What does “Training Loss” mean?

A mathematical objective that quantifies prediction error during training.

Performance degradation over time as real-world conditions diverge from training assumptions.

Additional inference computation used during response generation to improve quality or reasoning.

A shift in real-world input data over time that can degrade model performance.

A configuration value set before training, such as learning rate, batch size, or depth.

The latest point in time reflected in a model's training data.