Edit ‘the_seventy_maxims_of_maximally_effective_machine_learning_engineers’

This commit is contained in:
osmarks 2025-03-22 11:01:04 +00:00 committed by wikimind
parent 895bef5ec3
commit 66814844ca

View File

@ -33,7 +33,7 @@ Based on [[https://schlockmercenary.fandom.com/wiki/The_Seventy_Maxims_of_Maxima
*. Only overfitters prosper (temporarily).
*. Any model is production-ready if you can containerize it.
*. If youre logging metrics, youre being audited.
*. If youre seeing NaN, you need a smaller learning rate.
*. If youre leaving GPUs unused, you need a bigger model.
*. That which does not break your model has made a suboptimal adversarial example.
*. When the loss plateaus, the wise call for more data.
*. There is no “overkill.” There is only “more tokens” and “CUDA out of memory.”