Implement Early Stopping Based on Validation Loss

Create a function to decide when to stop training a model early based on a list of validation losses. The early stopping criterion should stop training if the validation loss hasn't improved for a specified number of epochs (patience), and only count as improvement if the loss decreases by more than a certain threshold (min_delta). Your function should return the epoch to stop at and the best epoch, where an improvement is only recorded when the loss decreases by more than min_delta from the previous best.

from typing import Tuple

def early_stopping(val_losses: list[float], patience: int, min_delta: float) -> Tuple[int, int]:
    # Your code here
    pass