wrapped-failing-pytorch-job.yaml

apiVersion: workload.codeflare.dev/v1beta2
kind: AppWrapper
metadata:
  name: sample-failing-pytorch-job
  labels:
    kueue.x-k8s.io/queue-name: default-queue
spec:
  components:
  - template:
      apiVersion: "kubeflow.org/v1"
      kind: PyTorchJob
      metadata:
        name: pytorch-simple
      spec:
        pytorchReplicaSpecs:
          Master:
            replicas: 1
            restartPolicy: Never
            template:
              spec:
                containers:
                - name: pytorch
                  image: docker.io/kubeflowkatib/pytorch-mnist-cpu:v1beta1-fc858d1
                  command:
                  - "python3"
                  - "/opt/pytorch-mnist/mnist.py"
                  - "--epochs=1"
                  resources:
                    requests:
                      cpu: 1
          Worker:
            replicas: 1
            restartPolicy: Never
            template:
              spec:
                containers:
                - name: pytorch
                  image: docker.io/kubeflowkatib/pytorch-mnist-cpu:v1beta1-fc858d1
                  command:
                  - sleep 10; exit 1
                  resources:
                    requests:
                      cpu: 1