It’s starting off from something that finished sampling.
It looks reasonable, but a couple problems:
-
If warmup hadn’t finished, then you wouldn’t have a metric.
-
I don’t know if there’s any way to cleanly stop a cmdstanpy job if things get interrupted partway through (I don’t know how spot instances work).
-
I’m scared partial output might break this process.
There’s a checkpointing thread over here that has some info: Current state of checkpointing in Stan - #13 by bbbales2
There is something in cmdstan called the diagnostic file
(I think recently [last few days] it has been renamed the latent dynamics file, but I don’t know if that’s made it to cmdstanpy yet) that could be used to do this.
@mitzimorris is there a way to provide a stepsize per-chain in cmdstanpy?