Validation Accuracy
A metric in machine learning that measures the correctness of a model's classification decisions on a validation set. It is commonly used for model selection and checkpoint selection.
Timeline (last 90 days)
Validation loss (such as cross-entropy) measures the difference between the model's predicted probability distribution and the true labels, while validation accuracy (or F1) measures the correctness of hard classification decisions; the two are not always monotonically in sync.
The checkpoint selected by the lowest-loss criterion and the checkpoint selected by the highest-accuracy criterion may be models from different stages of training, so their test performance may naturally differ.
All Facts (2)
Validation loss (such as cross-entropy) measures the difference between the model's predicted probability distribution and the true labels, while validation accuracy (or F1) measures the correctness of hard classification decisions; the two are not always monotonically in sync.
50%UnverifiedThe checkpoint selected by the lowest-loss criterion and the checkpoint selected by the highest-accuracy criterion may be models from different stages of training, so their test performance may naturally differ.
50%