bash: cannot set terminal process group (-1): Inappropriate ioctl for device
bash: no job control in this shell
2020-09-13 13:21:52,954 sagemaker-training-toolkit INFO     Imported framework sagemaker_pytorch_container.training
2020-09-13 13:21:52,957 sagemaker-training-toolkit INFO     No GPUs detected (normal if no gpus installed)
2020-09-13 13:21:52,966 sagemaker_pytorch_container.training INFO     Block until all host DNS lookups succeed.
2020-09-13 13:21:59,219 sagemaker_pytorch_container.training INFO     Invoking user training script.
2020-09-13 13:21:59,607 sagemaker-training-toolkit INFO     No GPUs detected (normal if no gpus installed)
2020-09-13 13:21:59,619 sagemaker-training-toolkit INFO     No GPUs detected (normal if no gpus installed)
2020-09-13 13:21:59,630 sagemaker-training-toolkit INFO     No GPUs detected (normal if no gpus installed)
2020-09-13 13:21:59,640 sagemaker-training-toolkit INFO     Invoking user script

Training Env:

{
    "additional_framework_parameters": {},
    "channel_input_dirs": {
        "data": "/opt/ml/input/data/data"
    },
    "current_host": "algo-2",
    "framework_module": "sagemaker_pytorch_container.training:main",
    "hosts": [
        "algo-1",
        "algo-2"
    ],
    "hyperparameters": {
        "task": 1,
        "arg": "hello world!",
        "worker": 1
    },
    "input_config_dir": "/opt/ml/input/config",
    "input_data_config": {
        "data": {
            "TrainingInputMode": "File",
            "S3DistributionType": "ShardedByS3Key",
            "RecordWrapperType": "None"
        }
    },
    "input_dir": "/opt/ml/input",
    "is_master": false,
    "job_name": "task1-2020-09-13-13-17-56-FZSEab99",
    "log_level": 20,
    "master_hostname": "algo-1",
    "model_dir": "/opt/ml/model",
    "module_dir": "s3://sagemaker-us-east-1-667232328135/tests/simple-sagemaker-sf_2020-09-13-13-16-10_py37/task1/task1-2020-09-13-13-17-56-FZSEab99/source/sourcedir.tar.gz",
    "module_name": "example",
    "network_interface_name": "eth0",
    "num_cpus": 2,
    "num_gpus": 0,
    "output_data_dir": "/opt/ml/output/data",
    "output_dir": "/opt/ml/output",
    "output_intermediate_dir": "/opt/ml/output/intermediate",
    "resource_config": {
        "current_host": "algo-2",
        "hosts": [
            "algo-1",
            "algo-2"
        ],
        "network_interface_name": "eth0"
    },
    "user_entry_point": "example.py"
}

Environment variables:

SM_HOSTS=["algo-1","algo-2"]
SM_NETWORK_INTERFACE_NAME=eth0
SM_HPS={"arg":"hello world!","task":1,"worker":1}
SM_USER_ENTRY_POINT=example.py
SM_FRAMEWORK_PARAMS={}
SM_RESOURCE_CONFIG={"current_host":"algo-2","hosts":["algo-1","algo-2"],"network_interface_name":"eth0"}
SM_INPUT_DATA_CONFIG={"data":{"RecordWrapperType":"None","S3DistributionType":"ShardedByS3Key","TrainingInputMode":"File"}}
SM_OUTPUT_DATA_DIR=/opt/ml/output/data
SM_CHANNELS=["data"]
SM_CURRENT_HOST=algo-2
SM_MODULE_NAME=example
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=2
SM_NUM_GPUS=0
SM_MODEL_DIR=/opt/ml/model
SM_MODULE_DIR=s3://sagemaker-us-east-1-667232328135/tests/simple-sagemaker-sf_2020-09-13-13-16-10_py37/task1/task1-2020-09-13-13-17-56-FZSEab99/source/sourcedir.tar.gz
SM_TRAINING_ENV={"additional_framework_parameters":{},"channel_input_dirs":{"data":"/opt/ml/input/data/data"},"current_host":"algo-2","framework_module":"sagemaker_pytorch_container.training:main","hosts":["algo-1","algo-2"],"hyperparameters":{"arg":"hello world!","task":1,"worker":1},"input_config_dir":"/opt/ml/input/config","input_data_config":{"data":{"RecordWrapperType":"None","S3DistributionType":"ShardedByS3Key","TrainingInputMode":"File"}},"input_dir":"/opt/ml/input","is_master":false,"job_name":"task1-2020-09-13-13-17-56-FZSEab99","log_level":20,"master_hostname":"algo-1","model_dir":"/opt/ml/model","module_dir":"s3://sagemaker-us-east-1-667232328135/tests/simple-sagemaker-sf_2020-09-13-13-16-10_py37/task1/task1-2020-09-13-13-17-56-FZSEab99/source/sourcedir.tar.gz","module_name":"example","network_interface_name":"eth0","num_cpus":2,"num_gpus":0,"output_data_dir":"/opt/ml/output/data","output_dir":"/opt/ml/output","output_intermediate_dir":"/opt/ml/output/intermediate","resource_config":{"current_host":"algo-2","hosts":["algo-1","algo-2"],"network_interface_name":"eth0"},"user_entry_point":"example.py"}
SM_USER_ARGS=["--arg","hello world!","--task","1","--worker","1"]
SM_OUTPUT_INTERMEDIATE_DIR=/opt/ml/output/intermediate
SM_CHANNEL_DATA=/opt/ml/input/data/data
SM_HP_TASK=1
SM_HP_ARG=hello world!
SM_HP_WORKER=1
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 example.py --arg hello world! --task 1 --worker 1


INFO:__main__:Starting worker...
INFO:task_toolkit.algo_lib:Args: Namespace(batch_size=64, channel_names=['data'], current_host='algo-2', epochs=50, hosts=['algo-1', 'algo-2'], hps={'arg': 'hello world!', 'task': 1, 'worker': 1}, input_config_dir='/opt/ml/input/config', input_data='/opt/ml/input/data/data', input_data_config='{"data":{"RecordWrapperType":"None","S3DistributionType":"ShardedByS3Key","TrainingInputMode":"File"}}', input_dir='/opt/ml/input', input_model='', job_name='task1-2020-09-13-13-17-56-FZSEab99', learning_rate=0.05, model_dir='/opt/ml/model', network_interface='eth0', num_cpus=2, num_gpus=0, output_data_dir='/opt/ml/output/data', output_dir='/opt/ml/output', resource_config='{"current_host":"algo-2","hosts":["algo-1","algo-2"],"network_interface_name":"eth0"}', state='/state', use_cuda=False)
INFO:task_toolkit.algo_lib:Unmatched: ['--arg', 'hello world!', '--task', '1', '--worker', '1']
INFO:task_toolkit.algo_lib:Deleting other instances' state
INFO:task_toolkit.algo_lib:Creating instance specific state dir
INFO:__main__:Hyperparams: {'arg': 'hello world!', 'task': 1, 'worker': 1}
INFO:__main__:Input data files: [PosixPath('/opt/ml/input/data/data/sample_data2.txt')]
INFO:__main__:State files: [PosixPath('/state/algo-2')]
INFO:task_toolkit.algo_lib:Marking instance algo-2 completion
INFO:__main__:finished!
2020-09-13 13:21:59,711 sagemaker-training-toolkit INFO     Reporting training SUCCESS
