# Phishing detector — v2 config (DistilBERT rework).
#
# v2.1 update (2026-06-19): the v2 run passed the §8 in-distribution gates but
# missed half the real .eml acceptance phishing (FN rate 0.50). Fixes landed in
# the data/preprocess layer (no hyperparameter change needed):
#   A1 — clean_text(keep_domains=True): URL host + email domain kept as signal
#        (lookalike domains / odd TLDs) instead of an opaque [URL].
#   B1 — synthetic augmentation: prepare adds 600 rows/class (header-complete,
#        both classes) covering BEC / fake-invoice / brand- AND IT-helpdesk
#        credential tactics the corpora miss. Tune via --augmentation-size.
#   B2 — input is now {sender_domain} [SEP] {subject} [SEP] {body} (was body-only);
#        leak-safe because the [SEP] scaffolding is always present and the
#        augmentation gives BOTH classes realistic headers.
#   Real-world promotion is now also gated on the .eml acceptance set
#   (src/eval/acceptance_phishing.py), not just the in-distribution §8 metrics.
#
# Why v2 (see feat/phishing-distilbert-v2 analysis, 2026-06-18):
#   v1.0 passed test gates (recall 0.970 / precision 0.928) but over-flagged on
#   real .eml at inference. Root causes addressed here:
#     #1 Base model  : distilbert-base-uncased — on-spec (ML_PIPELINE.md §3, mBERT
#                      dropped: data is English-only; DistilBERT is faster on CPU
#                      and ~3× smaller, easing the 500 ms gate + checkpoint size).
#     #4 Class weight : multiplier dropped 3.0 -> 1.0. v1 stacked balanced (inverse-
#                      frequency) AND a 3× multiplier => ~6× gradient pressure on
#                      phishing, saturating its probability for almost any input.
#                      Pure inverse-frequency now; the THRESHOLD does the recall
#                      work, not the loss.
#     #5 Early stop   : monitor f1_phishing, not recall_phishing. Monitoring raw
#                      recall picked the most trigger-happy checkpoint; F1 balances
#                      recall against precision. Recall is still guaranteed by the
#                      eval-time threshold + gate.
#   (#2 legit diversity + #3 body-only input are in loaders.py / preprocess.py.)
#
# Run via:
#   make data-phishing
#   make train-phishing config=configs/phishing_v2.yaml

model_type: phishing
model_name: distilbert-base-uncased   # §3 decision: English-only data, on-spec

dataset: ealvaradob/phishing-dataset       # primary phishing training data (HF)
legit_source: emails.csv                   # Enron corpus — negative class source

num_labels: 2   # legit (0) | phishing (1)  — matches PHISHING_LABELS in constants.py

hyperparameters:
  learning_rate: 2.0e-5         # AdamW (mirrors priority protocol, ML_PIPELINE.md §3)
  weight_decay: 0.01
  batch_size: 16
  gradient_accumulation_steps: 1
  num_epochs: 4                 # 3–5 with early stopping
  warmup_ratio: 0.10
  lr_scheduler_type: linear
  max_seq_length: 512
  # Early stopping on F1 — balances recall vs precision (fix #5). Recall is still
  # enforced by the post-training threshold + the >=0.95 eval gate.
  early_stopping_metric: f1_phishing
  early_stopping_patience: 2
  class_weights: balanced                # inverse-frequency base weights from train dist
  phishing_class_multiplier: 1.0         # fix #4: no extra stacking — let threshold drive recall
  mixed_precision: bf16                  # falls back to fp16 / none as needed

seed: 42

output_dir: checkpoints/phishing_v2

wandb:
  project: priormail
  tags:
    - model:phishing
    - stage:exp

# --- run provenance (auto-recorded) ---
_git_sha: 7cdeae7
_git_dirty: False
_trained_at: 2026-06-19T03:00:44