Two days of kernel debugging ended at one default value

Browser training plateaued near a loss of 2.45. The curve was smooth enough to look like a model or kernel limit. The WebGPU kernels were not the cause. The browser used a learning rate of 3e-3 while the Python reference used 3e-4. The default had drifted by a factor of ten. Kernel parity tests covered the numerical operations, but nothing... Weiterlesen