Have a story about / support for experiment tracking: graphs of observables e.g. loss, device health

[lukstafi]

This needn't be the core library though...

[lukstafi]

I thought of supporting numerical logging in ppx_minidebug, it's one direction of resolving this issue.

[lukstafi]

W&B is the gold standard. Some ideas outside the Weights and Biases space:

• Ketrew: Keep Track of Experimental Workflows, not machine-learning specific, but an OCaml library already, might turn out a great match
• labml: Monitor deep learning model training and hardware usage from mobile, Python API, MongoDB for the monitoring
• Aim 💫 — An easy-to-use & supercharged open-source experiment tracker. -- would need to integrate via Python