Codex
|
27089a4853
|
feat(training): LoRA sentiment + emotion pipelines complete
- Sentiment LoRA (FinBERT): 5 epochs, early stopping, 6.2MB adapter
- Emotion LoRA (DistilRoBERTa): 5 epochs, weighted loss, 8.1MB adapter
- Both with early stopping (patience=3, threshold=0.001)
- Data augmentation: templates + crypto slang
- Human-in-the-loop verification CLI
- Disk-conscious: save_total_limit=1, ~6-8MB each
|
2026-09-26 19:58:48 +02:00 |
|