Codex
|
72ea72b49c
|
feat(training): LoRA pipeline with human-in-the-loop verification
- PEFT/LoRA fine-tuning (r=8, alpha=16) — only 1.2% params trainable
- Data augmentation: templates + crypto slang (5x from 177→885 samples)
- Human-in-the-loop CLI verification with persistent JSONL log
- Disk-conscious: save_total_limit=1, ~6MB adapter size
- CPU-friendly, single-file deployment
- Tested: 1 epoch in ~4min on CPU, 6MB adapter
|
2026-09-26 18:54:41 +02:00 |
|