Early Stopping Patience

Problem

Determine the epoch where early stopping triggers. Track the best (lowest) validation loss seen; count consecutive epochs without a strict improvement and return the first index where that count reaches patience.

Return -1 if the run never triggers or the input is empty.

Hint

Reset the patience counter whenever a new best loss appears.

Test cases

case 1

in: [[1,0.9,0.85,0.87,0.88,0.89],2]

expected: 4

case 2

in: [[1,0.9,0.8],3]

expected: -1

case 3

in: [[1,1,1],1]

expected: 1

case 4

in: [[],2]

expected: -1

Starter codePython

def early_stopping_epoch(val_losses, patience):
    # Your code here
    pass

4 test cases · run your code against them in the editor