Closed joshua-zh closed 7 months ago
I ran two of the same models using brms, the default backend = "rstan" caused rstudio to abort, then I changed to backend = "cmdstanr", and the same model ran well.
The data and the model comes from stan website
t_long_CNSubset20red1_sub3_ord = read.csv("https://discourse.mc-stan.org/uploads/short-zrl/byihhT2MGE2yXgTZB1pg93wPxio.csv") t = brm(bf(y ~ mo(g_size) * mo(g_noise) * g_shape * g_interps), data = t_long_CNSubset20red1_sub3_ord, chains = 2, backend = "rstan")
Rstudio popped up the R Session Aborted. Within the R console, the model ran well; By the way, the example ran without any problems in Rstudio.
example(stan_model, package="rstan", run.dontrun = TRUE, verbose = TRUE)
t = brm(bf(y ~ mo(g_size) * mo(g_noise) * g_shape * g_interps), data = t_long_CNSubset20red1_sub3_ord, chains = 2, backend = "cmdstanr")
cmdstanr backend did not cause rstudio to crash.
Session information:
packageVersion("cmdstanr") [1] ‘0.6.1.9000’ packageVersion("brms") [1] ‘2.20.6’ packageVersion("rstan") [1] ‘2.33.1.9000’ R.version.string [1] "R version 4.3.1 (2023-06-16)"
packageVersion("cmdstanr") [1] ‘0.6.1.9000’
packageVersion("brms") [1] ‘2.20.6’
packageVersion("rstan") [1] ‘2.33.1.9000’
R.version.string [1] "R version 4.3.1 (2023-06-16)"
MacOS 14.1 sonoma
When I updated the R version to 4.3.2, the crash problem was solved.
I ran two of the same models using brms, the default backend = "rstan" caused rstudio to abort, then I changed to backend = "cmdstanr", and the same model ran well.
The data and the model comes from stan website
Rstudio popped up the R Session Aborted. Within the R console, the model ran well; By the way, the example ran without any problems in Rstudio.
cmdstanr backend did not cause rstudio to crash.
Session information:
MacOS 14.1 sonoma