apiVersion: "kubeflow.org/v1alpha3"
kind: Experiment
metadata:
  namespace: kubeflow
  labels:
    controller-tools.k8s.io: "1.0"
  name: never-resume-example
spec:
  objective:
    type: maximize
    goal: 0.99
    objectiveMetricName: Validation-accuracy
    additionalMetricNames:
      - Train-accuracy
  algorithm:
    algorithmName: random
  parallelTrialCount: 3
  maxTrialCount: 12
  maxFailedTrialCount: 3
  resumePolicy: Never
  parameters:
    - name: --lr
      parameterType: double
      feasibleSpace:
        min: "0.01"
        max: "0.03"
    - name: --num-layers
      parameterType: int
      feasibleSpace:
        min: "2"
        max: "5"
    - name: --optimizer
      parameterType: categorical
      feasibleSpace:
        list:
          - sgd
          - adam
          - ftrl
  trialTemplate:
    goTemplate:
      rawTemplate: |-
        apiVersion: batch/v1
        kind: Job
        metadata:
          name: {{.Trial}}
          namespace: {{.NameSpace}}
        spec:
          template:
            spec:
              containers:
              - name: {{.Trial}}
                image: docker.io/kubeflowkatib/mxnet-mnist
                command:
                - "python3"
                - "/opt/mxnet-mnist/mnist.py"
                - "--batch-size=64"
                {{- with .HyperParameters}}
                {{- range .}}
                - "{{.Name}}={{.Value}}"
                {{- end}}
                {{- end}}
              restartPolicy: Never