Choose between SFT and DPO
Choose the learner target that fits the distinction you want the model to learn.
Prerequisites
A training objective grounded in selected benchmark criteria and access to Weights training.
Steps
- For supervised fine-tuning, identify the target behavior an appropriate demonstration should teach.
- For preference optimization, identify a meaningful preference between responses to the same input and the rubric that explains it.
- Create the preparation with the intended Benchmark Version and supported method. Inspect the resulting target fields in Dataset.
- Check that the export profile, connected service, and model family support the method and material types before a training handoff.
Object and state changes
The preparation records the method and selected scope. Dataset and provider compatibility are separate checks.
Success criteria
Each example has a usable demonstration target or a meaningful preferred/rejected distinction for the chosen method.
Common failure modes
Choosing a method because a provider accepts the file; constructing preference pairs whose difference does not reflect the intended standard.