search

h2oai / h2o-3

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
http://h2o.ai
Apache License 2.0
6.87k stars 1.99k forks source link

xgboost grow_policy is not working properly under gpu backend #11733

Open exalate-issue-sync[bot] opened 1 year ago

exalate-issue-sync[bot] commented 1 year ago

The 'lossguide' grow_policy used with h2o.xgboost does not appear to work under a gpu backend. I have tried updating the drivers and completely reinstalling the CUDA toolkit and while the algorithm will run, it comes back with a completely underfit model (AUC of .5). The cpu backend appears to work as intended.

My R session info is:

R version 3.4.1 (2017-06-30) Platform: x86_64-pc-linux-gnu (64-bit) Running under: Ubuntu 16.04.3 LTS

Matrix products: default BLAS: /usr/lib/openblas-base/libblas.so.3 LAPACK: /usr/lib/libopenblasp-r0.2.18.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] bindrcpp_0.2 dplyr_0.7.2 readr_1.1.1 h2o_3.14.0.2

loaded via a namespace (and not attached): [1] Rcpp_0.12.12 lubridate_1.6.0 assertthat_0.2.0 bitops_1.0-6 R6_2.2.2 jsonlite_1.5 magrittr_1.5 stringi_1.1.5
[9] rlang_0.1.2 data.table_1.10.5 tools_3.4.1 stringr_1.2.0 glue_1.1.1 RCurl_1.95-4.8 hms_0.3 compiler_3.4.1
[17] pkgconfig_2.0.1 bindr_0.1 tibble_1.3.3

Corresponding Nvidia SMI:

+-----------------------------------------------------------------------------+ | NVIDIA-SMI 375.66 Driver Version: 375.66 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | 0 GeForce GTX 108... Off | 0000:17:00.0 Off | N/A | | 0% 46C P8 15W / 250W | 500MiB / 11172MiB | 0% Default | | 1 GeForce GTX 108... Off | 0000:66:00.0 On | N/A | | 0% 29C P8 14W / 250W | 75MiB / 11171MiB | 0% Default |

hasithjp commented 1 year ago

JIRA Issue Migration Info

Jira Issue: PUBDEV-4855 Assignee: New H2O Bugs Reporter: Stewart Bobbitt State: Open Fix Version: N/A Attachments: N/A Development PRs: N/A