# Example from: https://github.com/kubeflow/training-operator/tree/master/examples/pytorch/elastic/imagenet
apiVersion: "kubeflow.org/v1"
kind: PyTorchJob
metadata:
  name: imagenet-elastic-cpu
spec:
  elasticPolicy:
    rdzvBackend: etcd
    rdzvHost: etcd-service
    rdzvPort: 2379
    minReplicas: 2
    maxReplicas: 24
    maxRestarts: 100
    metrics:
      - type: Resource
        resource:
          name: cpu
          target:
            type: Utilization
            averageUtilization: 80
  pytorchReplicaSpecs:
    Worker:
      replicas: 2
      restartPolicy: OnFailure
      template:
        spec:
          containers:
            - name: pytorch
              image: kubeflow/pytorch-elastic-example-imagenet:latest
              imagePullPolicy: IfNotPresent
              resources:
                requests:
                  cpu: 4
              env:
              - name: LOGLEVEL
                value: DEBUG
              command:
                - python
                - -m
                - torch.distributed.run
                - /workspace/examples/imagenet.py
                - "--arch=resnet18"
                - "--epochs=20"
                - "--batch-size=32"
                - "--workers=0"
                - "/workspace/data/tiny-imagenet-200"