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

sentiment_engine/training/requirements-lora.txt

@@ -0,0 +1,8 @@
+# Minimal requirements for LoRA pipeline (CPU-friendly)
+torch==2.3.0 --index-url https://download.pytorch.org/whl/cpu
+transformers==4.44.0
+peft==0.12.0
+datasets==2.20.0
+accelerate==0.33.0
+scikit-learn==1.5.0
+numpy==1.26.0