Download presentation/reports/eval_ft-scratch/metrics.json from BuildITSystems/phishing-detector-encoder: direct link, hf CLI and curl.
- Browser
- Download file 27 kB
-
https://huggingface.co/BuildITSystems/phishing-detector-encoder/resolve/main/presentation/reports/eval_ft-scratch/metrics.json
- Command line
-
hf download hf://BuildITSystems/phishing-detector-encoder/presentation/reports/eval_ft-scratch/metrics.json
-
curl -L -o metrics.json https://huggingface.co/BuildITSystems/phishing-detector-encoder/resolve/main/presentation/reports/eval_ft-scratch/metrics.json
27 kB
| { | |
| "timestamp": "2026-10-09 09:57", | |
| "run_name": "ft-scratch", | |
| "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-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": 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": 0.9165746534167587, | |
| "precision": 0.7751954821894005, | |
| "recall": 0.9165382639958911, | |
| "f1": 0.8399623440809603, | |
| "specificity": 0.9165860735009671, | |
| "false_positive_rate": 0.08341392649903288, | |
| "false_negative_rate": 0.08346173600410889, | |
| "confusion_matrix": { | |
| "tn": 11373, | |
| "fp": 1035, | |
| "fn": 325, | |
| "tp": 3569 | |
| }, | |
| "n": 16302, | |
| "n_positive": 3894, | |
| "n_negative": 12408 | |
| }, | |
| "threshold_free": { | |
| "roc_auc": 0.9755163385154697, | |
| "pr_auc": 0.9455998878489401, | |
| "recall_at_fpr_1pct": { | |
| "fpr_budget": 0.01, | |
| "recall": 0.7773497688751926, | |
| "fpr": 0.009993552546744036, | |
| "threshold": 0.9809021353721619, | |
| "threshold_rule": "flag when p >= threshold" | |
| }, | |
| "recall_at_fpr_0_1pct": { | |
| "fpr_budget": 0.001, | |
| "recall": 0.4953775038520801, | |
| "fpr": 0.0009671179883945841, | |
| "threshold": 0.9961771965026855, | |
| "threshold_rule": "flag when p >= threshold" | |
| }, | |
| "best_f1": { | |
| "threshold": 0.941460371017456, | |
| "f1": 0.8772071707777328, | |
| "precision": 0.9231205673758865, | |
| "recall": 0.8356445814072933 | |
| } | |
| }, | |
| "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": 3569, | |
| "predicted_phishing": 332, | |
| "predicted_spam": 3237 | |
| }, | |
| "false_positives_flagged": { | |
| "n": 1035, | |
| "predicted_phishing": 281, | |
| "predicted_spam": 754 | |
| }, | |
| "missed_positives": { | |
| "n": 325, | |
| "predicted_phishing": 84, | |
| "predicted_spam": 241 | |
| }, | |
| "all_flagged": { | |
| "n": 4604, | |
| "predicted_phishing": 613, | |
| "predicted_spam": 3991 | |
| }, | |
| "unsplit_unwanted_rows_flagged": { | |
| "n": 3569, | |
| "predicted_phishing": 332, | |
| "predicted_spam": 3237 | |
| } | |
| }, | |
| "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": 0.9522613065326633, | |
| "precision": 0.9307692307692308, | |
| "recall": 0.9958847736625515, | |
| "f1": 0.9622266401590458, | |
| "specificity": 0.8838709677419355, | |
| "false_positive_rate": 0.11612903225806452, | |
| "false_negative_rate": 0.00411522633744856, | |
| "confusion_matrix": { | |
| "tn": 137, | |
| "fp": 18, | |
| "fn": 1, | |
| "tp": 242 | |
| }, | |
| "n": 398, | |
| "n_positive": 243, | |
| "n_negative": 155, | |
| "roc_auc": 0.9961502721359352 | |
| } | |
| }, | |
| "per_source": { | |
| "TREC-06": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9165746534167587, | |
| "precision": 0.7751954821894005, | |
| "recall": 0.9165382639958911, | |
| "f1": 0.8399623440809603, | |
| "specificity": 0.9165860735009671, | |
| "false_positive_rate": 0.08341392649903288, | |
| "false_negative_rate": 0.08346173600410889, | |
| "confusion_matrix": { | |
| "tn": 11373, | |
| "fp": 1035, | |
| "fn": 325, | |
| "tp": 3569 | |
| }, | |
| "n": 16302, | |
| "n_positive": 3894, | |
| "n_negative": 12408, | |
| "roc_auc": 0.9755163385154697, | |
| "label3_counts": { | |
| "legit": 12408, | |
| "phish": 0, | |
| "spam": 0, | |
| "unwanted": 3894 | |
| } | |
| } | |
| }, | |
| "length_confound": { | |
| "by_outcome": { | |
| "tp": { | |
| "n": 3569, | |
| "mean_tokens_full": 280.4, | |
| "mean_tokens_fed": 231.1, | |
| "median_tokens_full": 201.0, | |
| "pct_truncated": 15.0 | |
| }, | |
| "tn": { | |
| "n": 11373, | |
| "mean_tokens_full": 854.8, | |
| "mean_tokens_fed": 300.9, | |
| "median_tokens_full": 282.0, | |
| "pct_truncated": 25.0 | |
| }, | |
| "fp": { | |
| "n": 1035, | |
| "mean_tokens_full": 727.5, | |
| "mean_tokens_fed": 213.6, | |
| "median_tokens_full": 168.0, | |
| "pct_truncated": 12.8 | |
| }, | |
| "fn": { | |
| "n": 325, | |
| "mean_tokens_full": 334.5, | |
| "mean_tokens_fed": 241.4, | |
| "median_tokens_full": 223.0, | |
| "pct_truncated": 17.8 | |
| }, | |
| "correct": { | |
| "n": 14942, | |
| "mean_tokens_full": 717.6, | |
| "mean_tokens_fed": 284.3, | |
| "median_tokens_full": 254.0, | |
| "pct_truncated": 22.7 | |
| }, | |
| "wrong": { | |
| "n": 1360, | |
| "mean_tokens_full": 633.6, | |
| "mean_tokens_fed": 220.2, | |
| "median_tokens_full": 184.0, | |
| "pct_truncated": 14.0 | |
| } | |
| }, | |
| "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": 0.899488926746167, | |
| "fpr": 0.18170103092783504, | |
| "accuracy": 0.8532648569332355 | |
| }, | |
| { | |
| "bucket": "65-128", | |
| "n": 2538, | |
| "n_positive": 736, | |
| "positive_rate": 0.2899921197793538, | |
| "recall": 0.9565217391304348, | |
| "fpr": 0.12097669256381798, | |
| "accuracy": 0.9014972419227738 | |
| }, | |
| { | |
| "bucket": "129-256", | |
| "n": 4594, | |
| "n_positive": 1196, | |
| "positive_rate": 0.260339573356552, | |
| "recall": 0.8896321070234113, | |
| "fpr": 0.10977045320776928, | |
| "accuracy": 0.8900740095777101 | |
| }, | |
| { | |
| "bucket": "257-512", | |
| "n": 4232, | |
| "n_positive": 780, | |
| "positive_rate": 0.1843100189035917, | |
| "recall": 0.9435897435897436, | |
| "fpr": 0.049536500579374275, | |
| "accuracy": 0.9491965973534972 | |
| }, | |
| { | |
| "bucket": ">512", | |
| "n": 3575, | |
| "n_positive": 595, | |
| "positive_rate": 0.16643356643356644, | |
| "recall": 0.9025210084033614, | |
| "fpr": 0.04429530201342282, | |
| "accuracy": 0.9468531468531468 | |
| } | |
| ] | |
| }, | |
| "inference": { | |
| "device": "cuda", | |
| "autocast_bf16": true, | |
| "batch_size": 64, | |
| "pad_to_multiple_of": 8, | |
| "num_labels": 3, | |
| "rows": 16302, | |
| "seconds": 57.73, | |
| "rows_per_s": 282.4, | |
| "padded_tokens": 4606544, | |
| "real_tokens": 4546874, | |
| "padded_tokens_per_s": 79791, | |
| "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.md", | |
| "n_fn": 325, | |
| "n_fp": 1035, | |
| "composition": { | |
| "fp": { | |
| "n": 1035, | |
| "mailing_list_or_digest": 0.107, | |
| "html_heavy": 0.001, | |
| "very_short_lt20_tokens": 0.012, | |
| "truncated_gt512": 0.128, | |
| "lure_phrase": 0.017 | |
| }, | |
| "tn": { | |
| "n": 11373, | |
| "mailing_list_or_digest": 0.31, | |
| "html_heavy": 0.002, | |
| "very_short_lt20_tokens": 0.005, | |
| "truncated_gt512": 0.25, | |
| "lure_phrase": 0.012 | |
| }, | |
| "fn": { | |
| "n": 325, | |
| "mailing_list_or_digest": 0.049, | |
| "html_heavy": 0.006, | |
| "very_short_lt20_tokens": 0.006, | |
| "truncated_gt512": 0.178, | |
| "lure_phrase": 0.003 | |
| }, | |
| "tp": { | |
| "n": 3569, | |
| "mailing_list_or_digest": 0.028, | |
| "html_heavy": 0.0, | |
| "very_short_lt20_tokens": 0.002, | |
| "truncated_gt512": 0.15, | |
| "lure_phrase": 0.068 | |
| } | |
| }, | |
| "fn_vs_tp_tokens": [ | |
| { | |
| "token": "gci", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "pre-registration", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "nasdaq", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "ringing", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "twx", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "inundated", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "yhoo", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "goog", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "producing", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "targeting", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "fotis", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "e-marketing", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "ibd", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "gannett", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "usages", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "greko's", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 581.21 | |
| }, | |
| { | |
| "token": "highlight", | |
| "share_a": 0.083, | |
| "share_b": 0.0, | |
| "ratio": 201.05 | |
| }, | |
| { | |
| "token": "posting", | |
| "share_a": 0.083, | |
| "share_b": 0.0, | |
| "ratio": 201.05 | |
| }, | |
| { | |
| "token": "vendors", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 193.74 | |
| }, | |
| { | |
| "token": "dgko", | |
| "share_a": 0.08, | |
| "share_b": 0.0, | |
| "ratio": 193.74 | |
| } | |
| ], | |
| "fp_vs_tn_tokens": [ | |
| { | |
| "token": "contents", | |
| "share_a": 0.049, | |
| "share_b": 0.012, | |
| "ratio": 4.17 | |
| }, | |
| { | |
| "token": "private", | |
| "share_a": 0.054, | |
| "share_b": 0.016, | |
| "ratio": 3.38 | |
| }, | |
| { | |
| "token": "dear", | |
| "share_a": 0.155, | |
| "share_b": 0.062, | |
| "ratio": 2.49 | |
| }, | |
| { | |
| "token": "view", | |
| "share_a": 0.052, | |
| "share_b": 0.023, | |
| "ratio": 2.33 | |
| }, | |
| { | |
| "token": "become", | |
| "share_a": 0.061, | |
| "share_b": 0.027, | |
| "ratio": 2.25 | |
| }, | |
| { | |
| "token": "service", | |
| "share_a": 0.088, | |
| "share_b": 0.046, | |
| "ratio": 1.9 | |
| }, | |
| { | |
| "token": "index", | |
| "share_a": 0.059, | |
| "share_b": 0.031, | |
| "ratio": 1.89 | |
| }, | |
| { | |
| "token": "website", | |
| "share_a": 0.06, | |
| "share_b": 0.032, | |
| "ratio": 1.86 | |
| }, | |
| { | |
| "token": "visit", | |
| "share_a": 0.058, | |
| "share_b": 0.032, | |
| "ratio": 1.84 | |
| }, | |
| { | |
| "token": "battery", | |
| "share_a": 0.057, | |
| "share_b": 0.033, | |
| "ratio": 1.76 | |
| }, | |
| { | |
| "token": "link", | |
| "share_a": 0.066, | |
| "share_b": 0.039, | |
| "ratio": 1.71 | |
| }, | |
| { | |
| "token": "free", | |
| "share_a": 0.129, | |
| "share_b": 0.076, | |
| "ratio": 1.7 | |
| }, | |
| { | |
| "token": "special", | |
| "share_a": 0.058, | |
| "share_b": 0.035, | |
| "ratio": 1.67 | |
| }, | |
| { | |
| "token": "receive", | |
| "share_a": 0.06, | |
| "share_b": 0.038, | |
| "ratio": 1.61 | |
| }, | |
| { | |
| "token": "remove", | |
| "share_a": 0.053, | |
| "share_b": 0.033, | |
| "ratio": 1.61 | |
| }, | |
| { | |
| "token": "world", | |
| "share_a": 0.055, | |
| "share_b": 0.036, | |
| "ratio": 1.53 | |
| }, | |
| { | |
| "token": "messages", | |
| "share_a": 0.079, | |
| "share_b": 0.055, | |
| "ratio": 1.45 | |
| }, | |
| { | |
| "token": "anybody", | |
| "share_a": 0.063, | |
| "share_b": 0.046, | |
| "ratio": 1.38 | |
| }, | |
| { | |
| "token": "open", | |
| "share_a": 0.062, | |
| "share_b": 0.046, | |
| "ratio": 1.35 | |
| }, | |
| { | |
| "token": "internet", | |
| "share_a": 0.062, | |
| "share_b": 0.047, | |
| "ratio": 1.34 | |
| } | |
| ], | |
| "top_fn_doc_ids": [ | |
| "primary:052869", | |
| "primary:117517", | |
| "primary:167537", | |
| "primary:006858", | |
| "primary:160621", | |
| "primary:001821", | |
| "primary:186190", | |
| "primary:077801", | |
| "primary:158787", | |
| "primary:150014", | |
| "primary:096110", | |
| "primary:079715", | |
| "primary:060379", | |
| "primary:029517", | |
| "primary:122099", | |
| "primary:161198", | |
| "primary:172680", | |
| "primary:015259", | |
| "primary:022080", | |
| "primary:043353", | |
| "primary:034854", | |
| "primary:055019", | |
| "primary:028469", | |
| "primary:195636", | |
| "primary:178407" | |
| ], | |
| "top_fp_doc_ids": [ | |
| "primary:025689", | |
| "primary:049322", | |
| "primary:066681", | |
| "primary:025650", | |
| "primary:093533", | |
| "primary:118028", | |
| "primary:040776", | |
| "primary:158244", | |
| "primary:197794", | |
| "primary:107869", | |
| "primary:119762", | |
| "primary:142763", | |
| "primary:193692", | |
| "primary:001010", | |
| "primary:064078", | |
| "primary:042367", | |
| "primary:118388", | |
| "primary:121856", | |
| "primary:098000", | |
| "primary:049912", | |
| "primary:057810", | |
| "primary:126981", | |
| "primary:125508", | |
| "primary:138875", | |
| "primary:070866" | |
| ], | |
| "threeway": null | |
| }, | |
| "plots": { | |
| "confusion_matrix": "reports/eval_ft-scratch/confusion_matrix.png", | |
| "roc_curve": "reports/eval_ft-scratch/roc_curve.png", | |
| "pr_curve": "reports/eval_ft-scratch/pr_curve.png" | |
| } | |
| } | |