Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

apiVersion: sagemaker.amazonaws.com/v1
kind: HyperPodPyTorchJob
metadata:
  labels:
    app.kubernetes.io/name: HyperPod
    app.kubernetes.io/managed-by: kustomize
  name: &jobname xxx
  annotations:
    XXX: XXX
    ......
spec:
  nprocPerNode: "X"
  replicaSpecs:
    - name: 'XXX'
      replicas: 16
      template:
        spec:
          nodeSelector:
            beta.kubernetes.io/instance-type: ml.p5.48xlarge
          containers:
            - name: XXX
              image: XXX
              imagePullPolicy: Always
              ports:
                - containerPort: 8080 # This is the port that HyperPodElasticAgent listens to
              resources:
                limits:
                  nvidia.com/gpu: 8
                  hugepages-2Mi: 5120Mi
                requests:
                  nvidia.com/gpu: 8
                  hugepages-2Mi: 5120Mi
                  memory: 32000Mi
          ......        
  runPolicy:
    jobMaxRetryCount: 50
    restartPolicy:
      numRestartBeforeFullJobRestart: 3 
      evalPeriodSeconds: 21600 
      maxFullJobRestarts: 1
    cleanPodPolicy: "All"
    logMonitoringConfiguration: 
      - name: "JobStart"
        logPattern: ".*Experiment configuration.*" # This is the start of the training script
        expectedStartCutOffInSeconds: 120 # Expected match in the first 2 minutes
      - name: "JobHangingDetection"
        logPattern: ".*\\[Epoch 0 Batch \\d+.*'training_loss_step': (\\d+(\\.\\d+)?).*"
        expectedRecurringFrequencyInSeconds: 300 # If next batch is not printed within 5 minute, consider it hangs. Or if loss is not decimal (e.g. nan) for 2 minutes, mark it hang as well.
        expectedStartCutOffInSeconds: 600 # Allow 10 minutes of job startup time
      - name: "NoS3CheckpointingDetection"
        logPattern: ".*The checkpoint is finalized. All shards is written.*"
        expectedRecurringFrequencyInSeconds: 600 # If next checkpoint s3 upload doesn't happen within 10 mins, mark it hang.
        expectedStartCutOffInSeconds: 1800 # Allow 30 minutes for first checkpoint upload
      - name: "LowThroughputDetection"
        logPattern: ".*\\[Epoch 0 Batch \\d+.*'samples\\/sec': (\\d+(\\.\\d+)?).*"
        metricThreshold: 80 # 80 samples/sec
        operator: "lteq"
        metricEvaluationDataPoints: 25 # if throughput lower than threshold for 25 datapoints, kill the job
      

logging.basicConfig(format="%(asctime)s [%(levelname)s] %(name)s: %(message)s", level=logging.INFO, stream=sys.stdout)

apiVersion: sagemaker.amazonaws.com/v1
kind: HyperPodPyTorchJob
metadata:
  labels:
    kueue.x-k8s.io/queue-name: user-queue # Specify the queue to run the job.
  name: hyperpodpytorchjob-sample
spec:
  nprocPerNode: "1"
  runPolicy:
    cleanPodPolicy: "None"
  replicaSpecs: 
    - name: pods
      replicas: 1
      spares: 1 # Specify how many spare nodes to reserve.
      template:
        spec:
          containers:
            - name: XXX
              image: XXX
              
              imagePullPolicy: Always
              ports:
                - containerPort: 8080
              resources:
                requests:
                  nvidia.com/gpu: "0"
                limits:
                  nvidia.com/gpu: "0"
      

Memantau

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  name: hyperpod-training-operator
  namespace: aws-hyperpod
spec:
  ......
  endpoints:
    - port: 8081
      path: /metrics
      interval: 15s

export AGENT_CMD="--backend=nccl"
exec hyperpodrun --server-host=${AGENT_HOST} --server-port=${AGENT_PORT} \
    --tee=3 --log_dir=/tmp/hyperpod \
    --nnodes=${NNODES} --nproc-per-node=${NPROC_PER_NODE} \
    --pre-train-script=/workspace/echo.sh --pre-train-args='Pre-training script' \
    --post-train-script=/workspace/echo.sh --post-train-args='Post-training script' \
    /workspace/mnist.py --epochs=1000 ${AGENT_CMD}

runPolicy:
    jobMaxRetryCount: 10
    cleanPodPolicy: "None"
    logMonitoringConfiguration:
      - name: "JobStartGracePeriod"
        # Sample log line: [default0]:2025-06-17 05:51:29,300 [INFO] __main__: Train Epoch: 5 [0/60000 (0%)]       loss=0.8470
        logPattern: ".*Train Epoch.*"  
        expectedStartCutOffInSeconds: 60 
      - name: "JobHangingDetection"
        logPattern: ".*Train Epoch.*"
        expectedRecurringFrequencyInSeconds: 10 # if the next batch is not printed within 10 seconds

runPolicy:
  jobMaxRetryCount: 10
  cleanPodPolicy: "None"
  logMonitoringConfiguration:
    - name: "LossSpikeDetection"
      logPattern: ".*training_loss_step (\\d+(?:\\.\\d+)?).*"   # training_loss_step 5.0
      metricThreshold: 2.0
      operator: "gt"
      metricEvaluationDataPoints: 5 # if loss higher than threshold for 5 data points, restart the job

runPolicy:
  jobMaxRetryCount: 10
  cleanPodPolicy: "None"
  logMonitoringConfiguration:
    - name: "TFLOPs"
      logPattern: ".* (.+)TFLOPs.*"    # Training model, speed: X TFLOPs...
      expectedRecurringFrequencyInSeconds: 5        
      metricThreshold: 100       # if Tflops is less than 100 for 5 data points, restart the job       
      operator: "lt"
      metricEvaluationDataPoints: 5

runPolicy:
  jobMaxRetryCount: 10
  cleanPodPolicy: "None"
  logMonitoringConfiguration:
    - name: "GPU Error"
      logPattern: ".*RuntimeError.*out of memory.*"
      faultOnMatch: true