We use W&B a lot for our research projects, and it's been super useful and has pretty much replaced TensorBoard (TB) for us. The killer features on top of TB is the ability to track your experiments (without keeping track of your log files on your computer -- i'm quite organized but that's a losing battle), and the ability to share training runs within a team. We do a lot of distributed training as well, and the system metrics they provide automatically are great for ensuring you're making the most of your GPU/CPU/memory.