521044992743 | |
| }, | |
| "Spam": { | |
| "precision": 0.9472361809045227, | |
| "recall": 0.9882044560943644, | |
| "f1": 0.9672867222578576 | |
| } | |
| }, | |
| "confusion": { | |
| "order": [ | |
| "Legitimate", | |
| "Phishing", | |
| "Spam" | |
| ], | |
| "rows_true_cols_pred": [ | |
| [ | |
| 6949, | |
| 13, | |
| 40 | |
| ], | |
| [ | |
| 4, | |
| 334, | |
| 2 | |
| ], | |
| [ | |
| 7, | |
| 2, | |
| 754 | |
| ] | |
| ] | |
| }, | |
| "phish_vs_spam_on_true_unwanted": { | |
| "n": 1103, | |
| "order": [ | |
| "Phishing", | |
| "Spam" | |
| ], | |
| "rows_true_cols_pred": [ | |
| [ | |
| 338, | |
| 2 | |
| ], | |
| [ | |
| 2, | |
| 761 | |
| ] | |
| ] | |
| } | |
| } | |
| }, | |
| "thresholds": { | |
| "decision": 0.5, | |
| "decision_applies_to": "P(unwanted) = sum of non-legitimate probabilities", | |
| "val_f1_optimal": 0.17105858027935028, | |
| "val_f1_at_optimal": 0.9928829915560917 | |
| }, | |
| "init": "pretrained:/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final", | |
| "params": { | |
| "total": 186290179, | |
| "trainable": 186290179, | |
| "embeddings": 34080768, | |
| "encoder_layers": 151154688, | |
| "final_norm": 2048, | |
| "head": 1052675 | |
| } | |
| }, | |
| "tokenizer": "/home/nathank/BITS/dev/Phishing Model/data/processed/tokenizer.json", | |
| "max_len": 512, | |
| "label_names": { | |
| "0": "Legitimate", | |
| "1": "Phishing", | |
| "2": "Spam" | |
| }, | |
| "binary_rollup": { | |
| "unwanted_name": "Unwanted (phishing or spam)", | |
| "classes": [ | |
| 1, | |
| 2 | |
| ], | |
| "rule": "P(unwanted) = sum of P(class) for class >= 1; flag when >= threshold" | |
| }, | |
| "split_sizes": { | |
| "rows": 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": 0.9347932768985401, | |
| "precision": 0.8119903019616487, | |
| "recall": 0.9460708782742681, | |
| "f1": 0.8739176847349069, | |
| "specificity": 0.931254029658285, | |
| "false_positive_rate": 0.06874597034171502, | |
| "false_negative_rate": 0.053929121725731895, | |
| "confusion_matrix": { | |
| "tn": 11555, | |
| "fp": 853, | |
| "fn": 210, | |
| "tp": 3684 | |
| }, | |
| "n": 16302, | |
| "n_positive": 3894, | |
| "n_negative": 12408 | |
| }, | |
| "threshold_free": { | |
| "roc_auc": 0.9835520193907075, | |
| "pr_auc": 0.9512527318693685, | |
| "recall_at_fpr_1pct": { | |
| "fpr_budget": 0.01, | |
| "recall": 0.6607601438109912, | |
| "fpr": 0.009993552546744036, | |
| "threshold": 0.9997559785842896, | |
| "threshold_rule": "flag when p >= threshold" | |
| }, | |
| "recall_at_fpr_0_1pct": { | |
| "fpr_budget": 0.001, | |
| "recall": 0.40729327170005136, | |
| "fpr": 0.0009671179883945841, | |
| "threshold": 0.999977171421051, | |
| "threshold_rule": "flag when p >= threshold" | |
| }, | |
| "best_f1": { | |
| "threshold": 0.9551892876625061, | |
| "f1": 0.8851884312007011, | |
| "precision": 0.8636696799413633, | |
| "recall": 0.9078068823831535 | |
| } | |
| }, | |
| "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": 3684, | |
| "predicted_phishing": 802, | |
| "predicted_spam": 2882 | |
| }, | |
| "false_positives_flagged": { | |
| "n": 853, | |
| "predicted_phishing": 366, | |
| "predicted_spam": 487 | |
| }, | |
| "missed_positives": { | |
| "n": 210, | |
| "predicted_phishing": 13, | |
| "predicted_spam": 197 | |
| }, | |
| "all_flagged": { | |
| "n": 4537, | |
| "predicted_phishing": 1168, | |
| "predicted_spam": 3369 | |
| }, | |
| "unsplit_unwanted_rows_flagged": { | |
| "n": 3684, | |
| "predicted_phishing": 802, | |
| "predicted_spam": 2882 | |
| } | |
| }, | |
| "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": 0.9321608040201005, | |
| "precision": 0.9029850746268657, | |
| "recall": 0.9958847736625515, | |
| "f1": 0.9471624266144814, | |
| "specificity": 0.832258064516129, | |
| "false_positive_rate": 0.16774193548387098, | |
| "false_negative_rate": 0.00411522633744856, | |
| "confusion_matrix": { | |
| "tn": 129, | |
| "fp": 26, | |
| "fn": 1, | |
| "tp": 242 | |
| }, | |
| "n": 398, | |
| "n_positive": 243, | |
| "n_negative": 155, | |
| "roc_auc": 0.9919288464091331 | |
| } | |
| }, | |
| "per_source": { | |
| "TREC-06": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9347932768985401, | |
| "precision": 0.8119903019616487, | |
| "recall": 0.9460708782742681, | |
| "f1": 0.8739176847349069, | |
| "specificity": 0.931254029658285, | |
| "false_positive_rate": 0.06874597034171502, | |
| "false_negative_rate": 0.053929121725731895, | |
| "confusion_matrix": { | |
| "tn": 11555, | |
| "fp": 853, | |
| "fn": 210, | |
| "tp": 3684 | |
| }, | |
| "n": 16302, | |
| "n_positive": 3894, | |
| "n_negative": 12408, | |
| "roc_auc": 0.9835520193907075, | |
| "label3_counts": { | |
| "legit": 12408, | |
| "phish": 0, | |
| "spam": 0, | |
| "unwanted": 3894 | |
| } | |
| } | |
| }, | |
| "length_confound": { | |
| "by_outcome": { | |
| "tp": { | |
| "n": 3684, | |
| "mean_tokens_full": 286.3, | |
| "mean_tokens_fed": 233.1, | |
| "median_tokens_full": 208.0, | |
| "pct_truncated": 15.1 | |
| }, | |
| "tn": { | |
| "n": 11555, | |
| "mean_tokens_full": 824.9, | |
| "mean_tokens_fed": 294.1, | |
| "median_tokens_full": 269.0, | |
| "pct_truncated": 23.5 | |
| }, | |
| "fp": { | |
| "n": 853, | |
| "mean_tokens_full": 1105.4, | |
| "mean_tokens_fed": 288.0, | |
| "median_tokens_full": 249.0, | |
| "pct_truncated": 30.9 | |
| }, | |
| "fn": { | |
| "n": 210, | |
| "mean_tokens_full": 260.3, | |
| "mean_tokens_fed": 210.7, | |
| "median_tokens_full": 134.0, | |
| "pct_truncated": 18.6 | |
| }, | |
| "correct": { | |
| "n": 15239, | |
| "mean_tokens_full": 694.7, | |
| "mean_tokens_fed": 279.3, | |
| "median_tokens_full": 247.0, | |
| "pct_truncated": 21.5 | |
| }, | |
| "wrong": { | |
| "n": 1063, | |
| "mean_tokens_full": 938.4, | |
| "mean_tokens_fed": 272.7, | |
| "median_tokens_full": 221.0, | |
| "pct_truncated": 28.5 | |
| } | |
| }, | |
| "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": 0.9063032367972743, | |
| "fpr": 0.13015463917525774, | |
| "accuracy": 0.8855465884079237 | |
| }, | |
| { | |
| "bucket": "65-128", | |
| "n": 2538, | |
| "n_positive": 736, | |
| "positive_rate": 0.2899921197793538, | |
| "recall": 0.9320652173913043, | |
| "fpr": 0.07935627081021088, | |
| "accuracy": 0.9239558707643813 | |
| }, | |
| { | |
| "bucket": "129-256", | |
| "n": 4594, | |
| "n_positive": 1196, | |
| "positive_rate": 0.260339573356552, | |
| "recall": 0.9690635451505016, | |
| "fpr": 0.05503237198351972, | |
| "accuracy": 0.9512407488027862 | |
| }, | |
| { | |
| "bucket": "257-512", | |
| "n": 4232, | |
| "n_positive": 780, | |
| "positive_rate": 0.1843100189035917, | |
| "recall": 0.9628205128205128, | |
| "fpr": 0.04577056778679027, | |
| "accuracy": 0.9558128544423441 | |
| }, | |
| { | |
| "bucket": ">512", | |
| "n": 3575, | |
| "n_positive": 595, | |
| "positive_rate": 0.16643356643356644, | |
| "recall": 0.934453781512605, | |
| "fpr": 0.08859060402684564, | |
| "accuracy": 0.9152447552447552 | |
| } | |
| ] | |
| }, | |
| "inference": { | |
| "device": "cuda", | |
| "autocast_bf16": true, | |
| "batch_size": 64, | |
| "pad_to_multiple_of": 8, | |
| "num_labels": 3, | |
| "rows": 16302, | |
| "seconds": 27.55, | |
| "rows_per_s": 591.7, | |
| "padded_tokens": 4606544, | |
| "real_tokens": 4546874, | |
| "padded_tokens_per_s": 167190, | |
| "peak_vram_gb": 1.7 | |
| }, | |
| "latency": { | |
| "instructor_benchmark_ms": 74.0, | |
| "samples_requested": 100, | |
| "sample_split": "test", | |
| "max_len": 512, | |
| "gpu_bf16": { | |
| "n": 100, | |
| "avg_ms": 5.05, | |
| "p50_ms": 4.42, | |
| "p95_ms": 6.98, | |
| "max_ms": 12.33, | |
| "avg_s": 0.0051, | |
| "mean_tokens": 280.0, | |
| "ratio_to_benchmark": 0.068, | |
| "device": "NVIDIA GeForce RTX 3090 Ti" | |
| }, | |
| "cpu_fp32": { | |
| "n": 100, | |
| "avg_ms": 246.62, | |
| "p50_ms": 242.67, | |
| "p95_ms": 356.11, | |
| "max_ms": 389.87, | |
| "avg_s": 0.2466, | |
| "mean_tokens": 280.0, | |
| "ratio_to_benchmark": 3.333, | |
| "threads": 16, | |
| "estimated_full_run_s": 27.1 | |
| }, | |
| "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-12L/best", | |
| "run_name": "ft-12L", | |
| "params": 186290179, | |
| "timestamp": "2026-10-09 08:54", | |
| "num_labels": 3, | |
| "measured_once_for_splits": [ | |
| "test", | |
| "test3" | |
| ] | |
| }, | |
| "error_analysis": { | |
| "path": "reports/eval_ft-12L/error_analysis.md", | |
| "n_fn": 210, | |
| "n_fp": 853, | |
| "composition": { | |
| "fp": { | |
| "n": 853, | |
| "mailing_list_or_digest": 0.164, | |
| "html_heavy": 0.002, | |
| "very_short_lt20_tokens": 0.011, | |
| "truncated_gt512": 0.309, | |
| "lure_phrase": 0.03 | |
| }, | |
| "tn": { | |
| "n": 11555, | |
| "mailing_list_or_digest": 0.302, | |
| "html_heavy": 0.002, | |
| "very_short_lt20_tokens": 0.005, | |
| "truncated_gt512": 0.235, | |
| "lure_phrase": 0.011 | |
| }, | |
| "fn": { | |
| "n": 210, | |
| "mailing_list_or_digest": 0.052, | |
| "html_heavy": 0.0, | |
| "very_short_lt20_tokens": 0.01, | |
| "truncated_gt512": 0.186, | |
| "lure_phrase": 0.005 | |
| }, | |
| "tp": { | |
| "n": 3684, | |
| "mailing_list_or_digest": 0.029, | |
| "html_heavy": 0.001, | |
| "very_short_lt20_tokens": 0.002, | |
| "truncated_gt512": 0.151, | |
| "lure_phrase": 0.066 | |
| } | |
| }, | |
| "fn_vs_tp_tokens": [ | |
| { | |
| "token": "yhoo", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "greko's", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "pre-registration", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "gannett", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "e-marketing", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "inundated", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "usages", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "producing", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "nasdaq", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "goog", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "ibd", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "ringing", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "gci", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "twx", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "fotis", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "targeting", | |
| "share_a": 0.119, | |
| "share_b": 0.0, | |
| "ratio": 297.56 | |
| }, | |
| { | |
| "token": "dgko", | |
| "share_a": 0.119, | |
| "share_b": 0.001, | |
| "ratio": 178.54 | |
| }, | |
| { | |
| "token": "dow", | |
| "share_a": 0.119, | |
| "share_b": 0.001, | |
| "ratio": 178.54 | |
| }, | |
| { | |
| "token": "clixme", | |
| "share_a": 0.119, | |
| "share_b": 0.001, | |
| "ratio": 178.54 | |
| }, | |
| { | |
| "token": "greko", | |
| "share_a": 0.119, | |
| "share_b": 0.001, | |
| "ratio": 178.54 | |
| } | |
| ], | |
| "fp_vs_tn_tokens": [ | |
| { | |
| "token": "forwarding", | |
| "share_a": 0.084, | |
| "share_b": 0.014, | |
| "ratio": 5.97 | |
| }, | |
| { | |
| "token": "esmtp", | |
| "share_a": 0.08, | |
| "share_b": 0.014, | |
| "ratio": 5.85 | |
| }, | |
| { | |
| "token": "hotmail", | |
| "share_a": 0.064, | |
| "share_b": 0.011, | |
| "ratio": 5.67 | |
| }, | |
| { | |
| "token": "inform", | |
| "share_a": 0.049, | |
| "share_b": 0.009, | |
| "ratio": 5.56 | |
| }, | |
| { | |
| "token": "precedence", | |
| "share_a": 0.053, | |
| "share_b": 0.01, | |
| "ratio": 5.48 | |
| }, | |
| { | |
| "token": "coordinator", | |
| "share_a": 0.054, | |
| "share_b": 0.01, | |
| "ratio": 5.31 | |
| }, | |
| { | |
| "token": "content-transfer-encoding", | |
| "share_a": 0.07, | |
| "share_b": 0.014, | |
| "ratio": 4.95 | |
| }, | |
| { | |
| "token": "mime-version", | |
| "share_a": 0.086, | |
| "share_b": 0.017, | |
| "ratio": 4.91 | |
| }, | |
| { | |
| "token": "safe", | |
| "share_a": 0.054, | |
| "share_b": 0.012, | |
| "ratio": 4.65 | |
| }, | |
| { | |
| "token": "private", | |
| "share_a": 0.069, | |
| "share_b": 0.016, | |
| "ratio": 4.46 | |
| }, | |
| { | |
| "token": "content-type", | |
| "share_a": 0.083, | |
| "share_b": 0.019, | |
| "ratio": 4.39 | |
| }, | |
| { | |
| "token": "official", | |
| "share_a": 0.053, | |
| "share_b": 0.012, | |
| "ratio": 4.38 | |
| }, | |
| { | |
| "token": "message-id", | |
| "share_a": 0.08, | |
| "share_b": 0.019, | |
| "ratio": 4.28 | |
| }, | |
| { | |
| "token": "service", | |
| "share_a": 0.165, | |
| "share_b": 0.041, | |
| "ratio": 4.0 | |
| }, | |
| { | |
| "token": "hosts", | |
| "share_a": 0.052, | |
| "share_b": 0.013, | |
| "ratio": 3.98 | |
| }, | |
| { | |
| "token": "reply-to", | |
| "share_a": 0.05, | |
| "share_b": 0.013, | |
| "ratio": 3.97 | |
| }, | |
| { | |
| "token": "sender", | |
| "share_a": 0.075, | |
| "share_b": 0.019, | |
| "ratio": 3.96 | |
| }, | |
| { | |
| "token": "forum", | |
| "share_a": 0.064, | |
| "share_b": 0.017, | |
| "ratio": 3.79 | |
| }, | |
| { | |
| "token": "decide", | |
| "share_a": 0.049, | |
| "share_b": 0.013, | |
| "ratio": 3.75 | |
| }, | |
| { | |
| "token": "us-ascii", | |
| "share_a": 0.057, | |
| "share_b": 0.015, | |
| "ratio": 3.73 | |
| } | |
| ], | |
| "top_fn_doc_ids": [ | |
| "primary:052869", | |
| "primary:080991", | |
| "primary:020947", | |
| "primary:024445", | |
| "primary:017336", | |
| "primary:086987", | |
| "primary:076023", | |
| "primary:199972", | |
| "primary:143065", | |
| "primary:045125", | |
| "primary:145723", | |
| "primary:147193", | |
| "primary:085220", | |
| "primary:186806", | |
| "primary:171201", | |
| "primary:167537", | |
| "primary:119133", | |
| "primary:166654", | |
| "primary:024565", | |
| "primary:177199", | |
| "primary:071266", | |
| "primary:036450", | |
| "primary:121268", | |
| "primary:160104", | |
| "primary:081278" | |
| ], | |
| "top_fp_doc_ids": [ | |
| "primary:143547", | |
| "primary:118028", | |
| "primary:182736", | |
| "primary:118388", | |
| "primary:126834", | |
| "primary:052736", | |
| "primary:065595", | |
| "primary:022188", | |
| "primary:194751", | |
| "primary:068707", | |
| "primary:142763", | |
| "primary:094404", | |
| "primary:041370", | |
| "primary:187756", | |
| "primary:085043", | |
| "primary:049322", | |
| "primary:174983", | |
| "primary:046160", | |
| "primary:158244", | |
| "primary:107132", | |
| "primary:070866", | |
| "primary:075107", | |
| "primary:042367", | |
| "primary:202546", | |
| "primary:010440" | |
| ], | |
| "threeway": null | |
| }, | |
| "plots": { | |
| "confusion_matrix": "reports/eval_ft-12L/confusion_matrix.png", | |
| "roc_curve": "reports/eval_ft-12L/roc_curve.png", | |
| "pr_curve": "reports/eval_ft-12L/pr_curve.png" | |
| } | |
| } | |