[chibi@rhel8 ~]$ sudo nvidia-docker run --rm -ti nvcr.io/nvidia/tensorflow:19.04-py3
                                                                                
================
== TensorFlow ==
================

NVIDIA Release 19.04 (build 6132408)
TensorFlow Version 1.13.1

Container image Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
Copyright 2017-2019 The TensorFlow Authors.  All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION.  All rights reserved.
NVIDIA modifications are covered by the license terms that apply to the underlying project or file.

NOTE: MOFED driver for multi-node communication was not detected.
      Multi-node communication performance may be reduced.

NOTE: The SHMEM allocation limit is set to the default of 64MB.  This may be
   insufficient for TensorFlow.  NVIDIA recommends the use of the following flags:
   nvidia-docker run --shm-size=1g --ulimit memlock=-1 --ulimit stack=67108864 ...

root@71bff3d91e1f:/workspace# ls
README.md  docker-examples  nvidia-examples
root@71bff3d91e1f:/workspace# cd nvidia-examples
root@71bff3d91e1f:/workspace/nvidia-examples# ls
NCF              bert                 cnn           ssdv1.2
OpenSeq2Seq      big_lstm             gnmt_v2       tensorrt
UNet_Industrial  build_imagenet_data  resnet50v1.5
root@71bff3d91e1f:/workspace/nvidia-examples# cd big_lstm
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm# ls
1b_word_vocab.txt  data_utils_test.py         language_model_test.py
README.md          download_1b_words_data.sh  model_utils.py
__init__.py        hparams.py                 run_utils.py
common.py          hparams_test.py            single_lm_train.py
data_utils.py      language_model.py          testdata
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm# ./download_1b_words_data.sh
Please specify root of dataset directory: data

Success: dataset root dir validated

--2020-02-03 20:13:18--  http://www.statmt.org/lm-benchmark/1-billion-word-language-modeling-benchmark-r13output.tar.gz
Resolving www.statmt.org (www.statmt.org)... 129.215.197.184
Connecting to www.statmt.org (www.statmt.org)|129.215.197.184|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1792209805 (1.7G) [application/x-gzip]
Saving to: ‘1-billion-word-language-modeling-benchmark-r13output.tar.gz’

1-billion-word-lang 100%[===================>]   1.67G   936KB/s    in 41m 59s

2020-02-03 20:55:17 (695 KB/s) - ‘1-billion-word-language-modeling-benchmark-r13output.tar.gz’ saved [1792209805/1792209805]

1-billion-word-language-modeling-benchmark-r13output/
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00024-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00057-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00055-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00096-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00081-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00033-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00072-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00082-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00018-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00008-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00059-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00005-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00091-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00062-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00031-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00095-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00076-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00006-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00038-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00015-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00087-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00021-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00049-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00009-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00027-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00056-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00046-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00032-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00029-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00088-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00085-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00011-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00012-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00067-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00003-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00093-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00050-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00053-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00044-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00019-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00066-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00028-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00045-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00039-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00071-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00052-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00078-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00037-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00002-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00014-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00048-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00017-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00004-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00077-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00080-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00020-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00051-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00016-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00079-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00043-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00068-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00099-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00064-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00034-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00054-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00040-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00070-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00063-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00041-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00083-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00061-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00073-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00094-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00030-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00060-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00035-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00023-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00042-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00025-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00090-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00089-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00065-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00075-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00022-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00026-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00098-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00084-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00010-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00069-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00013-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00092-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00036-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00097-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00007-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00074-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00001-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00047-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00086-of-00100
1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00058-of-00100
1-billion-word-language-modeling-benchmark-r13output/.svn/
1-billion-word-language-modeling-benchmark-r13output/.svn/tmp/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/de/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/de/de102cd0c91cd19e6612f0840e68a2f20ba8134c.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/de/deed1b75d3bd5cc36ae6aeb85d56680b892b7948.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/86/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/86/86c58db52fbf362c5bc329afc33b8805085fcb0d.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/9f/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/9f/9f2882e21f860a83ad6ea8898ebab140974ed301.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/bc/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/bc/bcdbc523ee7488dc438cab869b6d5e236578dbfa.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/d2/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/d2/d2718bc26d0ee0a213d7d4add99a304cb5b39ede.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/c5/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/c5/c5b24f61479da923123d0394a188da922ea0359c.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/11/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/11/116d6ea61730d8199127596b072e981338597779.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/b0/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/b0/b0e26559cfe641245584a9400b35ba28d64f1411.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/d3/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/d3/d3ae508e3bcb0e696dd70aecd052410f1f7afc1d.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/9e/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/9e/9e148bd766e8805e0eb97eeae250433ec7a2e996.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/31/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/31/31b645a482e0b81fda3c567cada307c6fcf7ec80.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/da/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/da/da39a3ee5e6b4b0d3255bfef95601890afd80709.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/c1/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/c1/c1ed42c415ec884e591fb5c70d373da640a383b5.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/e3/
1-billion-word-language-modeling-benchmark-r13output/.svn/pristine/e3/e37ba0f85e94073ccaced1eed7e4f5d737a25f49.svn-base
1-billion-word-language-modeling-benchmark-r13output/.svn/entries
1-billion-word-language-modeling-benchmark-r13output/.svn/format
1-billion-word-language-modeling-benchmark-r13output/.svn/wc.db
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00015-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00031-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00027-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00010-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00033-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00042-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00046-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00037-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00000-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00029-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00013-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00002-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00048-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00006-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00030-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00025-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00039-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00008-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00020-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00001-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00034-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00044-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00045-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00016-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00004-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00035-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00038-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00009-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00024-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00022-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00021-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00032-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00011-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00049-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00041-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00019-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00023-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00040-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00014-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00007-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00017-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00012-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00018-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00003-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00028-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en-00000-of-00100
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00043-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00005-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00036-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00026-of-00050
1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/news.en.heldout-00047-of-00050
1-billion-word-language-modeling-benchmark-r13output/README

Success! One billion words dataset ready at:
data/1-billion-word-language-modeling-benchmark-r13output/
Please pass this dir to single_lm_train.py via the --datadir option.

root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm# time python single_lm_train.py --mode=train --logdir=./logs --num_gpus=4 --datadir=./data/1-billion-word-language-modeling-benchmark-r13output

WARNING: The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
  * https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
  * https://github.com/tensorflow/addons
If you depend on functionality not listed there, please file an issue.

*****HYPER PARAMETERS*****
{'learning_rate': 0.2, 'do_summaries': False, 'keep_prob': 0.9, 'run_profiler': False, 'batch_size': 128, 'emb_size': 512, 'num_gpus': 4, 'max_grad_norm': 10.0, 'optimizer': 0, 'num_shards': 8, 'max_time': 180, 'projected_size': 512, 'num_steps': 20, 'num_delayed_steps': 150, 'state_size': 2048, 'num_sampled': 8192, 'average_params': True, 'vocab_size': 793470, 'num_layers': 1}
**************************
WARNING:tensorflow:From /usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From /opt/tensorflow/nvidia-examples/big_lstm/model_utils.py:33: UniformUnitScaling.__init__ (from tensorflow.python.ops.init_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.initializers.variance_scaling instead with distribution=uniform to get equivalent behavior.
WARNING:tensorflow:From /opt/tensorflow/nvidia-examples/big_lstm/language_model.py:75: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.
Instructions for updating:
Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.
WARNING:tensorflow:From /opt/tensorflow/nvidia-examples/big_lstm/language_model.py:107: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
WARNING:tensorflow:From /usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/nn_impl.py:1444: sparse_to_dense (from tensorflow.python.ops.sparse_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Create a `tf.sparse.SparseTensor` and use `tf.sparse.to_dense` instead.
WARNING:tensorflow:From /usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/array_grad.py:425: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
Current time: 1580763373.093285
ALL VARIABLES
WARNING:tensorflow:From /opt/tensorflow/nvidia-examples/big_lstm/run_utils.py:18: all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Please use tf.global_variables instead.
model/emb_0:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_1:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_2:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_3:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_4:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_5:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_6:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_7:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/lstm_0/LSTMCell/W_0:0 (1024, 8192) <dtype: 'float32_ref'> /gpu:0
model/lstm_0/LSTMCell/B:0 (8192,) <dtype: 'float32_ref'> /gpu:0
model/lstm_0/LSTMCell/W_P_0:0 (2048, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_0:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_1:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_2:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_3:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_4:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_5:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_6:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_7:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_b:0 (793470,) <dtype: 'float32_ref'> /gpu:0
model/global_step:0 () <dtype: 'int32_ref'>
model/model/emb_0/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/emb_1/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/emb_2/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/emb_3/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/emb_4/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/emb_5/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/emb_6/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/emb_7/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/lstm_0/LSTMCell/W_0/Adagrad:0 (1024, 8192) <dtype: 'float32_ref'> /gpu:0
model/model/lstm_0/LSTMCell/B/Adagrad:0 (8192,) <dtype: 'float32_ref'> /gpu:0
model/model/lstm_0/LSTMCell/W_P_0/Adagrad:0 (2048, 512) <dtype: 'float32_ref'> /gpu:0
model/model/softmax_w_0/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/softmax_w_1/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/softmax_w_2/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/softmax_w_3/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/softmax_w_4/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/softmax_w_5/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/softmax_w_6/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/softmax_w_7/Adagrad:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/model/softmax_b/Adagrad:0 (793470,) <dtype: 'float32_ref'> /gpu:0
model/model/lstm_0/LSTMCell/W_0/ExponentialMovingAverage:0 (1024, 8192) <dtype: 'float32_ref'> /gpu:0
model/model/lstm_0/LSTMCell/B/ExponentialMovingAverage:0 (8192,) <dtype: 'float32_ref'> /gpu:0
model/model/lstm_0/LSTMCell/W_P_0/ExponentialMovingAverage:0 (2048, 512) <dtype: 'float32_ref'> /gpu:0
TRAINABLE VARIABLES
model/emb_0:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_1:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_2:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_3:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_4:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_5:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_6:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/emb_7:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/lstm_0/LSTMCell/W_0:0 (1024, 8192) <dtype: 'float32_ref'> /gpu:0
model/lstm_0/LSTMCell/B:0 (8192,) <dtype: 'float32_ref'> /gpu:0
model/lstm_0/LSTMCell/W_P_0:0 (2048, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_0:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_1:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_2:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_3:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_4:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_5:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_6:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_w_7:0 (99184, 512) <dtype: 'float32_ref'> /gpu:0
model/softmax_b:0 (793470,) <dtype: 'float32_ref'> /gpu:0
LOCAL VARIABLES
model/model/state_0_0:0 (128, 2560) <dtype: 'float32_ref'> /gpu:0
model/model_1/state_1_0:0 (128, 2560) <dtype: 'float32_ref'> /gpu:1
model/model_2/state_2_0:0 (128, 2560) <dtype: 'float32_ref'> /gpu:2
model/model_3/state_3_0:0 (128, 2560) <dtype: 'float32_ref'> /gpu:3
WARNING:tensorflow:From /opt/tensorflow/nvidia-examples/big_lstm/run_utils.py:32: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
2020-02-03 20:56:14.055317: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2200015000 Hz
2020-02-03 20:56:14.061117: I tensorflow/compiler/xla/service/service.cc:161] XLA service 0xd0c1770 executing computations on platform Host. Devices:
2020-02-03 20:56:14.061150: I tensorflow/compiler/xla/service/service.cc:168]   StreamExecutor device (0): <undefined>, <undefined>
2020-02-03 20:56:15.124206: I tensorflow/compiler/xla/service/service.cc:161] XLA service 0xadd7f60 executing computations on platform CUDA. Devices:
2020-02-03 20:56:15.124245: I tensorflow/compiler/xla/service/service.cc:168]   StreamExecutor device (0): TITAN RTX, Compute Capability 7.5
2020-02-03 20:56:15.124254: I tensorflow/compiler/xla/service/service.cc:168]   StreamExecutor device (1): TITAN RTX, Compute Capability 7.5
2020-02-03 20:56:15.124263: I tensorflow/compiler/xla/service/service.cc:168]   StreamExecutor device (2): GeForce RTX 2080 Ti, Compute Capability 7.5
2020-02-03 20:56:15.124273: I tensorflow/compiler/xla/service/service.cc:168]   StreamExecutor device (3): GeForce RTX 2080 Ti, Compute Capability 7.5
2020-02-03 20:56:15.125670: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties:
name: TITAN RTX major: 7 minor: 5 memoryClockRate(GHz): 1.77
pciBusID: 0000:82:00.0
totalMemory: 23.65GiB freeMemory: 23.48GiB
2020-02-03 20:56:15.125739: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 1 with properties:
name: TITAN RTX major: 7 minor: 5 memoryClockRate(GHz): 1.77
pciBusID: 0000:83:00.0
totalMemory: 23.65GiB freeMemory: 23.48GiB
2020-02-03 20:56:15.125796: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 2 with properties:
name: GeForce RTX 2080 Ti major: 7 minor: 5 memoryClockRate(GHz): 1.635
pciBusID: 0000:02:00.0
totalMemory: 10.76GiB freeMemory: 10.37GiB
2020-02-03 20:56:15.125837: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 3 with properties:
name: GeForce RTX 2080 Ti major: 7 minor: 5 memoryClockRate(GHz): 1.635
pciBusID: 0000:03:00.0
totalMemory: 10.76GiB freeMemory: 10.60GiB
2020-02-03 20:56:15.126056: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0, 1, 2, 3
2020-02-03 20:56:16.373334: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-02-03 20:56:16.373394: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990]      0 1 2 3
2020-02-03 20:56:16.373404: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0:   N N N N
2020-02-03 20:56:16.373410: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 1:   N N N N
2020-02-03 20:56:16.373418: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 2:   N N N N
2020-02-03 20:56:16.373442: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 3:   N N N N
2020-02-03 20:56:16.373657: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 22757 MB memory) -> physical GPU (device: 0, name: TITAN RTX, pci bus id: 0000:82:00.0, compute capability: 7.5)
2020-02-03 20:56:16.373935: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 22757 MB memory) -> physical GPU (device: 1, name: TITAN RTX, pci bus id: 0000:83:00.0, compute capability: 7.5)
2020-02-03 20:56:16.374149: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:2 with 10004 MB memory) -> physical GPU (device: 2, name: GeForce RTX 2080 Ti, pci bus id: 0000:02:00.0, compute capability: 7.5)
2020-02-03 20:56:16.374327: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:3 with 10224 MB memory) -> physical GPU (device: 3, name: GeForce RTX 2080 Ti, pci bus id: 0000:03:00.0, compute capability: 7.5)
Processing file: ./data/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00048-of-00100
Finished processing!
2020-02-03 20:56:58.088053: I tensorflow/stream_executor/dso_loader.cc:153] successfully opened CUDA library libcublas.so.10 locally
Iteration 1, time = 22.37s, wps = 458, train loss = 13.0031
Iteration 2, time = 18.95s, wps = 540, train loss = 12.9526
Iteration 3, time = 0.11s, wps = 95585, train loss = 12.8299
Iteration 4, time = 0.10s, wps = 97703, train loss = 11.2766
Iteration 5, time = 0.10s, wps = 106271, train loss = 12.5715
Iteration 6, time = 0.10s, wps = 101701, train loss = 15.4158
Iteration 7, time = 0.10s, wps = 100070, train loss = 13.6081
Iteration 8, time = 0.10s, wps = 100071, train loss = 12.1453
Iteration 9, time = 0.10s, wps = 103186, train loss = 28.8821
Iteration 20, time = 1.07s, wps = 105677, train loss = 11.1364
Iteration 40, time = 1.96s, wps = 104229, train loss = 9.6204
Iteration 60, time = 1.95s, wps = 105054, train loss = 9.0927
Iteration 80, time = 1.96s, wps = 104578, train loss = 8.9390
Iteration 100, time = 1.94s, wps = 105628, train loss = 8.2379
Iteration 120, time = 1.95s, wps = 105294, train loss = 7.5226
Iteration 140, time = 1.94s, wps = 105728, train loss = 6.9707
Iteration 160, time = 1.95s, wps = 104759, train loss = 6.8336
Iteration 180, time = 1.96s, wps = 104568, train loss = 6.8043
Iteration 200, time = 1.95s, wps = 105088, train loss = 6.4154
Iteration 220, time = 1.93s, wps = 105910, train loss = 6.2507
Iteration 240, time = 1.91s, wps = 107022, train loss = 6.2901
Iteration 260, time = 1.96s, wps = 104244, train loss = 6.1811
Iteration 280, time = 1.93s, wps = 106290, train loss = 6.1038
Iteration 300, time = 1.95s, wps = 105094, train loss = 6.0242
Iteration 320, time = 1.94s, wps = 105558, train loss = 5.9667
Iteration 340, time = 1.94s, wps = 105414, train loss = 5.9616
Iteration 360, time = 1.95s, wps = 105007, train loss = 5.8782
Iteration 380, time = 1.94s, wps = 105521, train loss = 5.8886
Iteration 400, time = 1.92s, wps = 106852, train loss = 5.9200
Iteration 420, time = 1.95s, wps = 105230, train loss = 5.8815
Iteration 440, time = 1.92s, wps = 106909, train loss = 5.8814
Iteration 460, time = 1.94s, wps = 105404, train loss = 5.8571
Iteration 480, time = 1.92s, wps = 106474, train loss = 5.7409
Iteration 500, time = 1.94s, wps = 105462, train loss = 5.6992
Iteration 520, time = 1.96s, wps = 104430, train loss = 5.7669
Iteration 540, time = 1.94s, wps = 105677, train loss = 5.6666
Iteration 560, time = 1.95s, wps = 105142, train loss = 5.6725
Iteration 580, time = 1.95s, wps = 105012, train loss = 5.6517
Iteration 600, time = 1.93s, wps = 105955, train loss = 5.6006
Iteration 620, time = 1.95s, wps = 104853, train loss = 5.5638
Iteration 640, time = 1.93s, wps = 106170, train loss = 5.5613
Iteration 660, time = 1.94s, wps = 105537, train loss = 5.6244
Iteration 680, time = 1.94s, wps = 105769, train loss = 5.5365
Iteration 700, time = 1.95s, wps = 104954, train loss = 5.4826
Iteration 720, time = 1.95s, wps = 104830, train loss = 5.4813
Iteration 740, time = 1.93s, wps = 106232, train loss = 5.4421
Iteration 760, time = 1.94s, wps = 105715, train loss = 5.4689
Iteration 780, time = 1.95s, wps = 104862, train loss = 5.4643
Processing file: ./data/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/news.en-00023-of-00100
Finished processing!
Iteration 800, time = 4.17s, wps = 49105, train loss = 5.4270
Iteration 820, time = 1.96s, wps = 104329, train loss = 5.4649
Iteration 840, time = 1.94s, wps = 105762, train loss = 5.3953
Iteration 860, time = 1.92s, wps = 106532, train loss = 5.4191
Iteration 880, time = 1.94s, wps = 105767, train loss = 5.3408
Iteration 900, time = 1.94s, wps = 105386, train loss = 5.3677
Iteration 920, time = 1.92s, wps = 106843, train loss = 5.3429
Iteration 940, time = 1.94s, wps = 105668, train loss = 5.2624
Iteration 960, time = 1.94s, wps = 105746, train loss = 5.2341
Iteration 980, time = 1.94s, wps = 105451, train loss = 5.3021
Iteration 1000, time = 1.95s, wps = 104878, train loss = 5.2493
Iteration 1020, time = 1.94s, wps = 105363, train loss = 5.2314
Iteration 1040, time = 1.93s, wps = 105948, train loss = 5.2292
Iteration 1060, time = 1.94s, wps = 105408, train loss = 5.2391
Iteration 1080, time = 1.96s, wps = 104309, train loss = 5.2231
Iteration 1100, time = 1.95s, wps = 104941, train loss = 5.1645
Iteration 1120, time = 1.96s, wps = 104694, train loss = 5.1580
Iteration 1140, time = 1.97s, wps = 103797, train loss = 5.1661
/usr/local/lib/python3.5/dist-packages/tensorflow/python/summary/writer/writer.py:386: UserWarning: Attempting to use a closed FileWriter. The operation will be a noop unless the FileWriter is explicitly reopened.
  warnings.warn("Attempting to use a closed FileWriter. "

real    3m22.615s
user    16m26.078s
sys     2m4.964s
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm# cat /etc/os-release
NAME="Ubuntu"
VERSION="16.04.6 LTS (Xenial Xerus)"
ID=ubuntu
ID_LIKE=debian
PRETTY_NAME="Ubuntu 16.04.6 LTS"
VERSION_ID="16.04"
HOME_URL="http://www.ubuntu.com/"
SUPPORT_URL="http://help.ubuntu.com/"
BUG_REPORT_URL="http://bugs.launchpad.net/ubuntu/"
VERSION_CODENAME=xenial
UBUNTU_CODENAME=xenial
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm# nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Fri_Feb__8_19:08:17_PST_2019
Cuda compilation tools, release 10.1, V10.1.105
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm# cd data
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm/data# ls
1-billion-word-language-modeling-benchmark-r13output
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm/data# cd 1-billion-word-language-modeling-benchmark-r13output
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm/data/1-billion-word-language-modeling-benchmark-r13output# ls
1b_word_vocab.txt  heldout-monolingual.tokenized.shuffled
README             training-monolingual.tokenized.shuffled
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm/data/1-billion-word-language-modeling-benchmark-r13output# cd training-monolingual.tokenized.shuffled
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm/data/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled# ls
news.en-00001-of-00100  news.en-00034-of-00100  news.en-00067-of-00100
news.en-00002-of-00100  news.en-00035-of-00100  news.en-00068-of-00100
news.en-00003-of-00100  news.en-00036-of-00100  news.en-00069-of-00100
news.en-00004-of-00100  news.en-00037-of-00100  news.en-00070-of-00100
news.en-00005-of-00100  news.en-00038-of-00100  news.en-00071-of-00100
news.en-00006-of-00100  news.en-00039-of-00100  news.en-00072-of-00100
news.en-00007-of-00100  news.en-00040-of-00100  news.en-00073-of-00100
news.en-00008-of-00100  news.en-00041-of-00100  news.en-00074-of-00100
news.en-00009-of-00100  news.en-00042-of-00100  news.en-00075-of-00100
news.en-00010-of-00100  news.en-00043-of-00100  news.en-00076-of-00100
news.en-00011-of-00100  news.en-00044-of-00100  news.en-00077-of-00100
news.en-00012-of-00100  news.en-00045-of-00100  news.en-00078-of-00100
news.en-00013-of-00100  news.en-00046-of-00100  news.en-00079-of-00100
news.en-00014-of-00100  news.en-00047-of-00100  news.en-00080-of-00100
news.en-00015-of-00100  news.en-00048-of-00100  news.en-00081-of-00100
news.en-00016-of-00100  news.en-00049-of-00100  news.en-00082-of-00100
news.en-00017-of-00100  news.en-00050-of-00100  news.en-00083-of-00100
news.en-00018-of-00100  news.en-00051-of-00100  news.en-00084-of-00100
news.en-00019-of-00100  news.en-00052-of-00100  news.en-00085-of-00100
news.en-00020-of-00100  news.en-00053-of-00100  news.en-00086-of-00100
news.en-00021-of-00100  news.en-00054-of-00100  news.en-00087-of-00100
news.en-00022-of-00100  news.en-00055-of-00100  news.en-00088-of-00100
news.en-00023-of-00100  news.en-00056-of-00100  news.en-00089-of-00100
news.en-00024-of-00100  news.en-00057-of-00100  news.en-00090-of-00100
news.en-00025-of-00100  news.en-00058-of-00100  news.en-00091-of-00100
news.en-00026-of-00100  news.en-00059-of-00100  news.en-00092-of-00100
news.en-00027-of-00100  news.en-00060-of-00100  news.en-00093-of-00100
news.en-00028-of-00100  news.en-00061-of-00100  news.en-00094-of-00100
news.en-00029-of-00100  news.en-00062-of-00100  news.en-00095-of-00100
news.en-00030-of-00100  news.en-00063-of-00100  news.en-00096-of-00100
news.en-00031-of-00100  news.en-00064-of-00100  news.en-00097-of-00100
news.en-00032-of-00100  news.en-00065-of-00100  news.en-00098-of-00100
news.en-00033-of-00100  news.en-00066-of-00100  news.en-00099-of-00100
root@71bff3d91e1f:/workspace/nvidia-examples/big_lstm/data/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled# exit
exit
[chibi@rhel8 ~]$ cat /etc/redhat-release
Red Hat Enterprise Linux release 8.1 (Ootpa)
[chibi@rhel8 ~]$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Wed_Oct_23_19:24:38_PDT_2019
Cuda compilation tools, release 10.2, V10.2.89
[chibi@rhel8 ~]$ sudo hddtemp /dev/sda
[sudo] chibi のパスワード:
/dev/sda: TS240GSSD220S: 31°C
[chibi@rhel8 ~]$ nvidia-smi nvlink -c
GPU 0: GeForce RTX 2080 Ti (UUID: GPU-1ac935c2-557f-282e-14e5-3f749ffd63ac)
GPU 1: GeForce RTX 2080 Ti (UUID: GPU-13277ce5-e1e9-0cb1-8cee-6c9e6618e774)
GPU 2: TITAN RTX (UUID: GPU-5a71d61e-f130-637a-b33d-4df555b0ed88)
GPU 3: TITAN RTX (UUID: GPU-7fb51c1d-c1e7-35cc-aad7-66971f05ddb7)
[chibi@rhel8 ~]$