Different glmmML output on different virtual machine (Microsoft Azure Machine Learning compute instance)

[gohry]

Hi, I am new to using an online platform for RStudio via the compute instance in Microsoft Azure Machine Learning.

I run glmmML with the same dataset separately on two virtual machines:

1. 1 core, 3.5GB RAM, 7GB storage
2. 2 cores, 7GB RAM, 14GB storage

For the first virtual machine, I have no problem running glmmML and upon repeated runs, I obtain consistent same outputs. The session info is:

sessionInfo()
R version 3.6.3 (2020-02-29)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 16.04.7 LTS

Matrix products: default
BLAS/LAPACK: /opt/intel/compilers_and_libraries_2018.2.199/linux/mkl/lib/intel64_lin/libmkl_rt.so

locale:
[1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
[5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8 LC_PAPER=en_US.UTF-8 LC_NAME=C
[9] LC_ADDRESS=C LC_TELEPHONE=C LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C

attached base packages:
[1] stats graphics grDevices utils datasets methods base

other attached packages:
[1] forcats_0.5.0 stringr_1.4.0 dplyr_1.0.2 purrr_0.3.4 readr_1.4.0 tidyr_1.1.2 tibble_3.0.3 ggplot2_3.3.2
[9] tidyverse_1.3.0 glmmML_1.1.1

loaded via a namespace (and not attached):
[1] Rcpp_1.0.5 cellranger_1.1.0 pillar_1.4.6 compiler_3.6.3 dbplyr_1.4.4 tools_3.6.3 jsonlite_1.7.1
[8] lubridate_1.7.9 lifecycle_0.2.0 gtable_0.3.0 pkgconfig_2.0.3 rlang_0.4.7 reprex_0.3.0 cli_2.0.2
[15] DBI_1.1.0 rstudioapi_0.11 haven_2.3.1 withr_2.3.0 xml2_1.3.2 httr_1.4.2 fs_1.5.0
[22] generics_0.0.2 vctrs_0.3.4 hms_0.5.3 grid_3.6.3 tidyselect_1.1.0 glue_1.4.2 R6_2.4.1
[29] fansi_0.4.1 readxl_1.3.1 modelr_0.1.8 blob_1.2.1 magrittr_1.5 backports_1.1.10 scales_1.1.1
[36] ellipsis_0.3.1 rvest_0.3.6 assertthat_0.2.1 colorspace_1.4-1 stringi_1.5.3 munsell_0.5.0 broom_0.7.1
[43] crayon_1.3.4

However, when I am running with the second virtual machine, I have convergence problem running glmmML, with the following message. Besides, upon repeated runs, I obtain different results for every separate run of glmmML.

Warning message:
glm.fit: algorithm did not converge

The session info for the second virtual machine is:

sessionInfo()
R version 3.6.3 (2020-02-29)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 16.04.7 LTS

Matrix products: default
BLAS/LAPACK: /opt/intel/compilers_and_libraries_2018.2.199/linux/mkl/lib/intel64_lin/libmkl_rt.so

locale:
[1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8 LC_MONETARY=en_US.UTF-8
[6] LC_MESSAGES=en_US.UTF-8 LC_PAPER=en_US.UTF-8 LC_NAME=C LC_ADDRESS=C LC_TELEPHONE=C
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C

attached base packages:
[1] stats graphics grDevices utils datasets methods base

other attached packages:
[1] glmmML_1.1.1 forcats_0.5.0 stringr_1.4.0 dplyr_1.0.2 purrr_0.3.4 readr_1.4.0 tidyr_1.1.2 tibble_3.0.3
[9] ggplot2_3.3.2 tidyverse_1.3.0

loaded via a namespace (and not attached):
[1] Rcpp_1.0.5 cellranger_1.1.0 pillar_1.4.6 compiler_3.6.3 dbplyr_1.4.4 tools_3.6.3 jsonlite_1.7.1 lubridate_1.7.9
[9] lifecycle_0.2.0 gtable_0.3.0 pkgconfig_2.0.3 rlang_0.4.9 reprex_0.3.0 cli_2.2.0 DBI_1.1.0 rstudioapi_0.11
[17] haven_2.3.1 withr_2.3.0 xml2_1.3.2 httr_1.4.2 fs_1.5.0 generics_0.1.0 vctrs_0.3.6 hms_0.5.3
[25] grid_3.6.3 tidyselect_1.1.0 glue_1.4.2 R6_2.5.0 fansi_0.4.1 readxl_1.3.1 modelr_0.1.8 blob_1.2.1
[33] magrittr_2.0.1 backports_1.2.1 scales_1.1.1 ellipsis_0.3.1 rvest_0.3.6 assertthat_0.2.1 colorspace_1.4-1 stringi_1.5.3
[41] munsell_0.5.0 broom_0.7.1 crayon_1.3.4

Both sessionInfo() have shown the same R version, platform and BLAS/LAPACK...The attached packages are also having the same versions. Can anyone help on why is there such a huge difference of glmmML output when running on different virtual machines (despite the same R version and platform used)?

Thanks in advanced if anyone could help on this!