Quite the opposite, GPUs running at a stable rate degrade less than GPU that continuously hit highs and lows (like it would happen on a gaming rig).
After digging around a bit I found an unverified claim from 2024 that GPUs in datacenters have a lifespan of 1-3 years
https://www.tomshardware.com/pc-components/gpus/datacenter-g...
Others say that moderate load means a lifespan of ~5 years
Not sure what that means but I would assume that a datacenter will start replacing a node once the error rate hits a certain threshold without really investigating why it failed, so the practical lifespan may be shorter than 5 years even if it would technically still be usable enough
Normal use means loading data into the GPU for each batch. The load is not even, though training might be worse than "production".