When & How to Fine-Tune

Customizing Model Behavior

Fine-tuning trains an existing OpenAI model on your own dataset to customize its behavior, tone, format, or domain knowledge. It does NOT add new knowledge — it adjusts HOW the model responds.

Decision Framework

Fine-Tuning Workflow

1. Prepare Data: Create a JSONL file of example conversations
2. Upload: Upload the training file via the Files API
3. Train: Create a fine-tuning job specifying the base model
4. Evaluate: Test the fine-tuned model against your eval set
5. Deploy: Use your custom model ID in API calls

// Training data format (JSONL):
{"messages": [
  {"role": "system", "content": "You are a concise legal assistant."},
  {"role": "user", "content": "Summarize this contract clause..."},
  {"role": "assistant", "content": "Key terms: ..."}
]}

// Create fine-tuning job:
const job = await openai.fineTuning.jobs.create({
  training_file: "file-abc123",
  model: "gpt-5.4-mini",
  hyperparameters: { n_epochs: 3 }
});

Best Practices

• Start with 50-100 high-quality examples — quality over quantity
• Always create a validation set (20% of data) to detect overfitting
• Fine-tune the smallest model that meets your needs (Mini > Pro)
• Use checkpoints to save intermediate states