> ## Documentation Index
> Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Fine-tuning

> Train supported base models from original or relabeled dataset outputs.

Fine-tuning creates a task-specific model through W\&B Serverless Training and records the resulting hosted artifact in Studio.

<Card title="Train your first model" href="/model-distillation/studio/fine-tuning-quickstart" arrow="true">
  Choose a dataset, base model, and training configuration in Studio.
</Card>

## Supported base models

See [Supported training models](/model-distillation/supported-models) for the current list and selection guidance. A model retained by an older fine-tune can remain visible even if it leaves the new-training list.

## Create a fine-tune

Choose:

* a ready dataset with training rows;
* original outputs or a completed relabel run;
* a base model;
* an optional fine-tune name;
* optional training parameters.

Names are normalized to lowercase hyphenated identifiers. When omitted, Studio generates a readable name.

## Training parameters

Open the advanced configuration only when you need control over:

| Field                      | Meaning                                                           |
| -------------------------- | ----------------------------------------------------------------- |
| Maximum examples           | Deterministic cap on training rows; validation is not capped      |
| Batch size                 | Positive integer or `auto`                                        |
| Peak learning rate         | Positive scalar used to build the default schedule                |
| Learning-rate schedule     | Explicit non-negative value for every optimizer step              |
| Assistant turns            | Train on all assistant turns or only the last turn                |
| Experimental configuration | Serverless Training options not yet modeled as first-class fields |

With a scalar peak learning rate, Model Distillation creates the same schedule used by the ART SFT helper: 10% linear warmup followed by linear decay to zero. Supplying a full list preserves it exactly.

## Status and artifacts

Fine-tunes move through **Queued**, **Training**, **Deployed**, or **Failed**. Training progress is reported from 0 to 100%. A deployed model includes an exact W\&B artifact reference and is immediately selectable through `wandb-inference` for evaluations and routing.

Deleting the Studio record does not delete the W\&B run or hosted artifact.

<Accordion title="API: List training jobs and artifacts (GET /tasks/{alias}/finetunes)">
  Use this request to find progress, terminal status, and the artifact reference used in evaluations and routing:

  ```bash theme={"system"}
  curl --url "https://distillation.training.wandb.ai/v1/tasks/ticket-classifier/finetunes" \
    --header "Authorization: Bearer $WANDB_API_KEY" \
    --header "Wandb-Entity: your-team"
  ```

  To start a job, use the request in [Fine-tuning Quick Start](/model-distillation/studio/fine-tuning-quickstart). See [List fine-tunes](/model-distillation/reference/management) for this operation.
</Accordion>