Get training job details.
Try it now
Test
RAM authorization
Request syntax
GET /api/v1/trainingjobs/{TrainingJobId} HTTP/1.1
Path Parameters
|
Parameter |
Type |
Required |
Description |
Example |
| TrainingJobId |
string |
Yes |
The ID of the training job. |
train129f212o89d |
Request parameters
|
Parameter |
Type |
Required |
Description |
Example |
No parameters required.
Response elements
|
Element |
Type |
Description |
Example |
|
object |
|||
| OutputChannels |
array<object> |
The configurations for the output data channels of the training job. |
|
|
object |
The configuration for an output data channel. |
||
| Name |
string |
The name of the output data. |
model |
| OutputUri |
string |
The URI of the output data. |
oss://test-bucket.oss-cn-hangzhou-internal.aliyuncs.com/path/to/output/model/ |
| DatasetId |
string |
The dataset ID. |
d-8o0hh35po15ejcdq2p |
| VersionName |
string |
The dataset version. |
v1 |
| Status |
string |
The status of the training job. |
Running |
| HyperParameters |
array<object> |
The hyperparameter settings for the training job. |
|
|
object |
A hyperparameter for the training job. |
||
| Name |
string |
The name of the hyperparameter. |
learning_rate |
| Value |
string |
The value of the hyperparameter. |
0.0001 |
| TrainingJobName |
string |
The training job name. |
qwen_llm |
| TrainingJobId |
string |
The training job ID. |
traini6hhxiq69eo |
| Scheduler |
object |
The scheduling configuration for the training job. |
|
| MaxRunningTimeInSeconds |
string |
The maximum runtime of the training job, in seconds. If the value is 0, the runtime is not limited. |
0 |
| MaxRunningTimeInMinutes |
string |
The maximum runtime, in minutes. |
100 |
| ReasonMessage |
string |
The reason for the training job failure. |
None |
| WorkspaceId |
string |
The workspace ID. |
86995 |
| ComputeResource |
object |
The compute resource configuration. |
|
| EcsCount |
integer |
The number of ECS instances. |
1 |
| EcsSpec |
string |
The ECS instance type. |
ecs.gn5-c8g1.2xlarge |
| ResourceId |
string |
The resource quota ID. |
quotam670lixikcl |
| ResourceName |
string |
The resource quota name. |
quota |
| InstanceCount |
integer |
The number of instances used from the resource quota. |
1 |
| InstanceSpec |
object |
The instance specification for the resource quota. |
|
| CPU |
string |
The number of vCPUs for the instance. |
8 |
| Memory |
string |
The memory size for the instance, in GiB. |
32 |
| SharedMemory |
string |
The shared memory size for the instance, in GiB. |
32 |
| GPU |
string |
The number of GPUs for the instance. |
1 |
| GPUType |
string |
The GPU type of the instance. |
V100 |
| UseSpotInstance |
boolean |
Indicates whether to use spot instances. |
true |
| SpotSpec |
object |
The configuration for spot instances. |
|
| SpotStrategy |
string |
The bidding policy for the spot instance. Valid values:
|
SpotWithPriceLimit |
| SpotDiscountLimit |
number |
The maximum hourly price for the spot instance. This parameter applies only when |
0.9 |
| Labels |
array<object> |
The labels for the training job. |
|
|
object |
A label for the training job. |
||
| Key |
string |
The label key. |
CreatedBy |
| Value |
string |
The label value. |
QuickStart |
| AlgorithmProvider |
string |
The algorithm provider. |
pai |
| InputChannels |
array<object> |
The configurations for the input data channels of the training job. |
|
|
object |
The configuration for an input data channel. |
||
| DatasetId |
string |
The dataset ID. |
d-475megosidivjfgfq6 |
| Name |
string |
The name of the input data. |
model |
| InputUri |
string |
The URI of the input data. |
oss://test-bucket.oss-cn-hangzhou-internal.aliyuncs.com/path/to/input/model/ |
| Options |
string |
The file system parameters for the input data. |
ossAppendable=true |
| VersionName |
string |
The dataset version. |
v1 |
| AlgorithmName |
string |
The algorithm name. |
llm_training |
| ReasonCode |
string |
The reason code for the training job's status. |
TrainingJobSucceed |
| GmtModifiedTime |
string |
The time when the training job status was last updated. |
2024-07-10T11:49:47Z |
| StatusTransitions |
array<object> |
The status transitions for the training job. |
|
|
object |
A status transition of the training job. |
||
| EndTime |
string |
The end time of the status. |
2024-07-10T11:49:47Z |
| ReasonCode |
string |
The status code. |
TrainingJobSucceed |
| ReasonMessage |
string |
The message for the status update. |
KubeDL job runs successfully |
| StartTime |
string |
The start time of the status. |
2024-07-10T11:49:47Z |
| Status |
string |
The status. |
Creating |
| TrainingJobDescription |
string |
The training job description. |
Qwen2大语言模型训练。 |
| UserId |
string |
The user ID. |
123456789 |
| AlgorithmVersion |
string |
The algorithm version. |
v0.0.1 |
| LatestMetrics |
array<object> |
The latest metrics for the training job. |
|
|
object |
A monitoring metric for the training job. |
||
| Name |
string |
The name of the metric. |
loss |
| Timestamp |
string |
The time when the metric was collected. |
2024-07-10T11:49:47Z |
| Value |
number |
The value of the metric. |
0.11 |
| GmtCreateTime |
string |
The time when the training job was created. |
2024-07-10T11:49:47Z |
| RequestId |
string |
The request ID. |
473469C7-AA6F-4DC5-B3DB-A3DC0DE3C83E |
| Instances |
array<object> |
The instances for the training job. |
|
|
object |
A training job instance. |
||
| Name |
string |
The instance name. |
train1oug3yehan4-master-0 |
| Role |
string |
The instance role. |
master |
| Status |
string |
The instance status. |
Succeeded |
| AlgorithmId |
string |
The training algorithm ID. |
algo-xsldfvu1334 |
| TrainingJobUrl |
string |
The URL of the training job details page. |
https://pai.console.aliyun.com/?regionId=cn-hangzhou&workspaceId=1234#/training/jobs/train1ouyadsl8n4 |
| RoleArn |
string |
The Alibaba Cloud Resource Name (ARN) of the RAM role used for delegated authorization. |
acs:ram::{accountID}:role/{roleName} |
| AlgorithmSpec | AlgorithmSpec |
The definition of the temporary algorithm. |
|
| IsTempAlgo |
boolean |
Indicates whether a temporary algorithm is used. |
true |
| LatestProgress |
object |
The latest progress of the training job. |
|
| OverallProgress |
object |
The overall progress of the training job. |
|
| Timestamp |
string |
The timestamp of the progress update. |
2023-07-04T13:20:18Z |
| Value |
number |
The progress value. |
0.75 |
| RemainingTime |
object |
The estimated remaining time for the training job to complete, in seconds. |
|
| Timestamp |
string |
The timestamp of the progress update. |
2023-07-04T13:20:18Z |
| Value |
integer |
The remaining time, in seconds. |
3600 |
| UserVpc |
object |
The user's VPC configuration. |
|
| VpcId |
string |
The VPC ID. |
vpc-abcdef**** |
| SwitchId |
string |
The vSwitch ID. |
vs-abcdef**** |
| SecurityGroupId |
string |
The security group ID. |
sg-abcdef**** |
| ExtendedCIDRs |
array |
The configuration for the extended CIDR blocks. |
|
|
string |
An extended CIDR block. |
192.168.0.1/24 |
|
| OutputModel |
object |
The model generated by the training job. |
|
| Uri |
string |
The URI of the model. |
oss://test-bucket.oss-cn-hangzhou-internal.aliyuncs.com/path/to/model/output/ |
| OutputChannelName |
string |
The name of the output channel for the model. |
model |
| Settings | JobSettings |
The additional settings for the training job. |
|
| ExperimentConfig |
object |
The configuration of the experiment associated with the training job. |
|
| ExperimentId |
string |
The ID of the associated experiment. |
exp-ds9aefia90v |
| ExperimentName |
string |
The name of the associated experiment. |
large_language_model_train |
| Duration |
integer |
The duration of the training job, in seconds. |
7200 |
| Environments |
object |
The environment variables for the training job. |
|
|
string |
An environment variable for the training job. |
debug=true |
|
| PythonRequirements |
array |
The required Python packages for the training job. |
|
|
string |
A required Python package for the training job. |
torch>=2.2.0 |
|
| Priority |
integer |
The priority of the training job. |
0 |
| AssignNodeSpec |
AssignNodeSpec |
Examples
Success response
JSON format
{
"OutputChannels": [
{
"Name": "model",
"OutputUri": "oss://test-bucket.oss-cn-hangzhou-internal.aliyuncs.com/path/to/output/model/",
"DatasetId": "d-8o0hh35po15ejcdq2p",
"VersionName": "v1"
}
],
"Status": "Running",
"HyperParameters": [
{
"Name": "learning_rate",
"Value": "0.0001"
}
],
"TrainingJobName": "qwen_llm",
"TrainingJobId": "traini6hhxiq69eo",
"Scheduler": {
"MaxRunningTimeInSeconds": "0",
"MaxRunningTimeInMinutes": "100"
},
"ReasonMessage": "None",
"WorkspaceId": "86995",
"ComputeResource": {
"EcsCount": 1,
"EcsSpec": "ecs.gn5-c8g1.2xlarge",
"ResourceId": "quotam670lixikcl",
"ResourceName": "quota",
"InstanceCount": 1,
"InstanceSpec": {
"CPU": "8",
"Memory": "32",
"SharedMemory": "32",
"GPU": "1",
"GPUType": "V100"
},
"UseSpotInstance": true,
"SpotSpec": {
"SpotStrategy": "SpotWithPriceLimit",
"SpotDiscountLimit": 0.9
}
},
"Labels": [
{
"Key": "CreatedBy",
"Value": "QuickStart"
}
],
"AlgorithmProvider": "pai",
"InputChannels": [
{
"DatasetId": "d-475megosidivjfgfq6",
"Name": "model",
"InputUri": "oss://test-bucket.oss-cn-hangzhou-internal.aliyuncs.com/path/to/input/model/",
"Options": "ossAppendable=true",
"VersionName": "v1"
}
],
"AlgorithmName": "llm_training",
"ReasonCode": "TrainingJobSucceed",
"GmtModifiedTime": "2024-07-10T11:49:47Z",
"StatusTransitions": [
{
"EndTime": "2024-07-10T11:49:47Z",
"ReasonCode": "TrainingJobSucceed",
"ReasonMessage": "KubeDL job runs successfully",
"StartTime": "2024-07-10T11:49:47Z",
"Status": "Creating"
}
],
"TrainingJobDescription": "Qwen2大语言模型训练。",
"UserId": "123456789",
"AlgorithmVersion": "v0.0.1",
"LatestMetrics": [
{
"Name": "loss",
"Timestamp": "2024-07-10T11:49:47Z",
"Value": 0.11
}
],
"GmtCreateTime": "2024-07-10T11:49:47Z",
"RequestId": "473469C7-AA6F-4DC5-B3DB-A3DC0DE3C83E",
"Instances": [
{
"Name": "train1oug3yehan4-master-0",
"Role": "master",
"Status": "Succeeded"
}
],
"AlgorithmId": "algo-xsldfvu1334",
"TrainingJobUrl": "https://pai.console.aliyun.com/?regionId=cn-hangzhou&workspaceId=1234#/training/jobs/train1ouyadsl8n4",
"RoleArn": "acs:ram::{accountID}:role/{roleName}",
"AlgorithmSpec": {
"OutputChannels": [
{
"Description": "",
"Required": true,
"Properties": {
"test": "test",
"test2": 1
},
"Name": "",
"SupportedChannelTypes": [
""
]
}
],
"HyperParameters": [
{
"DefaultValue": "",
"Type": "",
"Description": "",
"Required": true,
"Name": "",
"Range": {
"Enum": [
""
],
"MinLength": 0,
"MaxLength": 0,
"Minimum": "",
"Maximum": "",
"ExclusiveMinimum": true,
"ExclusiveMaximum": true,
"Pattern": ""
},
"DisplayName": ""
}
],
"JobType": "",
"Command": [
""
],
"MetricDefinitions": [
{
"Description": "train dataset oob score",
"Regex": ".*train:oob_score=([-+]?[0-9]*\\\\.?[0-9]+(?:[eE][-+]?[0-9]+)?).*",
"Name": "train:oob_score"
}
],
"InputChannels": [
{
"Description": "",
"Required": true,
"Properties": {
"test": "test",
"test2": 1
},
"Name": "",
"SupportedChannelTypes": [
""
]
}
],
"SupportsDistributedTraining": true,
"Image": "",
"SupportedInstanceTypes": [
""
],
"ComputeResource": {
"Policy": {
"Version": "",
"Value": ""
}
},
"CodeDir": {
"LocationType": "",
"LocationValue": {
"test": "test",
"test2": 1
}
},
"Customization": {
"CodeDir": true
},
"ResourceRequirements": [
{
"Key": "SupportedMachineTypes",
"Operator": "in",
"Values": [
"GPU"
]
}
],
"ProgressDefinitions": {
"OverallProgress": {
"Description": "",
"Regex": ""
},
"RemainingTime": {
"Description": "",
"Regex": ""
}
}
},
"IsTempAlgo": true,
"LatestProgress": {
"OverallProgress": {
"Timestamp": "2023-07-04T13:20:18Z",
"Value": 0.75
},
"RemainingTime": {
"Timestamp": "2023-07-04T13:20:18Z",
"Value": 3600
}
},
"UserVpc": {
"VpcId": "vpc-abcdef****",
"SwitchId": "vs-abcdef****",
"SecurityGroupId": "sg-abcdef****",
"ExtendedCIDRs": [
"192.168.0.1/24"
]
},
"OutputModel": {
"Uri": "oss://test-bucket.oss-cn-hangzhou-internal.aliyuncs.com/path/to/model/output/",
"OutputChannelName": "model"
},
"Settings": {
"BusinessUserId": "166924",
"Caller": "SilkFlow",
"Tags": {
"key": ""
},
"PipelineId": "pid-123456",
"EnableTideResource": true,
"EnableErrorMonitoringInAIMaster": false,
"ErrorMonitoringArgs": "--enable-log-hang-detection true",
"EnableRDMA": true,
"EnableOssAppend": true,
"OversoldType": "AcceptQuotaOverSold",
"AdvancedSettings": {
"test": "test",
"test2": 1
},
"Driver": "535.54.03",
"EnableSanityCheck": true,
"SanityCheckArgs": "--sanity-check-timing=AfterJobFaultTolerant --sanity-check-timeout-ops=MarkJobFai",
"JobReservedMinutes": 30,
"JobReservedPolicy": "Always"
},
"ExperimentConfig": {
"ExperimentId": "exp-ds9aefia90v",
"ExperimentName": "large_language_model_train"
},
"Duration": 7200,
"Environments": {
"key": "debug=true"
},
"PythonRequirements": [
"torch>=2.2.0"
],
"Priority": 0,
"AssignNodeSpec": {
"EnableAssignNode": true,
"NodeNames": "",
"AntiAffinityNodeNames": ""
}
}
Error codes
See Error Codes for a complete list.
Release notes
See Release Notes for a complete list.