tensor

Run this anywhere: >>> 0.1 + 0.2 0.30000000000000004 >>> 0.1 + 0.2 == 0.3 False And in real training runs, this happens: step 39,998 loss 2.41 step 39,999 loss 2.40 step 40,000 loss nan Both outputs have the same cause: the way computers store numbe…

Figure 1. the program this whole series is about.