from-volume-resume.yaml

---
apiVersion: kubeflow.org/v1beta1
kind: Experiment
metadata:
  namespace: kubeflow
  name: from-volume-resume
spec:
  objective:
    type: minimize
    goal: 0.001
    objectiveMetricName: loss
  algorithm:
    algorithmName: random
  parallelTrialCount: 3
  maxTrialCount: 12
  maxFailedTrialCount: 3
  resumePolicy: FromVolume
  parameters:
    - name: lr
      parameterType: double
      feasibleSpace:
        min: "0.01"
        max: "0.05"
    - name: momentum
      parameterType: double
      feasibleSpace:
        min: "0.5"
        max: "0.9"
  trialTemplate:
    primaryContainerName: training-container
    trialParameters:
      - name: learningRate
        description: Learning rate for the training model
        reference: lr
      - name: momentum
        description: Momentum for the training model
        reference: momentum
    trialSpec:
      apiVersion: batch/v1
      kind: Job
      spec:
        template:
          spec:
            containers:
              - name: training-container
                image: docker.io/kubeflowkatib/pytorch-mnist-cpu:latest
                command:
                  - "python3"
                  - "/opt/pytorch-mnist/mnist.py"
                  - "--epochs=1"
                  - "--batch-size=16"
                  - "--lr=${trialParameters.learningRate}"
                  - "--momentum=${trialParameters.momentum}"
            restartPolicy: Never