model training and scenarios
Common challenges in a model training are 1. overfitting - high train accuracy, terrible production performance Red flag signals Train accuracy 98%+, val accuracy 65–70% Train loss keeps falling, val loss starts rising (divergence point) Large gap between train F1 and val F1 Model memorises noise — shuffling labels barely changes train loss Primary metrics to watch Train/val loss gap Generalisation gap Val accuracy Learning curves Val F1 Watch the gap , not the absolute numbers. Train acc 98% is fine if val acc is also 94%. The gap is the signal. Primary metrics to watch Train/val loss gap Generalisation gap Val accuracy Learning curves Val F1 Watch the gap , not the absolute numbers. Train acc 98% is fine if val acc is also 94%. The gap is the signal. This is what a overfitting learning curve graph looks like. As you can see the generalization gap higher than 0.15 is a red flag. In our case, it is 0.426. One more thing to note is the red line will diverge and ...