Validation Loss
Validation loss is a measure of error between the predicted outcomes by a machine learning model and the actual outcomes of a validation dataset. It is a key metric for evaluating a model's performance and for tuning hyperparameters.
Understanding Validation Loss
Unlike training loss, which is calculated during the model training phase, validation loss is computed on a separate, unseen dataset. It helps in determining how well a model generalizes to new data. A model with low training loss but high validation loss is likely overfitting.
![Lakera LLM Security Playbook](https://cdn.prod.website-files.com/65080baa3f9a607985451de3/65254b087d7b8af4624a0982_CTA%20Image.webp)
Download this guide to delve into the most common LLM security risks and ways to mitigate them.
![](https://cdn.prod.website-files.com/65080baa3f9a607985451de3/650d8986cacb870bc87f91f2_Spacer%20Bottomr.webp)
untouchable mode.
Lakera Guard protects your LLM applications from cybersecurity risks with a single line of code. Get started in minutes. Become stronger every day.
Several people are typing about AI/ML security. 
Come join us and 1000+ others in a chat that’s thoroughly SFW.