Machine Learning Software Engineer 🤖 Advocating AI @LightningAI ⚡️ Creator of @GradsFlow 🚀
May 9, 2022 • 4 tweets • 3 min read
Day-4 🧵: Avoid overfitting with Early Stopping callback! 🚀
@PyTorchLightnin Early stopping callback automatically stops training once it detects that there is no improvement in the monitored metrics (for example validation accuracy). ⚡️
1/3
It provides additional parameters that stop training at extreme points:
1️⃣ stopping_threshold
Stop training if the monitored metric has reached this threshold.
2️⃣ divergence_threshold
Stop training if the monitored metric is worse than this threshold.
2/3