forked from docs/doc-exports
Lai, Weijian
2f0818cf3d
Reviewed-by: Pruthi, Vineet <vineet.pruthi@t-systems.com> Co-authored-by: Lai, Weijian <laiweijian4@huawei.com> Co-committed-by: Lai, Weijian <laiweijian4@huawei.com>
150 lines
7.6 KiB
HTML
150 lines
7.6 KiB
HTML
<a name="ShowTrainingJobMetrics"></a><a name="ShowTrainingJobMetrics"></a>
|
|
|
|
<h1 class="topictitle1">Querying the Running Metrics of a Specified Task in a Training Job</h1>
|
|
<div id="body0000001296628300"><div class="section"><h4 class="sectiontitle">Function</h4><p>This API is used to query the running metrics of a specified task in a training job.</p>
|
|
</div>
|
|
<div class="section"><h4 class="sectiontitle">URI</h4><p>GET /v2/{project_id}/training-jobs/{training_job_id}/metrics/{task_id}</p>
|
|
|
|
<div class="tablenoborder"><table cellpadding="4" cellspacing="0" summary="" frame="border" border="1" rules="all"><caption><b>Table 1 </b>Path Parameters</caption><thead align="left"><tr><th align="left" class="cellrowborder" valign="top" width="20%" id="mcps1.3.2.3.2.5.1.1"><p>Parameter</p>
|
|
</th>
|
|
<th align="left" class="cellrowborder" valign="top" width="20%" id="mcps1.3.2.3.2.5.1.2"><p>Mandatory</p>
|
|
</th>
|
|
<th align="left" class="cellrowborder" valign="top" width="20%" id="mcps1.3.2.3.2.5.1.3"><p>Type</p>
|
|
</th>
|
|
<th align="left" class="cellrowborder" valign="top" width="40%" id="mcps1.3.2.3.2.5.1.4"><p>Description</p>
|
|
</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody><tr><td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.2.3.2.5.1.1 "><p>project_id</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.2.3.2.5.1.2 "><p>Yes</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.2.3.2.5.1.3 "><p>String</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="40%" headers="mcps1.3.2.3.2.5.1.4 "><p>Project ID. For details, see <a href="modelarts_03_0147.html">Obtaining a Project ID</a>.</p>
|
|
</td>
|
|
</tr>
|
|
<tr><td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.2.3.2.5.1.1 "><p>training_job_id</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.2.3.2.5.1.2 "><p>Yes</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.2.3.2.5.1.3 "><p>String</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="40%" headers="mcps1.3.2.3.2.5.1.4 "><p>ID of a training job.</p>
|
|
</td>
|
|
</tr>
|
|
<tr><td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.2.3.2.5.1.1 "><p>task_id</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.2.3.2.5.1.2 "><p>Yes</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.2.3.2.5.1.3 "><p>String</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="40%" headers="mcps1.3.2.3.2.5.1.4 "><p>Name of a training job.</p>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
</div>
|
|
</div>
|
|
<div class="section"><h4 class="sectiontitle">Request Parameters</h4><p>None</p>
|
|
</div>
|
|
<div class="section"><h4 class="sectiontitle">Response Parameters</h4><p><strong>Status code: 200</strong></p>
|
|
|
|
<div class="tablenoborder"><table cellpadding="4" cellspacing="0" summary="" id="ShowTrainingJobMetrics__response_Metric" frame="border" border="1" rules="all"><caption><b>Table 2 </b>Response body parameters</caption><thead align="left"><tr><th align="left" class="cellrowborder" valign="top" width="20%" id="mcps1.3.4.3.2.4.1.1"><p>Parameter</p>
|
|
</th>
|
|
<th align="left" class="cellrowborder" valign="top" width="20%" id="mcps1.3.4.3.2.4.1.2"><p>Type</p>
|
|
</th>
|
|
<th align="left" class="cellrowborder" valign="top" width="60%" id="mcps1.3.4.3.2.4.1.3"><p>Description</p>
|
|
</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody><tr><td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.4.3.2.4.1.1 "><p>metrics</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.4.3.2.4.1.2 "><p>Array of <a href="#ShowTrainingJobMetrics__response_metrics">metrics</a> objects</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="60%" headers="mcps1.3.4.3.2.4.1.3 "><p>Running metrics.</p>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
</div>
|
|
|
|
<div class="tablenoborder"><a name="ShowTrainingJobMetrics__response_metrics"></a><a name="response_metrics"></a><table cellpadding="4" cellspacing="0" summary="" id="ShowTrainingJobMetrics__response_metrics" frame="border" border="1" rules="all"><caption><b>Table 3 </b>metrics</caption><thead align="left"><tr><th align="left" class="cellrowborder" valign="top" width="20%" id="mcps1.3.4.4.2.4.1.1"><p>Parameter</p>
|
|
</th>
|
|
<th align="left" class="cellrowborder" valign="top" width="20%" id="mcps1.3.4.4.2.4.1.2"><p>Type</p>
|
|
</th>
|
|
<th align="left" class="cellrowborder" valign="top" width="60%" id="mcps1.3.4.4.2.4.1.3"><p>Description</p>
|
|
</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody><tr><td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.4.4.2.4.1.1 "><p>metric</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.4.4.2.4.1.2 "><p>String</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="60%" headers="mcps1.3.4.4.2.4.1.3 "><p>Running metric. The options are as follows: <strong>cpuUsage</strong>: CPU usage <strong>memUsage</strong>: physical memory usage <strong>gpuUtil</strong>: GPU utilization <strong>gpuMemUsage</strong>: GPU memory usage <strong>npuUtil</strong>: NPU utilization <strong>npuMemUsage</strong>: NPU memory usage</p>
|
|
</td>
|
|
</tr>
|
|
<tr><td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.4.4.2.4.1.1 "><p>value</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="20%" headers="mcps1.3.4.4.2.4.1.2 "><p>Array of numbers</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="60%" headers="mcps1.3.4.4.2.4.1.3 "><p>Value of a running metric. An average value is collected every minute.</p>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
</div>
|
|
</div>
|
|
<div class="section"><h4 class="sectiontitle">Example Requests</h4><p>The following shows how to query the running metrics of the <strong>work-0</strong> task of the training job whose UUID is <strong>2cd88daa-31a4-40a8-a58f-d186b0e93e4f</strong>.</p>
|
|
<pre class="screen">GET https://endpoint/v2/{project_id}/training-jobs/2cd88daa-31a4-40a8-a58f-d186b0e93e4f/metrics/worker-0</pre>
|
|
</div>
|
|
<div class="section"><h4 class="sectiontitle">Example Responses</h4><p><strong>Status code: 200</strong></p>
|
|
<p>ok</p>
|
|
<pre class="screen">{
|
|
"metrics" : [ {
|
|
"metric" : "cpuUsage",
|
|
"value" : [ -1, -1, 2.43, 4.524, 6.714, 12.422, 9.214, 5.36, 7.5, 10.088, 8.975, 11.423, 11.548, 14.563, 16.833 ]
|
|
}, {
|
|
"metric" : "memUsage",
|
|
"value" : [ -1, -1, 0.04, 0.521, 1.652, 4.252, 6.433, 7.384, 7.982, 8.718, 9.365, 9.881, 10.192, 9.994, 9.005 ]
|
|
}, {
|
|
"metric" : "gpuUtil",
|
|
"value" : [ -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 ]
|
|
}, {
|
|
"metric" : "gpuMemUsage",
|
|
"value" : [ -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 ]
|
|
}, {
|
|
"metric" : "npuUtil",
|
|
"value" : [ -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 ]
|
|
}, {
|
|
"metric" : "npuMemUsage",
|
|
"value" : [ -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 ]
|
|
} ]
|
|
}</pre>
|
|
</div>
|
|
<div class="section"><h4 class="sectiontitle">Status Codes</h4>
|
|
<div class="tablenoborder"><table cellpadding="4" cellspacing="0" summary="" id="ShowTrainingJobMetrics__status_code" frame="border" border="1" rules="all"><thead align="left"><tr><th align="left" class="cellrowborder" valign="top" width="15%" id="mcps1.3.7.2.1.3.1.1"><p>Status Code</p>
|
|
</th>
|
|
<th align="left" class="cellrowborder" valign="top" width="85%" id="mcps1.3.7.2.1.3.1.2"><p>Description</p>
|
|
</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody><tr><td class="cellrowborder" valign="top" width="15%" headers="mcps1.3.7.2.1.3.1.1 "><p>200</p>
|
|
</td>
|
|
<td class="cellrowborder" valign="top" width="85%" headers="mcps1.3.7.2.1.3.1.2 "><p>ok</p>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
</div>
|
|
</div>
|
|
<div class="section"><h4 class="sectiontitle">Error Codes</h4><p>See <a href="modelarts_03_0095.html">Error Codes</a>.</p>
|
|
</div>
|
|
</div>
|
|
<div>
|
|
<div class="familylinks">
|
|
<div class="parentlink"><strong>Parent topic:</strong> <a href="trainingJobs.html">Training Job Management</a></div>
|
|
</div>
|
|
</div>
|
|
|