> ## 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 Quick Start

> Train your first specialized model from a ready dataset.

<Note>
  Before you begin, create a dataset with training entries. If you generated better targets with relabeling, wait for that relabel run to complete.
</Note>

<Steps>
  <Step title="Open Tuned Models">
    From the task, open **Tuned Models** and select **Train model**.
  </Step>

  <Step title="Choose the training data">
    Select a ready dataset, then choose the original outputs or a completed relabel run as the targets the model should learn.
  </Step>

  <Step title="Select a base model">
    Choose one of the [supported training models](/model-distillation/supported-models). When compute is available, train more than one candidate instead of assuming the largest model will perform best.
  </Step>

  <Step title="Keep or customize the defaults">
    The fine-tune name is optional. Leave the training configuration automatic for the first run, or expand customization to set batch size, peak learning rate, schedule, epochs, or LoRA parameters.
  </Step>

  <Step title="Start training">
    Select **Start training**. The model moves through **Queued** and **Training**, and Studio reports progress from 0 to 100%.
  </Step>

  <Step title="Use the deployed artifact">
    When the status becomes **Deployed**, the exact W\&B artifact appears in Studio and becomes available for evaluations and routing through `wandb-inference`.
  </Step>
</Steps>

Next, [evaluate the fine-tune](/model-distillation/studio/evaluations-quickstart) on held-out validation rows before sending it production traffic.

<Accordion title="API: Start training (POST /tasks/{alias}/finetunes)">
  Omit `model_config` to use the automatic training configuration:

  ```bash theme={"system"}
  curl --request POST \
    --url "https://distillation.training.wandb.ai/v1/tasks/ticket-classifier/finetunes" \
    --header "Authorization: Bearer $WANDB_API_KEY" \
    --header "Wandb-Entity: your-team" \
    --header "Content-Type: application/json" \
    --data "{
      \"dataset_id\": \"$DATASET_ID\",
      \"model_name\": \"ticket-classifier-qwen\",
      \"base_model\": \"Qwen/Qwen3.6-27B\"
    }"
  ```

  Poll the returned fine-tune until it is `deployed` or `failed`. See [Create a fine-tune](/model-distillation/reference/management).
</Accordion>