Training and Evaluating LLMs
Hello and welcome to the second article of my blog series on Generative AI and Large Language Models (LLMs)!
In the first blog post of this series, I shared fundamental information about Generative AI and Large Language Models (LLMs).
In this post, I will discuss the training process of LLMs, fine-tuning and instruction fine-tuning. Additionally, I will cover how to evaluate these models and which metric scores to use for their assessment.
Let’s get start!
Training LLM
The most crucial step in any project is accurately defining its purpose and scope. Once you have determined how the LLM should function in practice, the next step is to select the model you will work with. Choosing the right size and architecture of the LLM is essential to fully realize the project’s scope. Key considerations for model selection include:
- Foundation Model: A pretrained LLM
- Train Your Own Model: A custom LLM
