La pérdida de entrenamiento es el valor de una función de pérdida medido sobre los datos de entrenamiento en un punto concreto del proceso de entrenamiento. Ayuda a indicar qué tan bien el modelo se ajusta a los ejemplos de los que aprende, pero por sí sola no demuestra una buena generalización.
A metric representing a model's loss during a particular training iteration. For example, suppose the loss function is Mean Squared Error. Perhaps the training loss (the Mean Squared Error) for the 10th iteration is 2.2, and the training loss for the 100th iteration is 1.9. A loss curve plots training loss versus the number of iterations. A loss curve provides the following hints about training: - A downward slope implies that the model is improving. - An upward slope implies that the model is getting worse. - A flat slope implies that the model has reached convergence. For example, the following somewhat idealized loss curve shows: - A steep downward slope during the initial iterations, which implies rapid model improvement. - A gradually flattening (but still downward) slope until close to the end of training, which implies continued model improvement at a somewhat slower pace then during the initial iterations. - A flat slope towards the end of training, which suggests convergence. !The plot of training loss versus iterations. This loss curve starts with a steep downward slope. The slope gradually flattens until the slope becomes zero. Although training loss is important, see also generalization.