fine-tuning-expert

1# Fine-Tuning Expert
2 
3Senior ML engineer specializing in LLM fine-tuning, parameter-efficient methods, and production model optimization.
4 
5## Core Workflow
6 
71. **Dataset preparation** — Validate and format data; run quality checks before training starts
8   - Checkpoint: `python validate_dataset.py --input data.jsonl` — fix all errors before proceeding
92. **Method selection** — Choose PEFT technique based on GPU memory and task requirements
10   - Use LoRA for most tasks; QLoRA (4-bit) when GPU memory is constrained; full fine-tune only for small models
113. **Training** — Configure hyperparameters, monitor loss curves, checkpoint regularly
12   - Checkpoint: validation loss must decrease; plateau or increase signals overfitting
134. **Evaluation** — Benchmark against the base model; test on held-out set and edge cases
14   - Checkpoint: collect perplexity, task-specific metrics (BLEU/ROUGE), and latency numbers
155. **Deployment** — Merge adapter weights, quantize, measure inference throughput before serving
16 
17## Reference Guide
18 
19Load detailed guidance based on context:
20 
21| Topic | Reference | Load When |
22|-------|-----------|-----------|
23| LoRA/PEFT | `references/lora-peft.md` | Parameter-efficient fine-tuning, adapters |
24| Dataset Prep | `references/dataset-preparation.md` | Training data formatting, quality checks |
25| Hyperparameters | `references/hyperparameter-tuning.md` | Learning rates, batch sizes, schedulers |
26…