bash: cannot set terminal process group (-1): Inappropriate ioctl for device
bash: no job control in this shell
2020-09-24 13:48:06,754 sagemaker-training-toolkit INFO     Imported framework sagemaker_pytorch_container.training
2020-09-24 13:48:06,777 sagemaker_pytorch_container.training INFO     Block until all host DNS lookups succeed.
2020-09-24 13:48:06,785 sagemaker_pytorch_container.training INFO     Invoking user training script.
2020-09-24 13:48:07,170 sagemaker-training-toolkit INFO     Invoking user script

Training Env:

{
    "additional_framework_parameters": {},
    "channel_input_dirs": {},
    "current_host": "algo-1",
    "framework_module": "sagemaker_pytorch_container.training:main",
    "hosts": [
        "algo-1"
    ],
    "hyperparameters": {
        "SSM_CMD_LINE": "cat /proc/cpuinfo && nvidia-smi"
    },
    "input_config_dir": "/opt/ml/input/config",
    "input_data_config": {},
    "input_dir": "/opt/ml/input",
    "is_master": true,
    "job_name": "shell-task-2020-09-24-13-43-56-W9UuW4Tv",
    "log_level": 20,
    "master_hostname": "algo-1",
    "model_dir": "/opt/ml/model",
    "module_dir": "s3://sagemaker-us-east-1-667232328135/tests/simple-sagemaker-example-cli_2020-09-24-13-43-54_py37/shell-task/shell-task-2020-09-24-13-43-56-W9UuW4Tv/source/sourcedir.tar.gz",
    "module_name": "shell_launcher",
    "network_interface_name": "eth0",
    "num_cpus": 8,
    "num_gpus": 1,
    "output_data_dir": "/opt/ml/output/data",
    "output_dir": "/opt/ml/output",
    "output_intermediate_dir": "/opt/ml/output/intermediate",
    "resource_config": {
        "current_host": "algo-1",
        "hosts": [
            "algo-1"
        ],
        "network_interface_name": "eth0"
    },
    "user_entry_point": "shell_launcher.py"
}

Environment variables:

SM_HOSTS=["algo-1"]
SM_NETWORK_INTERFACE_NAME=eth0
SM_HPS={"SSM_CMD_LINE":"cat /proc/cpuinfo && nvidia-smi"}
SM_USER_ENTRY_POINT=shell_launcher.py
SM_FRAMEWORK_PARAMS={}
SM_RESOURCE_CONFIG={"current_host":"algo-1","hosts":["algo-1"],"network_interface_name":"eth0"}
SM_INPUT_DATA_CONFIG={}
SM_OUTPUT_DATA_DIR=/opt/ml/output/data
SM_CHANNELS=[]
SM_CURRENT_HOST=algo-1
SM_MODULE_NAME=shell_launcher
SM_LOG_LEVEL=20
SM_FRAMEWORK_MODULE=sagemaker_pytorch_container.training:main
SM_INPUT_DIR=/opt/ml/input
SM_INPUT_CONFIG_DIR=/opt/ml/input/config
SM_OUTPUT_DIR=/opt/ml/output
SM_NUM_CPUS=8
SM_NUM_GPUS=1
SM_MODEL_DIR=/opt/ml/model
SM_MODULE_DIR=s3://sagemaker-us-east-1-667232328135/tests/simple-sagemaker-example-cli_2020-09-24-13-43-54_py37/shell-task/shell-task-2020-09-24-13-43-56-W9UuW4Tv/source/sourcedir.tar.gz
SM_TRAINING_ENV={"additional_framework_parameters":{},"channel_input_dirs":{},"current_host":"algo-1","framework_module":"sagemaker_pytorch_container.training:main","hosts":["algo-1"],"hyperparameters":{"SSM_CMD_LINE":"cat /proc/cpuinfo && nvidia-smi"},"input_config_dir":"/opt/ml/input/config","input_data_config":{},"input_dir":"/opt/ml/input","is_master":true,"job_name":"shell-task-2020-09-24-13-43-56-W9UuW4Tv","log_level":20,"master_hostname":"algo-1","model_dir":"/opt/ml/model","module_dir":"s3://sagemaker-us-east-1-667232328135/tests/simple-sagemaker-example-cli_2020-09-24-13-43-54_py37/shell-task/shell-task-2020-09-24-13-43-56-W9UuW4Tv/source/sourcedir.tar.gz","module_name":"shell_launcher","network_interface_name":"eth0","num_cpus":8,"num_gpus":1,"output_data_dir":"/opt/ml/output/data","output_dir":"/opt/ml/output","output_intermediate_dir":"/opt/ml/output/intermediate","resource_config":{"current_host":"algo-1","hosts":["algo-1"],"network_interface_name":"eth0"},"user_entry_point":"shell_launcher.py"}
SM_USER_ARGS=["--SSM_CMD_LINE","cat /proc/cpuinfo && nvidia-smi"]
SM_OUTPUT_INTERMEDIATE_DIR=/opt/ml/output/intermediate
SM_HP_SSM_CMD_LINE=cat /proc/cpuinfo && nvidia-smi
PYTHONPATH=/opt/ml/code:/opt/conda/bin:/opt/conda/lib/python36.zip:/opt/conda/lib/python3.6:/opt/conda/lib/python3.6/lib-dynload:/opt/conda/lib/python3.6/site-packages

Invoking script with the following command:

/opt/conda/bin/python shell_launcher.py --SSM_CMD_LINE cat /proc/cpuinfo && nvidia-smi


INFO:worker_toolkit.worker_lib:Deleting other instances' state
INFO:worker_toolkit.worker_lib:Creating instance specific state dir
INFO:worker_toolkit.worker_lib:Worker config: Namespace(channel_data='', channel_model='', channels=[], current_host='algo-1', hosts=['algo-1'], hps={'SSM_CMD_LINE': 'cat /proc/cpuinfo && nvidia-smi'}, input_config_dir='/opt/ml/input/config', input_data_config='{}', input_dir='/opt/ml/input', instance_state='/state/algo-1', job_name='shell-task-2020-09-24-13-43-56-W9UuW4Tv', model_dir='/opt/ml/model', network_interface_name='eth0', num_cpus=8, num_gpus=1, output_data_dir='/opt/ml/output/data', output_dir='/opt/ml/output', resource_config='{"current_host":"algo-1","hosts":["algo-1"],"network_interface_name":"eth0"}', state='/state')
INFO:__main__:Launching: cat /proc/cpuinfo && nvidia-smi
processor#011: 0
vendor_id#011: GenuineIntel
cpu family#011: 6
model#011#011: 79
model name#011: Intel(R) Xeon(R) CPU E5-2686 v4 @ 2.30GHz
stepping#011: 1
microcode#011: 0xb000038
cpu MHz#011#011: 2700.256
cache size#011: 46080 KB
physical id#011: 0
siblings#011: 8
core id#011#011: 0
cpu cores#011: 4
apicid#011#011: 0
initial apicid#011: 0
fpu#011#011: yes
fpu_exception#011: yes
cpuid level#011: 13
wp#011#011: yes
flags#011#011: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx xsaveopt
bugs#011#011: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs taa itlb_multihit
bogomips#011: 4600.16
clflush size#011: 64
cache_alignment#011: 64
address sizes#011: 46 bits physical, 48 bits virtual
power management:

processor#011: 1
vendor_id#011: GenuineIntel
cpu family#011: 6
model#011#011: 79
model name#011: Intel(R) Xeon(R) CPU E5-2686 v4 @ 2.30GHz
stepping#011: 1
microcode#011: 0xb000038
cpu MHz#011#011: 2702.726
cache size#011: 46080 KB
physical id#011: 0
siblings#011: 8
core id#011#011: 1
cpu cores#011: 4
apicid#011#011: 2
initial apicid#011: 2
fpu#011#011: yes
fpu_exception#011: yes
cpuid level#011: 13
wp#011#011: yes
flags#011#011: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx xsaveopt
bugs#011#011: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs taa itlb_multihit
bogomips#011: 4600.16
clflush size#011: 64
cache_alignment#011: 64
address sizes#011: 46 bits physical, 48 bits virtual
power management:

processor#011: 2
vendor_id#011: GenuineIntel
cpu family#011: 6
model#011#011: 79
model name#011: Intel(R) Xeon(R) CPU E5-2686 v4 @ 2.30GHz
stepping#011: 1
microcode#011: 0xb000038
cpu MHz#011#011: 2700.463
cache size#011: 46080 KB
physical id#011: 0
siblings#011: 8
core id#011#011: 2
cpu cores#011: 4
apicid#011#011: 4
initial apicid#011: 4
fpu#011#011: yes
fpu_exception#011: yes
cpuid level#011: 13
wp#011#011: yes
flags#011#011: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx xsaveopt
bugs#011#011: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs taa itlb_multihit
bogomips#011: 4600.16
clflush size#011: 64
cache_alignment#011: 64
address sizes#011: 46 bits physical, 48 bits virtual
power management:

processor#011: 3
vendor_id#011: GenuineIntel
cpu family#011: 6
model#011#011: 79
model name#011: Intel(R) Xeon(R) CPU E5-2686 v4 @ 2.30GHz
stepping#011: 1
microcode#011: 0xb000038
cpu MHz#011#011: 2699.958
cache size#011: 46080 KB
physical id#011: 0
siblings#011: 8
core id#011#011: 3
cpu cores#011: 4
apicid#011#011: 6
initial apicid#011: 6
fpu#011#011: yes
fpu_exception#011: yes
cpuid level#011: 13
wp#011#011: yes
flags#011#011: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx xsaveopt
bugs#011#011: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs taa itlb_multihit
bogomips#011: 4600.16
clflush size#011: 64
cache_alignment#011: 64
address sizes#011: 46 bits physical, 48 bits virtual
power management:

processor#011: 4
vendor_id#011: GenuineIntel
cpu family#011: 6
model#011#011: 79
model name#011: Intel(R) Xeon(R) CPU E5-2686 v4 @ 2.30GHz
stepping#011: 1
microcode#011: 0xb000038
cpu MHz#011#011: 2700.111
cache size#011: 46080 KB
physical id#011: 0
siblings#011: 8
core id#011#011: 0
cpu cores#011: 4
apicid#011#011: 1
initial apicid#011: 1
fpu#011#011: yes
fpu_exception#011: yes
cpuid level#011: 13
wp#011#011: yes
flags#011#011: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx xsaveopt
bugs#011#011: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs taa itlb_multihit
bogomips#011: 4600.16
clflush size#011: 64
cache_alignment#011: 64
address sizes#011: 46 bits physical, 48 bits virtual
power management:

processor#011: 5
vendor_id#011: GenuineIntel
cpu family#011: 6
model#011#011: 79
model name#011: Intel(R) Xeon(R) CPU E5-2686 v4 @ 2.30GHz
stepping#011: 1
microcode#011: 0xb000038
cpu MHz#011#011: 2700.253
cache size#011: 46080 KB
physical id#011: 0
siblings#011: 8
core id#011#011: 1
cpu cores#011: 4
apicid#011#011: 3
initial apicid#011: 3
fpu#011#011: yes
fpu_exception#011: yes
cpuid level#011: 13
wp#011#011: yes
flags#011#011: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx xsaveopt
bugs#011#011: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs taa itlb_multihit
bogomips#011: 4600.16
clflush size#011: 64
cache_alignment#011: 64
address sizes#011: 46 bits physical, 48 bits virtual
power management:

processor#011: 6
vendor_id#011: GenuineIntel
cpu family#011: 6
model#011#011: 79
model name#011: Intel(R) Xeon(R) CPU E5-2686 v4 @ 2.30GHz
stepping#011: 1
microcode#011: 0xb000038
cpu MHz#011#011: 2699.983
cache size#011: 46080 KB
physical id#011: 0
siblings#011: 8
core id#011#011: 2
cpu cores#011: 4
apicid#011#011: 5
initial apicid#011: 5
fpu#011#011: yes
fpu_exception#011: yes
cpuid level#011: 13
wp#011#011: yes
flags#011#011: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx xsaveopt
bugs#011#011: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs taa itlb_multihit
bogomips#011: 4600.16
clflush size#011: 64
cache_alignment#011: 64
address sizes#011: 46 bits physical, 48 bits virtual
power management:

processor#011: 7
vendor_id#011: GenuineIntel
cpu family#011: 6
model#011#011: 79
model name#011: Intel(R) Xeon(R) CPU E5-2686 v4 @ 2.30GHz
stepping#011: 1
microcode#011: 0xb000038
cpu MHz#011#011: 2700.163
cache size#011: 46080 KB
physical id#011: 0
siblings#011: 8
core id#011#011: 3
cpu cores#011: 4
apicid#011#011: 7
initial apicid#011: 7
fpu#011#011: yes
fpu_exception#011: yes
cpuid level#011: 13
wp#011#011: yes
flags#011#011: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx xsaveopt
bugs#011#011: cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs taa itlb_multihit
bogomips#011: 4600.16
clflush size#011: 64
cache_alignment#011: 64
address sizes#011: 46 bits physical, 48 bits virtual
power management:

Thu Sep 24 13:48:07 2020       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 440.33.01    Driver Version: 440.33.01    CUDA Version: 10.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  Tesla V100-SXM2...  On   | 00000000:00:1E.0 Off |                    0 |
| N/A   45C    P0    25W / 300W |      0MiB / 16160MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+
INFO:worker_toolkit.worker_lib:Marking instance algo-1 completion
INFO:__main__:finished with 0 return code!
2020-09-24 13:48:07,335 sagemaker-training-toolkit INFO     Reporting training SUCCESS
