Fine-Tuning Workflow

Learn how to fine-tune Gemma models for your specific tasks using Facet’s training service

Fine‑tune a Gemma model on your domain data with a simple, repeatable flow. You’ll pick a base model, choose a training method (SFT, DPO/ORPO, or GRPO), and run efficiently with Full, LoRA, or QLoRA depending on resources. Vision variants support text+image.

1. Prepare your dataset

   Process data into conversation or preference format using the dataset preprocessing guide.

   Verify a small sample looks correct before training.

2. Select base model and method

   Pick a Gemma size that fits your budget, then choose SFT (supervised), DPO/ORPO (preference), or GRPO (reasoning with rewards).

3. Enable PEFT and quantization if needed

   Start with QLoRA for strong results on modest hardware; use Full finetune only when you need maximal capacity.

4. Launch and monitor

   Start the job and watch training/validation signals to catch issues early.

5. Evaluate and iterate

   Test the model, compare to the baseline, and iterate on data or settings.

Next: open the Training guide for step‑by‑step configuration details.