all: logCollection: http kubeflow: maxExecDuration: 15m nniManagerIp: kubeflowConfig: operator: tf-operator apiVersion: v1alpha2 storage: azureStorage keyVault: vaultName: name: azureStorage: accountName: azureShare: trial: worker: replicas: 1 command: gpuNum: 1 cpuNum: 1 memoryMB: 8192 image: trainingServicePlatform: kubeflow frameworkcontroller: maxExecDuration: 15m nniManagerIp: frameworkcontrollerConfig: serviceAccountName: frameworkbarrier storage: azureStorage keyVault: vaultName: name: azureStorage: accountName: azureShare: trial: taskRoles: - name: worker taskNum: 1 command: gpuNum: 1 cpuNum: 1 memoryMB: 8192 image: frameworkAttemptCompletionPolicy: minFailedTaskCount: 1 minSucceededTaskCount: 1 trainingServicePlatform: frameworkcontroller local: trainingServicePlatform: local paiYarn: nniManagerIp: maxExecDuration: 15m paiYarnConfig: host: passWord: userName: trainingServicePlatform: paiYarn trial: gpuNum: 1 cpuNum: 1 dataDir: image: memoryMB: 8192 outputDir: virtualCluster: pai: nniManagerIp: maxExecDuration: 15m paiConfig: host: userName: trainingServicePlatform: pai trial: gpuNum: 1 cpuNum: 1 image: memoryMB: 8192 nniManagerNFSMountPath: containerNFSMountPath: paiStoragePlugin: remote: machineList: - ip: passwd: port: username: trainingServicePlatform: remote