# This HPO job was designed to fail during the "Training" phase.
# The image specified refers to a plain Tensorflow DLC image that does not have
# the correct entrypoint for a SageMaker training job. This will fail with a 
# python exception that should be captured by the operator.
apiVersion: sagemaker.aws.amazon.com/v1
kind: HyperparameterTuningJob
metadata:
  name: failing-xgboost-mnist-hpo
spec:
  region: us-west-2
  tags:
  - key: test-key
    value: test-value
  hyperParameterTuningJobConfig:
    strategy: Bayesian
    hyperParameterTuningJobObjective:
      type: Minimize
      metricName: validation:error
    resourceLimits:
      maxNumberOfTrainingJobs: 2
      maxParallelTrainingJobs: 2
    parameterRanges:
      integerParameterRanges:
      - name: num_round
        minValue: '10'
        maxValue: '20'
        scalingType: Linear
      continuousParameterRanges: []
      categoricalParameterRanges: []
    trainingJobEarlyStoppingType: Auto
  trainingJobDefinition:
    staticHyperParameters:
    - name: base_score
      value: '0.5'
    - name: booster
      value: gbtree
    - name: csv_weights
      value: '0'
    - name: dsplit
      value: row
    - name: grow_policy
      value: depthwise
    - name: lambda_bias
      value: '0.0'
    - name: max_bin
      value: '256'
    - name: max_leaves
      value: '0'
    - name: normalize_type
      value: tree
    - name: objective
      value: reg:linear
    - name: one_drop
      value: '0'
    - name: prob_buffer_row
      value: '1.0'
    - name: process_type
      value: default
    - name: rate_drop
      value: '0.0'
    - name: refresh_leaf
      value: '1'
    - name: sample_type
      value: uniform
    - name: scale_pos_weight
      value: '1.0'
    - name: silent
      value: '0'
    - name: sketch_eps
      value: '0.03'
    - name: skip_drop
      value: '0.0'
    - name: tree_method
      value: auto
    - name: tweedie_variance_power
      value: '1.5'
    - name: updater
      value: grow_colmaker,prune
    algorithmSpecification:
      trainingImage: 763104351884.dkr.ecr.us-west-2.amazonaws.com/tensorflow-training:2.0.1-gpu-py36-cu100-ubuntu18.04
      trainingInputMode: File
      metricDefinitions:
      - name: validation:error
        regex: "validation_error=(.*?);"
    roleArn: {ROLE_ARN}
    inputDataConfig:
    - channelName: train
      dataSource:
        s3DataSource:
          s3DataType: S3Prefix
          s3Uri: s3://{DATA_BUCKET}/train/
          s3DataDistributionType: FullyReplicated
      contentType: text/csv
      compressionType: None
      recordWrapperType: None
      inputMode: File
    - channelName: validation
      dataSource:
        s3DataSource:
          s3DataType: S3Prefix
          s3Uri: s3://{DATA_BUCKET}/validation/
          s3DataDistributionType: FullyReplicated
      contentType: text/csv
      compressionType: None
      recordWrapperType: None
      inputMode: File
    outputDataConfig:
      s3OutputPath: s3://{DATA_BUCKET}/xgboost
    resourceConfig:
      instanceType: ml.m4.xlarge
      instanceCount: 1
      volumeSizeInGB: 25
    stoppingCondition:
      maxRuntimeInSeconds: 3600
    enableNetworkIsolation: true
    enableInterContainerTrafficEncryption: false