my-training-job.yaml

apiVersion: sagemaker.services.k8s.aws/v1alpha1
kind: TrainingJob
metadata:
  name: <YOUR JOB NAME>
spec:
  # Name that will appear in SageMaker console
  trainingJobName: <YOUR JOB NAME> 
  # Modify these parameters to meet your own script's needs
  hyperParameters: 
    max_depth: "5"
    gamma: "4"
    eta: "0.2"
    min_child_weight: "6"
    silent: "0"
    objective: "multi:softmax"
    num_class: "10"
    num_round: "10"
  algorithmSpecification:
    # The URL and tag of your ECR container
    # If you are not on us-west-2 you can find an imageURI here https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-algo-docker-registry-paths.html
    trainingImage: 433757028032.dkr.ecr.us-west-2.amazonaws.com/xgboost:1
    trainingInputMode: File
  # A role with SageMaker and S3 access
  # example arn:aws:iam::1234567890:role/service-role/AmazonSageMaker-ExecutionRole
  roleARN: <YOUR SAGEMAKER ROLE ARN> 
  outputDataConfig:
    # The output path of our model
    s3OutputPath: s3://<YOUR BUCKET/OUTPUT> 
  resourceConfig:
    instanceCount: 1
    instanceType: ml.m4.xlarge
    volumeSizeInGB: 5
  stoppingCondition:
    maxRuntimeInSeconds: 86400
  inputDataConfig:
    - channelName: train
      dataSource:
        s3DataSource:
          s3DataType: S3Prefix
          # The input path of our train data 
          s3URI: s3://<YOUR BUCKET>/sagemaker/xgboost/train
          s3DataDistributionType: FullyReplicated
      contentType: text/libsvm
      compressionType: None
    - channelName: validation
      dataSource:
        s3DataSource:
          s3DataType: S3Prefix
          # The input path of our validation data 
          s3URI: s3://<YOUR BUCKET>/sagemaker/xgboost/validation
          s3DataDistributionType: FullyReplicated
      contentType: text/libsvm
      compressionType: None