job.yml

$schema: https://azuremlschemas.azureedge.net/latest/commandJob.schema.json

# name of the experiment, use this to structure your training results
experiment_name: nebula-mnist-example
display_name: nebula-mnist-example

code: .

# compute cluster on which the command above should be run
# note: before you can use the compute, it needs to be created first in your AzureML workspace
compute: gpu-v100-1GPU-cluster

# compute resources
resources:
    # number of nodes in the cluster above
    instance_count: 1

# environment in which the command above should be run in
# note: It is recommended to use an environment which either is the ACPT image or at least inherits from it. The ACPT
#       image has many frameworks related to PyTorch pre-installed, hence reduces efforts to create your own
#       environment. To learn more about environments in AML, see
#       https://learn.microsoft.com/en-us/azure/machine-learning/concept-environments
#
# for the latest ACPT image using PyTorch 2.2, CUDA 12.1 on Python 3.10
# environment: azureml:AzureML-acpt-pytorch-2.2-cuda12.1@latest
environment: azureml:AzureML-acpt-pytorch-2.2-cuda12.1@latest
# for a specific version
#environment: azureml:AzureML-acpt-pytorch-2.2-cuda12.1:3
# for the latest version of a custom environment:  (====install Nebula in dockerfile environment=====)
#environment: azureml:ACPT-Extended@latest
# for a specific Docker image (has to be compatible with Azure ML):
#environment:
#    image: mcr.microsoft.com/azureml/curated/acpt-pytorch-2.2-cuda12.1:2

# command that should be run by the job (====install Nebula with comand OR use dockerfile environment=====)
command: >-
      python train.py --save-model