Fine-Tuning
Fine-tuning lets you customise an AI model with your own data so it performs better on the tasks that matter to you. You pick a base model and a training dataset, set a few training parameters, and launch a job that produces a tailored model. Use this section to start fine-tuning jobs and track the ones you've already run.
Available with Pro Plans
Anyone with can edit access can launch and manage fine-tunings
Start a fine-tuning
Click New to open the fine-tuning form. Select the base model and the training dataset, then personalise the job by entering the desired parameters:
| Field | Description |
|---|---|
| Name | A name to identify the fine-tuning job and its resulting model. |
| Description | Optional notes about the job's purpose. |
| Base model | The model to fine-tune, chosen from your AI Model Registry. |
| Dataset | The training dataset whose entries the model learns from. |
| Learning Rate | How large an adjustment the model makes at each training step. |
| Batch Size | The number of training examples processed together in one step. |
| Epochs | The number of times the training run passes over the full dataset. |
When you're ready, click Launch to start the job. The new fine-tuning then appears in the list, where you can follow its progress.
If you're unsure about Learning Rate, Batch Size or Epochs, hover the information icon next to each field for guidance, or start from the defaults and adjust based on results.
Browse fine-tunings
The Fine-Tuning list shows every job with columns for Name, Base model, Training dataset and Created at. When no jobs exist yet, the page invites you to add one.
- Search – Use the search box to filter jobs by name.
- Sort – Click the arrows next to any column header to sort the list by that column.