Templates: Train an LLM

LLM Model Training

Now that you have generated your LLM Dataset, you can train your custom LLM Model.

1. Open the LLM Trainer Element settings and make the following adjustments
   
   
   
2. Base Model Architecture: The default model is great for creating a model quickly. Want to train something tailored to a specific idea? Check out our Supported LLM Base Models page to learn more about all the models in Navigator
3. Dataset Folder Path: Using the “Select Directory” button, choose the folder where you saved your LLM dataset during LLM Dataset Generation. Need a dataset? We've got two for you right here.
   1. Sci-Fi Novels
   2. Logistics Warehouse Management
4. Artifact Save Path: Using the “Select Directory” button, choose the folder where you would like to save your trained adapter.
5. Base Model Assets Path: Using the “Select Directory” button, choose the folder where you would like to save your base model.
6. Evaluator API Key: Add a Groq, OpenAI, Claude, or Gemini API key to enable the Faithfulness and Relevancy benchmarks in your training metrics. If you need a free API key, you can generate one for Groq here.
   
7. Batch Size: 4 is recommended for testing
8. Leave all other settings as the default.
9. You can now hit run. This process may take a while, so be patient.

For detailed breakdown on LLM Training check out our in-depth article here.