| {"run_name": "ft-ce", "timestamp": "2026-10-09T04:28:29", "init": "pretrained:/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final", "dials": {"n_layers": 24, "frozen_layers": 0, "epochs_planned": 3, "epochs_run": 1.248, "loss": "cross_entropy", "focal_gamma": null, "lr": 3e-05, "batch_size": 32, "micro_batch": 16, "class_weights": null, "synthetic": "off", "synthetic_rows": 0, "warmup_fraction": 0.06, "max_steps": null, "limit_rows": null, "seed": 42, "schedule": "linear_decay", "selection_metric": "val_f1_unwanted", "pooling": "cls", "num_labels": 3, "device": "cuda"}, "params": {"total": 337444867, "trainable": 337444867, "embeddings": 34080768, "encoder_layers": 302309376, "final_norm": 2048, "head": 1052675}, "steps_run": 6250, "n_train": 160263, "n_val": 15284, "train_seconds": 3089.2, "peak_vram_gb": 13.133, "best_epoch": 0, "best_step": 5000, "best_score": 0.992930086410055, "val": {"accuracy": 0.9923449358806595, "precision": 0.9938308939155679, "recall": 0.992030910408114, "f1": 0.992930086410055, "roc_auc": 0.9995503578823617, "pr_auc": 0.9996107014519675, "f1_unwanted": 0.992930086410055, "macro_f1_3way": 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}}, "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]]}}}, "val_threshold": 0.5, "label_names": ["Legitimate", "Phishing", "Spam"], "stopped_by": "early_stopping", "resumed_from_step": null, "test": null} |
| {"run_name": "ft-weighted", "timestamp": "2026-10-09T05:55:09", "init": "pretrained:/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final", "dials": {"n_layers": 24, "frozen_layers": 0, "epochs_planned": 2, "epochs_run": 2.0, "loss": "weighted_cross_entropy", "focal_gamma": null, "lr": 3e-05, "batch_size": 32, "micro_batch": 16, "class_weights": "inverse_frequency", "synthetic": "off", "synthetic_rows": 0, "warmup_fraction": 0.06, "max_steps": null, "limit_rows": null, "seed": 42, "schedule": "linear_decay", "selection_metric": "val_f1_unwanted", "pooling": "cls", "num_labels": 3, "device": "cuda"}, "params": {"total": 337444867, "trainable": 337444867, "embeddings": 34080768, "encoder_layers": 302309376, "final_norm": 2048, "head": 1052675}, "steps_run": 10018, "n_train": 160263, "n_val": 15284, "train_seconds": 5013.9, "peak_vram_gb": 13.133, "best_epoch": 1, "best_step": 10000, "best_score": 0.99373795761079, "val": {"accuracy": 0.9931954985605862, "precision": 0.9911121787172712, "recall": 0.9963776865491427, "f1": 0.99373795761079, "roc_auc": 0.9997532357160727, "pr_auc": 0.9997920087331971, "f1_unwanted": 0.99373795761079, "macro_f1_3way": 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}}, "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]]}}}, "val_threshold": 0.5, "label_names": ["Legitimate", "Phishing", "Spam"], "stopped_by": "epochs_done", "resumed_from_step": null, "test": null} |
| {"run_name": "ft-focal", "timestamp": "2026-10-09T07:21:55", "init": "pretrained:/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final", "dials": {"n_layers": 24, "frozen_layers": 0, "epochs_planned": 2, "epochs_run": 2.0, "loss": "focal", "focal_gamma": 2.0, "lr": 3e-05, "batch_size": 32, "micro_batch": 16, "class_weights": null, "synthetic": "off", "synthetic_rows": 0, "warmup_fraction": 0.06, "max_steps": null, "limit_rows": null, "seed": 42, "schedule": "linear_decay", "selection_metric": "val_f1_unwanted", "pooling": "cls", "num_labels": 3, "device": "cuda"}, "params": {"total": 337444867, "trainable": 337444867, "embeddings": 34080768, "encoder_layers": 302309376, "final_norm": 2048, "head": 1052675}, "steps_run": 10018, "n_train": 160263, "n_val": 15284, "train_seconds": 5033.3, "peak_vram_gb": 13.133, "best_epoch": 1, "best_step": 8750, "best_score": 0.9951084002657166, "val": {"accuracy": 0.9947003402250719, "precision": 0.9954089646007007, "recall": 0.9948080173871046, "f1": 0.9951084002657166, "roc_auc": 0.9998186946414248, "pr_auc": 0.9998464119156345, "f1_unwanted": 0.9951084002657166, "macro_f1_3way": 0.9868751212108838, "per_class": {"Legitimate": {"precision": 0.9988533753762362, "recall": 0.99528706083976, "f1": 0.9970670291151013}, "Phishing": {"precision": 0.9853372434017595, "recall": 0.9882352941176471, "f1": 0.986784140969163}, "Spam": {"precision": 0.9618805590851334, "recall": 0.9921363040629095, "f1": 0.9767741935483871}}, "three_way": {"n": 8105, "accuracy": 0.994694632942628, "macro_f1": 0.9868751212108838, "per_class": {"Legitimate": {"precision": 0.9988533753762362, "recall": 0.99528706083976, "f1": 0.9970670291151013}, "Phishing": {"precision": 0.9853372434017595, "recall": 0.9882352941176471, "f1": 0.986784140969163}, "Spam": {"precision": 0.9618805590851334, "recall": 0.9921363040629095, "f1": 0.9767741935483871}}, "confusion": {"order": ["Legitimate", "Phishing", "Spam"], "rows_true_cols_pred": [[6969, 4, 29], [3, 336, 1], [5, 1, 757]]}, "phish_vs_spam_on_true_unwanted": {"n": 1103, "order": ["Phishing", "Spam"], "rows_true_cols_pred": [[339, 1], [1, 762]]}}}, "val_threshold": 0.5, "label_names": ["Legitimate", "Phishing", "Spam"], "stopped_by": "early_stopping", "resumed_from_step": null, "test": null} |
| {"run_name": "ft-synthetic", "timestamp": "2026-10-09T08:16:37", "init": "pretrained:/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final", "dials": {"n_layers": 24, "frozen_layers": 0, "epochs_planned": 2, "epochs_run": 1.232, "loss": "cross_entropy", "focal_gamma": null, "lr": 3e-05, "batch_size": 32, "micro_batch": 16, "class_weights": null, "synthetic": "on", "synthetic_rows": 2000, "warmup_fraction": 0.06, "max_steps": null, "limit_rows": null, "seed": 42, "schedule": "linear_decay", "selection_metric": "val_f1_unwanted", "pooling": "cls", "num_labels": 3, "device": "cuda"}, "params": {"total": 337444867, "trainable": 337444867, "embeddings": 34080768, "encoder_layers": 302309376, "final_norm": 2048, "head": 1052675}, "steps_run": 6250, "n_train": 162263, "n_val": 15284, "train_seconds": 3118.3, "peak_vram_gb": 13.131, "best_epoch": 0, "best_step": 5000, "best_score": 0.9926514877725575, "val": {"accuracy": 0.9920177963883801, "precision": 0.9903846153846154, "recall": 0.9949287611687998, "f1": 0.9926514877725575, "roc_auc": 0.9996055651398734, "pr_auc": 0.9996662445428656, "f1_unwanted": 0.9926514877725575, "macro_f1_3way": 0.9665378162175431, "per_class": {"Legitimate": {"precision": 0.9992783951508154, "recall": 0.988860325621251, "f1": 0.9940420644605555}, "Phishing": {"precision": 0.8805194805194805, "recall": 0.9970588235294118, "f1": 0.9351724137931035}, "Spam": {"precision": 0.9532237673830595, "recall": 0.9882044560943644, "f1": 0.9703989703989704}}, "three_way": {"n": 8105, "accuracy": 0.9891425046267736, "macro_f1": 0.9665378162175431, "per_class": {"Legitimate": {"precision": 0.9992783951508154, "recall": 0.988860325621251, "f1": 0.9940420644605555}, "Phishing": {"precision": 0.8805194805194805, "recall": 0.9970588235294118, "f1": 0.9351724137931035}, "Spam": {"precision": 0.9532237673830595, "recall": 0.9882044560943644, "f1": 0.9703989703989704}}, "confusion": {"order": ["Legitimate", "Phishing", "Spam"], "rows_true_cols_pred": [[6924, 41, 37], [1, 339, 0], [4, 5, 754]]}, "phish_vs_spam_on_true_unwanted": {"n": 1103, "order": ["Phishing", "Spam"], "rows_true_cols_pred": [[340, 0], [6, 757]]}}}, "val_threshold": 0.5, "label_names": ["Legitimate", "Phishing", "Spam"], "stopped_by": "early_stopping", "resumed_from_step": null, "test": null} |
| {"run_name": "ft-12L", "timestamp": "2026-10-09T08:54:49", "init": "pretrained:/home/nathank/BITS/dev/Phishing Model/checkpoints/pretrain/large-24L/final", "dials": {"n_layers": 12, "frozen_layers": 0, "epochs_planned": 2, "epochs_run": 1.747, "loss": "cross_entropy", "focal_gamma": null, "lr": 3e-05, "batch_size": 32, "micro_batch": 16, "class_weights": null, "synthetic": "off", "synthetic_rows": 0, "warmup_fraction": 0.06, "max_steps": null, "limit_rows": null, "seed": 42, "schedule": "linear_decay", "selection_metric": "val_f1_unwanted", "pooling": "cls", "num_labels": 3, "device": "cuda"}, "params": {"total": 186290179, "trainable": 186290179, "embeddings": 34080768, "encoder_layers": 151154688, "final_norm": 2048, "head": 1052675}, "steps_run": 8750, "n_train": 160263, "n_val": 15284, "train_seconds": 2118.2, "peak_vram_gb": 6.969, "best_epoch": 1, "best_step": 6250, "best_score": 0.9925057415689592, "val": {"accuracy": 0.9918869405914682, "precision": 0.9935866408518877, "recall": 0.9914271914996378, "f1": 0.9925057415689592, "roc_auc": 0.9995007118744352, "pr_auc": 0.9995737781814353, "f1_unwanted": 0.9925057415689592, "macro_f1_3way": 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}}, "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]]}}}, "val_threshold": 0.5, "label_names": ["Legitimate", "Phishing", "Spam"], "stopped_by": "early_stopping", "resumed_from_step": null, "test": null} |
| {"run_name": "ft-scratch", "timestamp": "2026-10-09T09:57:34", "init": "scratch", "dials": {"n_layers": 24, "frozen_layers": 0, "epochs_planned": 2, "epochs_run": 1.497, "loss": "cross_entropy", "focal_gamma": null, "lr": 3e-05, "batch_size": 32, "micro_batch": 16, "class_weights": null, "synthetic": "off", "synthetic_rows": 0, "warmup_fraction": 0.06, "max_steps": null, "limit_rows": null, "seed": 42, "schedule": "linear_decay", "selection_metric": "val_f1_unwanted", "pooling": "cls", "num_labels": 3, "device": "cuda"}, "params": {"total": 337444867, "trainable": 337444867, "embeddings": 34080768, "encoder_layers": 302309376, "final_norm": 2048, "head": 1052675}, "steps_run": 7500, "n_train": 160263, "n_val": 15284, "train_seconds": 3656.4, "peak_vram_gb": 13.133, "best_epoch": 0, "best_step": 5009, "best_score": 0.9874562778916898, "val": {"accuracy": 0.9863909971211725, "precision": 0.9863855421686747, "recall": 0.9885293407389519, "f1": 0.9874562778916898, "roc_auc": 0.9984844430897414, "pr_auc": 0.998618660839301, "f1_unwanted": 0.9874562778916898, "macro_f1_3way": 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}}, "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]]}}}, "val_threshold": 0.5, "label_names": ["Legitimate", "Phishing", "Spam"], "stopped_by": "early_stopping", "resumed_from_step": null, "test": null} |
| {"run_name": "ft-ce", "timestamp": "2026-10-09 09:59", "stage": "evaluate", "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-ce/best", "splits": ["test", "test3"], "num_labels": 3, "dev_run": false, "limit_rows": null, "val": null, "test": {"accuracy": 0.9495153968838179, "precision": 0.8610392664001881, "recall": 0.9404211607601438, "f1": 0.8989812200810113, "specificity": 0.9523694390715667, "roc_auc": 0.9874951859346837, "pr_auc": 0.9625515458938435, "recall_at_fpr_1pct": 0.7745249101181304, "recall_at_fpr_0_1pct": 0.35285053929121724, "confusion_matrix": {"tn": 11817, "fp": 591, "fn": 232, "tp": 3662}, "n": 16302, "threshold": 0.5, "lure_recall": 0.9958847736625515, "f1_unwanted": 0.8989812200810113, "threeway": null}, "test3": {"accuracy": 0.989751552795031, "precision": 0.9876847290640394, "recall": 0.9852579852579852, "f1": 0.986469864698647, "specificity": 0.992496248124062, "roc_auc": 0.9991504761389705, "pr_auc": 0.9985052105989761, "recall_at_fpr_1pct": 0.9868959868959869, "recall_at_fpr_0_1pct": 0.868959868959869, "confusion_matrix": {"tn": 1984, "fp": 15, "fn": 18, "tp": 1203}, "n": 3220, "threshold": 0.5, "lure_recall": 0.9925373134328358, "f1_unwanted": 0.986469864698647, "threeway": {"n": 3220, "accuracy": 0.986335403726708, "macro_f1": 0.9821678741985428, "macro_f1_present_classes": 0.9821678741985428, "per_class": {"Legitimate": {"precision": 0.991008991008991, "recall": 0.992496248124062, "f1": 0.9917520619845038, "support": 1999}, "Phishing": {"precision": 0.9806576402321083, "recall": 0.9731285988483686, "f1": 0.976878612716763, "support": 521}, "Spam": {"precision": 0.9771754636233951, "recall": 0.9785714285714285, "f1": 0.9778729478943612, "support": 700}}, "confusion_matrix_3x3": [[1984, 4, 11], [9, 507, 5], [9, 6, 685]], "kind_accuracy_on_true_unwanted": 0.9893529893529893}, "macro_f1_3way": 0.9821678741985428}, "latency_ms": {"gpu_bf16_avg": 9.89, "cpu_fp32_avg": 513.57}} |
| {"run_name": "ft-focal", "timestamp": "2026-10-09 10:46", "stage": "evaluate", "checkpoint": "/home/nathank/BITS/dev/Phishing Model/checkpoints/finetune/ft-focal/best", "splits": ["test", "test3"], "num_labels": 3, "dev_run": false, "limit_rows": null, "val": null, "test": {"accuracy": 0.9619065145380935, "precision": 0.8794342684906098, "recall": 0.9740626605033385, "f1": 0.9243328865602534, "specificity": 0.9580915538362347, "roc_auc": 0.9946343971962354, "pr_auc": 0.9847899987683836, "recall_at_fpr_1pct": 0.8954802259887006, "recall_at_fpr_0_1pct": 0.6497175141242938, "confusion_matrix": {"tn": 11888, "fp": 520, "fn": 101, "tp": 3793}, "n": 16302, "threshold": 0.5, "lure_recall": 0.9958847736625515, "f1_unwanted": 0.9243328865602534, "threeway": null}, "test3": {"accuracy": 0.989751552795031, "precision": 0.9892915980230642, "recall": 0.9836199836199836, "f1": 0.986447638603696, "specificity": 0.9934967483741871, "roc_auc": 0.9993325901279878, "pr_auc": 0.9988537821967886, "recall_at_fpr_1pct": 0.9868959868959869, "recall_at_fpr_0_1pct": 0.8787878787878788, "confusion_matrix": {"tn": 1986, "fp": 13, "fn": 20, "tp": 1201}, "n": 3220, "threshold": 0.5, "lure_recall": 1.0, "f1_unwanted": 0.986447638603696, "threeway": {"n": 3220, "accuracy": 0.9885093167701864, "macro_f1": 0.9867305252015051, "macro_f1_present_classes": 0.9867305252015051, "per_class": {"Legitimate": {"precision": 0.9900299102691924, "recall": 0.9934967483741871, "f1": 0.9917602996254682, "support": 1999}, "Phishing": {"precision": 0.9961240310077519, "recall": 0.9865642994241842, "f1": 0.991321118611379, "support": 521}, "Spam": {"precision": 0.9785100286532952, "recall": 0.9757142857142858, "f1": 0.977110157367668, "support": 700}}, "confusion_matrix_3x3": [[1986, 1, 12], [4, 514, 3], [16, 1, 683]], "kind_accuracy_on_true_unwanted": 0.9959049959049959}, "macro_f1_3way": 0.9867305252015051}, "latency_ms": {"gpu_bf16_avg": 10.08, "cpu_fp32_avg": 458.57}} |
|
|
