trainer.yaml

apiVersion: batch/v1
kind: Job
metadata:
  name: vgg16job-trainer
spec:
  parallelism: 20
  completions: 20
  template:
    metadata:
      labels:
        paddle-job: vgg16job
    spec:
      imagePullSecrets:
        - name: job-registry-secret
      hostNetwork: true
      containers:
      - name: trainer
        image: "registry.baidu.com/paddlepaddle/rawjob:vgg16_fluid"
        imagePullPolicy: Always
        command: ["paddle_k8s", "start_fluid"]
        env:
        - name: PADDLE_JOB_NAME
          value: vgg16job
        - name: TRAINING_ROLE
          value: "TRAINER"
        - name: TRAINERS
          value: "20"
        - name: PSERVERS
          value: "10"
        - name: TOPOLOGY
          value: ""
        - name: ENTRY
          value: "cd /workspace && LD_LIBRARY_PATH=/usr/local/lib MKL_NUM_THREADS=1 python /workspace/vgg16.py --local 0"
        - name: TRAINER_PACKAGE
          value: "/workspace"
        - name: PADDLE_INIT_PORT
          value: "30236"
        - name: PADDLE_INIT_NICS
          value: "xgbe0"
        - name: PADDLE_INIT_TRAINER_COUNT
          value: "1"
        - name: PADDLE_INIT_PORTS_NUM
          value: "1"
        - name: PADDLE_INIT_PORTS_NUM_FOR_SPARSE
          value: "1"
        - name: PADDLE_INIT_NUM_GRADIENT_SERVERS
          value: "20"
        - name: PADDLE_INIT_NUM_PASSES
          value: "1"
        - name: PADDLE_INIT_USE_GPU
          value: "0"
        - name: LD_LIBRARY_PATH
          value: "/usr/local/nvidia/lib64"
        - name: NAMESPACE
          valueFrom:
            fieldRef:
              fieldPath: "metadata.namespace"
        - name: POD_IP
          valueFrom:
            fieldRef:
              fieldPath: "status.podIP"
        resources:
          requests:
            memory: 40Gi
            cpu: 2
          limits:
            memory: 40Gi
            cpu: 2
      restartPolicy: Never