Katib random example

1. kubectl -n moey920 get experiment random -o yaml

apiVersion: kubeflow.org/v1beta1
kind: Experiment
metadata:
  annotations:
    kubectl.kubernetes.io/last-applied-configuration: |
      {"apiVersion":"kubeflow.org/v1beta1","kind":"Experiment","metadata":{"annotations":{},"name":"random","namespace":"moey920"},"spec":{"algorithm":{"algorithmName":"random"},"maxFailedTrialCount":3,"maxTrialCount":12,"objective":{"additionalMetricNames":["Train-accuracy"],"goal":0.99,"objectiveMetricName":"Validation-accuracy","type":"maximize"},"parallelTrialCount":3,"parameters":[{"feasibleSpace":{"max":"0.03","min":"0.01"},"name":"lr","parameterType":"double"},{"feasibleSpace":{"max":"5","min":"2"},"name":"num-layers","parameterType":"int"},{"feasibleSpace":{"list":["sgd","adam","ftrl"]},"name":"optimizer","parameterType":"categorical"}],"trialTemplate":{"primaryContainerName":"training-container","trialParameters":[{"description":"Learning rate for the training model","name":"learningRate","reference":"lr"},{"description":"Number of training model layers","name":"numberLayers","reference":"num-layers"},{"description":"Training model optimizer (sdg, adam or ftrl)","name":"optimizer","reference":"optimizer"}],"trialSpec":{"apiVersion":"batch/v1","kind":"Job","spec":{"template":{"spec":{"containers":[{"command":["python3","/opt/mxnet-mnist/mnist.py","--batch-size=64","--lr=${trialParameters.learningRate}","--num-layers=${trialParameters.numberLayers}","--optimizer=${trialParameters.optimizer}"],"image":"docker.io/kubeflowkatib/mxnet-mnist:v1beta1-45c5727","name":"training-container"}],"restartPolicy":"Never"}}}}}}}
  creationTimestamp: "2021-12-03T09:04:06Z"
  finalizers:
  - update-prometheus-metrics
  generation: 1
  name: random
  namespace: moey920
  resourceVersion: "34104516"
  uid: da5597ce-7e40-4492-a59f-8fbc13350b89
spec:
  algorithm:
    algorithmName: random
  maxFailedTrialCount: 3
  maxTrialCount: 12
  metricsCollectorSpec:
    collector:
      kind: StdOut
  objective:
    additionalMetricNames:
    - Train-accuracy
    goal: 0.99
    metricStrategies:
    - name: Validation-accuracy
      value: max
    - name: Train-accuracy
      value: max
    objectiveMetricName: Validation-accuracy
    type: maximize
  parallelTrialCount: 3
  parameters:
  - feasibleSpace:
      max: "0.03"
      min: "0.01"
    name: lr
    parameterType: double
  - feasibleSpace:
      max: "5"
      min: "2"
    name: num-layers
    parameterType: int
  - feasibleSpace:
      list:
      - sgd
      - adam
      - ftrl
    name: optimizer
    parameterType: categorical
  resumePolicy: LongRunning
  trialTemplate:
    failureCondition: status.conditions.#(type=="Failed")#|#(status=="True")#
    primaryContainerName: training-container
    successCondition: status.conditions.#(type=="Complete")#|#(status=="True")#
    trialParameters:
    - description: Learning rate for the training model
      name: learningRate
      reference: lr
    - description: Number of training model layers
      name: numberLayers
      reference: num-layers
    - description: Training model optimizer (sdg, adam or ftrl)
      name: optimizer
      reference: optimizer
    trialSpec:
      apiVersion: batch/v1
      kind: Job
      spec:
        template:
          spec:
            containers:
            - command:
              - python3
              - /opt/mxnet-mnist/mnist.py
              - --batch-size=64
              - --lr=${trialParameters.learningRate}
              - --num-layers=${trialParameters.numberLayers}
              - --optimizer=${trialParameters.optimizer}
              image: docker.io/kubeflowkatib/mxnet-mnist:v1beta1-45c5727
              name: training-container
            restartPolicy: Never
status:
  conditions:
  - lastTransitionTime: "2021-12-03T09:04:06Z"
    lastUpdateTime: "2021-12-03T09:04:06Z"
    message: Experiment is created
    reason: ExperimentCreated
    status: "True"
    type: Created
  - lastTransitionTime: "2021-12-03T09:04:57Z"
    lastUpdateTime: "2021-12-03T09:04:57Z"
    message: Experiment is running
    reason: ExperimentRunning
    status: "True"
    type: Running
  currentOptimalTrial:
    bestTrialName: ""
    observation:
      metrics: null
    parameterAssignments: null
  runningTrialList:
  - random-b5d4plgx
  - random-qwllpfh9
  - random-vbc2tscx
  startTime: "2021-12-03T09:04:06Z"
  trials: 3
  trialsRunning: 3

마지막 값 status.conditions.type이 Succeeded이면 실험이 완료된 것입니다.