Features
Fine-Tuning
Fine-tune open-source and proprietary LLMs straight from the FinetuneDB platform using production logs or uploaded datasets for a streamlined fine-tuning process.
![Hero Light](https://mintlify.s3-us-west-1.amazonaws.com/finetunedb/images/finetune-compact.webp)
![Hero Dark](https://mintlify.s3-us-west-1.amazonaws.com/finetunedb/images/finetune-compact.webp)
Fine-tuning Step-by-Step
FinetuneDB allows you to train, evaluate, and deploy your models all within one platform. Follow these steps to fine-tune a new model:
- Select a Dataset: Start by creating a new dataset or selecting an existing one.
- Initiate Fine-tuning: Click “Fine-tune model” in the dataset overview or in the editor interface.
- Select a Base Model: Choose the base model for fine-tuning.
- Configure Settings: Optionally adjust hyperparameters such as epochs, batch size, and learning rate multiplier.
- Start Training: Click “Deploy” to begin the fine-tuning process.
The training duration can range from a few minutes to several hours, depending on the model size and data volume. You will receive a notification on the platform once the training is complete.
![Hero Light](https://mintlify.s3-us-west-1.amazonaws.com/finetunedb/images/finetune-notification.webp)
![Hero Dark](https://mintlify.s3-us-west-1.amazonaws.com/finetunedb/images/finetune-notification.webp)