apiVersion: "kubeflow.org/v1alpha3"
kind: Experiment
metadata:
  namespace: kubeflow
  labels:
    controller-tools.k8s.io: "1.0"
  name: custom-metricscollector-example
spec:
  objective:
    type: maximize
    goal: 0.99
    objectiveMetricName: accuracy
  metricsCollectorSpec:
    source:
      fileSystemPath:
        path: "/katib/mnist.log"
        kind: File
    collector:
      kind: Custom
      customCollector:
        args:
        - -m
        - accuracy
        - -s
        - katib-db-manager.kubeflow:6789
        - -path
        - /katib/mnist.log
        image: kubeflowkatib/custom-metrics-collector:latest
        imagePullPolicy: Always
        name: custom-metrics-logger-and-collector
        env:
        - name: TrialNamePrefix
          valueFrom:
            fieldRef:
              fieldPath: metadata.name
  algorithm:
    algorithmName: random
  parallelTrialCount: 3
  maxTrialCount: 12
  maxFailedTrialCount: 3
  parameters:
    - name: --lr
      parameterType: double
      feasibleSpace:
        min: "0.01"
        max: "0.03"
    - name: --momentum
      parameterType: double
      feasibleSpace:
        min: "0.3"
        max: "0.7"
  trialTemplate:
    goTemplate:
        rawTemplate: |-
          apiVersion: batch/v1
          kind: Job
          metadata:
            name: {{.Trial}}
            namespace: {{.NameSpace}}
          spec:
            template:
              spec:
                containers:
                - name: {{.Trial}}
                  image: docker.io/kubeflowkatib/pytorch-mnist
                  imagePullPolicy: Always
                  command:
                  - "python"
                  - "/var/mnist.py"
                  - "--epochs=1"
                  {{- with .HyperParameters}}
                  {{- range .}}
                  - "{{.Name}}={{.Value}}"
                  {{- end}}
                  {{- end}}
                restartPolicy: Never