Classic overfitting or something else

Classic overfitting if the curves separate smoothly. If validation loss jumps around, suspect the split instead: leakage between sets, or a validation set too small to be stable. Plot both losses per epoch before touching regularisation.

Seed every source of randomness, pin the library versions, and disable nondeterministic kernels on the GPU. Even then expect small differences from floating point order; the goal is results that agree within noise, not bitwise equality.

The reporting layer, until something forces it. It is the part that feels productive to build and the part nobody opens twice.