Explainer
Overfitting
Fitting training examples too closely so performance on new inputs suffers.
Watch two curves. Training loss is measured on examples used to update the weights. Validation loss is measured on held-out examples. If training loss falls while validation loss rises, the model fits training examples better but predicts held-out examples worse. That is an overfitting warning: fitting the training set too closely can hurt performance on new inputs (Google). Persistently poor results on both sets can indicate underfitting. Early stopping ends a run when a chosen validation measure stops improving. Save checkpoints, snapshots during training, and compare them on the intended task; the last one need not be best (Microsoft).
Going deeper
Loss is not the task. InstructGPT's validation loss overfit after 1 epoch, yet training for more epochs still improved reward model scores and human preference (Ouyang et al. 2022). Pick checkpoints by task evaluations, not loss alone. Perplexity, the exponential of the average loss, carries the same information on another scale: a loss of 2.0 is a perplexity of 7.39. It depends on the tokenizer, so it cannot be compared across models with different tokenizers (Hugging Face).
In the long read: What happens during training. Every related term is in Fine-tuning, every concept.
Read next: Learning rate