GetExperiment - 获取实验详情

授权信息

请求参数

返回参数

示例

正常返回示例

JSON格式

{
  "Data": {
    "Task": {
      "TaskId": 167420,
      "CreateTime": 0,
      "UpdateTime": 0,
      "StartTime": 0,
      "EndTime": 0,
      "Params": {
        "key": "{}"
      },
      "Scene": "baseline",
      "Status": "success"
    },
    "Workload": {
      "WorkloadId": 13,
      "WorkloadName": "test",
      "WorkloadDescription": "test",
      "WorkloadType": "AI",
      "Family": "AI",
      "Scene": "NLP-LLM",
      "Scope": "common",
      "JobKind": "PyTorchJob",
      "DefaultCpuPerWorker": 90,
      "DefaultGpuPerWorker": 8,
      "DefaultMemoryPerWorker": 500,
      "DefaultShareMemory": 500,
      "ParamSettings": [
        {
          "ParamName": "ITERATION",
          "ParamDesc": "迭代数",
          "ParamValue": "100",
          "DefaultValue": "100",
          "ParamRegex": "[0-9]+",
          "ParamType": "number"
        }
      ],
      "StaticConfig": {
        "FrameWork": "pyTorch",
        "SoftwareStack": "python",
        "Os": "linux",
        "Parameters": "7B"
      },
      "VersionId": 1
    },
    "Resource": {
      "ResourceId": 189,
      "ResourceName": "ecs.r8y.4xlarge",
      "CpuCoreLimit": 90,
      "GpuLimit": 8,
      "MemoryLimit": 500,
      "MaxGpu": 8,
      "MaxCpuCore": 90,
      "MaxMemory": 500,
      "UserAccessParam": {
        "AccessId": "dev",
        "AccessKey": "test",
        "WorkspaceId": "123434542498",
        "Endpoint": "test"
      },
      "MachineType": {
        "MemoryInfo": "32x 64GB DDR4 3200 Memory",
        "Type": "Public",
        "BondNum": 5,
        "NodeCount": 1,
        "CpuInfo": "2x Intel Icelake 8369B 32C CPU",
        "NetworkInfo": "1x 100Gbps DP NIC for VPC \\n 4x 100Gbps DP RoCE NIC",
        "GpuInfo": "8x NVIDIA SXM4 80GB A100 GPU",
        "DiskInfo": "2x 480GB SATA SSD \\n 4x 3.84TB NVMe SSD",
        "NetworkMode": "2",
        "Name": "efg1.nvga1n"
      },
      "ResourceNodes": [
        {
          "NodeName": "InputCheck"
        }
      ]
    },
    "ExperimentId": 1726882991828689000,
    "CreateTime": 0,
    "UpdateTime": 0,
    "ExperimentName": "test",
    "ExperimentType": "AI",
    "ResourceName": "cifnews-guoyuan",
    "WorkloadName": "test",
    "StartTime": "2024-11-29 02:16:35",
    "EndTime": "2024-11-29 02:26:35",
    "Status": "RUNNING",
    "Results": {
      "ExperimentId": 1748274952976261000,
      "Duration": 764,
      "SecondsPerIteration": 1000,
      "SamplesPerSecond": 10,
      "Mfu": 54.2,
      "WarningWorker": [
        {
          "ExperimentId": 9,
          "Hostname": "whza008403",
          "PodName": "fluxserv-6fc89b45cf-w8wq6",
          "GpuNum": 8,
          "GpuName": "8x OAM 810 GPU",
          "WarningFlag": true,
          "WarningMsg": "存在慢节点",
          "ErrorFlag": true,
          "ErrorMsg": "错误信息",
          "Tflops": 14,
          "SamplesPerSecond": 15
        }
      ],
      "ErrorWorker": [
        {
          "ExperimentId": 97,
          "Hostname": "60.188.98.209",
          "PodName": "hzs-forge-sdxl-online-7ff4d86444-pc95h",
          "GpuNum": 8,
          "GpuName": "8x OAM 810 GPU",
          "WarningFlag": false,
          "WarningMsg": "无",
          "ErrorFlag": true,
          "ErrorMsg": "Connection reset",
          "Tflops": 12,
          "SamplesPerSecond": 23
        }
      ],
      "WarningBoundList": [
        {
          "Iteration": 10,
          "Upper": 56,
          "Lower": 14
        }
      ],
      "TaskIndividualResultList": [
        {
          "ExperimentId": 48,
          "Hostname": "p-jt-waf-app1",
          "PodName": "fluxserv-6fc89b45cf-w8wq6",
          "GpuNum": 8,
          "GpuName": "8x OAM 810 GPU",
          "WarningFlag": false,
          "WarningMsg": "无",
          "ErrorFlag": false,
          "ErrorMsg": "无",
          "Tflops": 16,
          "SamplesPerSecond": 28
        }
      ],
      "TaskIndividualResultMap": {
        "key": [
          {
            "ExperimentId": 54,
            "Hostname": "p-jt-waf-app1\n",
            "PodName": "fluxserv-6fc89b45cf-w8wq6",
            "GpuNum": 8,
            "GpuName": "8x OAM 810 GPU\n",
            "WarningFlag": false,
            "WarningMsg": "无",
            "ErrorFlag": false,
            "ErrorMsg": "无",
            "Tflops": 45,
            "SamplesPerSecond": 23
          }
        ]
      }
    },
    "SetParams": {
      "key": "{}"
    },
    "GetParams": {
      "key": "{}"
    },
    "EnvParams": {
      "CpuPerWorker": 90,
      "GpuPerWorker": 8,
      "MemoryPerWorker": 500,
      "ShareMemory": 500,
      "WorkerNum": 1,
      "CudaVersion": "1.0.0",
      "NCCLVersion": "1.0.0",
      "GpuDriverVersion": "1.0.0",
      "PyTorchVersion": "1.0.0",
      "ResourceNodes": [
        {
          "NodeName": "p-jt-waf-app1",
          "TotalCPU": 90,
          "TotalGPU": 8,
          "TotalMemory": 500,
          "RequestCPU": 90,
          "RequestGPU": 8,
          "RequestMemory": 500
        }
      ],
      "ExtendParam": {
        "key": "{}"
      }
    }
  },
  "RequestId": "E67E2E4C-2B47-5C55-AA17-1D771E070AEF",
  "AccessDeniedDetail": "{}",
  "TotalCount": 0
}

错误码

变更历史