Trainings
Trainings are dedicated workloads that are specifically used for training models. They are by design preemptible workloads because they are used in unattended sessions where the scientists and researchers do not need to be present. These workloads are allowed to utilize resources over the project's quota.
Create a training workload using container related fields.
Authorizations
AuthorizationstringRequired
Bearer authentication
Body
and
Responses
202
Request completed successfully.
application/json
and
400
Bad submission request.
application/json
401
Unauthorized
application/json
403
Forbidden
application/json
503
unexpected error
application/json
post/api/v1/workloads/trainings
POST /api/v1/workloads/trainings HTTP/1.1
Host: app.run.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 4026
{
"name": "my-workload-name",
"useGivenNameAsPrefix": true,
"projectId": 1,
"clusterId": "71f69d83-ba66-4822-adf5-55ce55efd210",
"spec": {
"command": "python",
"args": "-x my-script.py",
"image": "python:3.8",
"imagePullPolicy": "Always",
"workingDir": "/home/myfolder",
"createHomeDir": true,
"probes": {
"readiness": {
"initialDelaySeconds": 1,
"periodSeconds": 1,
"timeoutSeconds": 1,
"successThreshold": 1,
"failureThreshold": 1,
"handler": {
"httpGet": {
"path": "/",
"port": 1,
"host": "example.com",
"scheme": "HTTP"
}
}
}
},
"nodeType": "my-node-type",
"nodePools": [
"my-node-pool-a",
"my-node-pool-b"
],
"podAffinity": {
"type": "Required",
"key": "text"
},
"tty": true,
"stdin": true,
"environmentVariables": [
{
"name": "HOME",
"value": "/home/my-folder",
"secret": {
"name": "postgress_secret",
"key": "POSTGRES_PASSWORD"
},
"configMap": {
"name": "my-config-map",
"key": "MY_POSTGRES_SCHEMA"
},
"podFieldRef": {
"path": "metadata.name"
},
"exclude": false,
"description": "Home directory of the user."
}
],
"annotations": [
{
"name": "billing",
"value": "my-billing-unit",
"exclude": false
}
],
"labels": [
{
"name": "stage",
"value": "initial-research",
"exclude": false
}
],
"tolerations": [
{
"name": "text",
"operator": "Equal",
"key": "text",
"value": "text",
"effect": "NoSchedule",
"seconds": 1,
"exclude": false
}
],
"terminateAfterPreemption": false,
"autoDeletionTimeAfterCompletionSeconds": 15,
"terminationGracePeriodSeconds": 20,
"backoffLimit": 3,
"restartPolicy": "Always",
"ports": [
{
"container": 8080,
"serviceType": "LoadBalancer",
"external": 30080,
"toolType": "pytorch",
"toolName": "my-pytorch",
"name": "port-instance-a",
"exclude": false
}
],
"exposedUrls": [
{
"container": 8080,
"url": "https://my-url.com",
"authorizedUsers": [
"user-a",
"user-b"
],
"authorizedGroups": [
"group-a",
"group-b"
],
"toolType": "jupyter",
"toolName": "my-pytorch",
"name": "url-instance-a",
"exclude": false
}
],
"relatedUrls": [
{
"url": "https://my-url.com",
"type": "wandb",
"name": "url-instance-a",
"exclude": false
}
],
"priorityClass": "build",
"completions": 1,
"parallelism": 1,
"compute": {
"gpuDevicesRequest": 1,
"gpuRequestType": "portion",
"gpuPortionRequest": 0.5,
"gpuPortionLimit": 0.5,
"gpuMemoryRequest": "10M",
"gpuMemoryLimit": "10M",
"cpuCoreRequest": 0.5,
"cpuCoreLimit": 2,
"cpuMemoryRequest": "20M",
"cpuMemoryLimit": "30M",
"largeShmRequest": false,
"extendedResources": [
{
"resource": "hardware-vendor.example/foo",
"quantity": 2,
"exclude": false
}
]
},
"storage": {
"dataVolume": [
{
"id": "123e4567-e89b-12d3-a456-426614174000",
"mountPath": "/mnt/data",
"exclude": false
}
],
"pvc": [
{
"name": "storage-instance-a",
"path": "/container/my-claim",
"existingPvc": false,
"claimName": "my-claim",
"readOnly": false,
"ephemeral": false,
"claimInfo": {
"size": "1G",
"storageClass": "my-storage-class",
"accessModes": {
"readWriteOnce": true,
"readOnlyMany": false,
"readWriteMany": false
},
"volumeMode": "Filesystem"
},
"exclude": false
}
],
"hostPath": [
{
"name": "storage-instance-a",
"path": "/container/directory",
"readOnly": true,
"mountPath": "/local/directory",
"mountPropagation": "None",
"exclude": false
}
],
"nfs": [
{
"name": "storage-instance-a",
"path": "/container/nfs",
"readOnly": true,
"server": "my.nfs.com",
"mountPath": "/local/nfs",
"exclude": false
}
],
"git": [
{
"name": "storage-instance-a",
"repository": "https://github.com/my-git/my-repo",
"branch": "main",
"revision": "text",
"path": "/container/my-repository",
"passwordSecret": "my-password-secret",
"secretKeyOfUser": "User",
"secretKeyOfPassword": "Password",
"exclude": false
}
],
"configMapVolume": [
{
"name": "storage-instance-a",
"configMap": "text",
"mountPath": "text",
"subPath": "text",
"exclude": false
}
],
"secretVolume": [
{
"name": "storage-instance-a",
"mountPath": "text",
"secret": "text",
"exclude": false
}
],
"s3": [
{
"name": "storage-instance-a",
"bucket": "my-bucket",
"path": "/container/my-bucket",
"url": "https://s3.amazonaws.com",
"accessKeySecret": "my-access-key-secret",
"secretKeyOfAccessKeyId": "AccessKeyId",
"secretKeyOfSecretKey": "SecretKey",
"exclude": false
}
]
},
"security": {
"uidGidSource": "fromTheImage",
"capabilities": [
"CHOWN",
"KILL"
],
"seccompProfileType": "RuntimeDefault",
"runAsNonRoot": true,
"readOnlyRootFilesystem": false,
"runAsUid": 500,
"runAsGid": 30,
"supplementalGroups": "2,3,5,8",
"allowPrivilegeEscalation": false,
"hostIpc": false,
"hostNetwork": false
}
}
}{
"name": "my-workload-name",
"requestedName": "text",
"workloadId": "123e4567-e89b-12d3-a456-426614174000",
"projectId": 1,
"departmentId": 2,
"clusterId": "71f69d83-ba66-4822-adf5-55ce55efd210",
"createdBy": "test@lab.com",
"createdAt": "2022-01-01T03:49:52.531Z",
"deletedAt": "2022-01-01T03:49:52.531Z",
"desiredPhase": "Running",
"actualPhase": "Creating",
"spec": {
"command": "python",
"args": "-x my-script.py",
"image": "python:3.8",
"imagePullPolicy": "Always",
"workingDir": "/home/myfolder",
"createHomeDir": true,
"probes": {
"readiness": {
"initialDelaySeconds": 1,
"periodSeconds": 1,
"timeoutSeconds": 1,
"successThreshold": 1,
"failureThreshold": 1,
"handler": {
"httpGet": {
"path": "/",
"port": 1,
"host": "example.com",
"scheme": "HTTP"
}
}
}
},
"nodeType": "my-node-type",
"nodePools": [
"my-node-pool-a",
"my-node-pool-b"
],
"podAffinity": {
"type": "Required",
"key": "text"
},
"tty": true,
"stdin": true,
"environmentVariables": [
{
"name": "HOME",
"value": "/home/my-folder",
"secret": {
"name": "postgress_secret",
"key": "POSTGRES_PASSWORD"
},
"configMap": {
"name": "my-config-map",
"key": "MY_POSTGRES_SCHEMA"
},
"podFieldRef": {
"path": "metadata.name"
},
"exclude": false,
"description": "Home directory of the user."
}
],
"annotations": [
{
"name": "billing",
"value": "my-billing-unit",
"exclude": false
}
],
"labels": [
{
"name": "stage",
"value": "initial-research",
"exclude": false
}
],
"tolerations": [
{
"name": "text",
"operator": "Equal",
"key": "text",
"value": "text",
"effect": "NoSchedule",
"seconds": 1,
"exclude": false
}
],
"terminateAfterPreemption": false,
"autoDeletionTimeAfterCompletionSeconds": 15,
"terminationGracePeriodSeconds": 20,
"backoffLimit": 3,
"restartPolicy": "Always",
"ports": [
{
"container": 8080,
"serviceType": "LoadBalancer",
"external": 30080,
"toolType": "pytorch",
"toolName": "my-pytorch",
"name": "port-instance-a",
"exclude": false
}
],
"exposedUrls": [
{
"container": 8080,
"url": "https://my-url.com",
"authorizedUsers": [
"user-a",
"user-b"
],
"authorizedGroups": [
"group-a",
"group-b"
],
"toolType": "jupyter",
"toolName": "my-pytorch",
"name": "url-instance-a",
"exclude": false
}
],
"relatedUrls": [
{
"url": "https://my-url.com",
"type": "wandb",
"name": "url-instance-a",
"exclude": false
}
],
"priorityClass": "build",
"completions": 1,
"parallelism": 1,
"compute": {
"gpuDevicesRequest": 1,
"gpuRequestType": "portion",
"gpuPortionRequest": 0.5,
"gpuPortionLimit": 0.5,
"gpuMemoryRequest": "10M",
"gpuMemoryLimit": "10M",
"cpuCoreRequest": 0.5,
"cpuCoreLimit": 2,
"cpuMemoryRequest": "20M",
"cpuMemoryLimit": "30M",
"largeShmRequest": false,
"extendedResources": [
{
"resource": "hardware-vendor.example/foo",
"quantity": 2,
"exclude": false
}
]
},
"storage": {
"dataVolume": [
{
"id": "123e4567-e89b-12d3-a456-426614174000",
"mountPath": "/mnt/data",
"exclude": false
}
],
"pvc": [
{
"name": "storage-instance-a",
"path": "/container/my-claim",
"existingPvc": false,
"claimName": "my-claim",
"readOnly": false,
"ephemeral": false,
"claimInfo": {
"size": "1G",
"storageClass": "my-storage-class",
"accessModes": {
"readWriteOnce": true,
"readOnlyMany": false,
"readWriteMany": false
},
"volumeMode": "Filesystem"
},
"exclude": false
}
],
"hostPath": [
{
"name": "storage-instance-a",
"path": "/container/directory",
"readOnly": true,
"mountPath": "/local/directory",
"mountPropagation": "None",
"exclude": false
}
],
"nfs": [
{
"name": "storage-instance-a",
"path": "/container/nfs",
"readOnly": true,
"server": "my.nfs.com",
"mountPath": "/local/nfs",
"exclude": false
}
],
"git": [
{
"name": "storage-instance-a",
"repository": "https://github.com/my-git/my-repo",
"branch": "main",
"revision": "text",
"path": "/container/my-repository",
"passwordSecret": "my-password-secret",
"secretKeyOfUser": "User",
"secretKeyOfPassword": "Password",
"exclude": false
}
],
"configMapVolume": [
{
"name": "storage-instance-a",
"configMap": "text",
"mountPath": "text",
"subPath": "text",
"exclude": false
}
],
"secretVolume": [
{
"name": "storage-instance-a",
"mountPath": "text",
"secret": "text",
"exclude": false
}
],
"s3": [
{
"name": "storage-instance-a",
"bucket": "my-bucket",
"path": "/container/my-bucket",
"url": "https://s3.amazonaws.com",
"accessKeySecret": "my-access-key-secret",
"secretKeyOfAccessKeyId": "AccessKeyId",
"secretKeyOfSecretKey": "SecretKey",
"exclude": false
}
]
},
"security": {
"uidGidSource": "fromTheImage",
"capabilities": [
"CHOWN",
"KILL"
],
"seccompProfileType": "RuntimeDefault",
"runAsNonRoot": true,
"readOnlyRootFilesystem": false,
"runAsUid": 500,
"runAsGid": 30,
"supplementalGroups": "2,3,5,8",
"allowPrivilegeEscalation": false,
"hostIpc": false,
"hostNetwork": false
}
}
}Retrieve training details using a workload id.
Authorizations
AuthorizationstringRequired
Bearer authentication
Path parameters
workloadIdstring · uuidRequired
The Universally Unique Identifier (UUID) of the workload.
Responses
200
Executed successfully.
application/json
and
401
Unauthorized
application/json
403
Forbidden
application/json
404
The specified resource was not found
application/json
500
unexpected error
application/json
503
unexpected error
application/json
get/api/v1/workloads/trainings/{workloadId}
GET /api/v1/workloads/trainings/{workloadId} HTTP/1.1
Host: app.run.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
{
"name": "my-workload-name",
"requestedName": "text",
"workloadId": "123e4567-e89b-12d3-a456-426614174000",
"projectId": 1,
"departmentId": 2,
"clusterId": "71f69d83-ba66-4822-adf5-55ce55efd210",
"createdBy": "test@lab.com",
"createdAt": "2022-01-01T03:49:52.531Z",
"deletedAt": "2022-01-01T03:49:52.531Z",
"desiredPhase": "Running",
"actualPhase": "Creating",
"spec": {
"command": "python",
"args": "-x my-script.py",
"image": "python:3.8",
"imagePullPolicy": "Always",
"workingDir": "/home/myfolder",
"createHomeDir": true,
"probes": {
"readiness": {
"initialDelaySeconds": 1,
"periodSeconds": 1,
"timeoutSeconds": 1,
"successThreshold": 1,
"failureThreshold": 1,
"handler": {
"httpGet": {
"path": "/",
"port": 1,
"host": "example.com",
"scheme": "HTTP"
}
}
}
},
"nodeType": "my-node-type",
"nodePools": [
"my-node-pool-a",
"my-node-pool-b"
],
"podAffinity": {
"type": "Required",
"key": "text"
},
"tty": true,
"stdin": true,
"environmentVariables": [
{
"name": "HOME",
"value": "/home/my-folder",
"secret": {
"name": "postgress_secret",
"key": "POSTGRES_PASSWORD"
},
"configMap": {
"name": "my-config-map",
"key": "MY_POSTGRES_SCHEMA"
},
"podFieldRef": {
"path": "metadata.name"
},
"exclude": false,
"description": "Home directory of the user."
}
],
"annotations": [
{
"name": "billing",
"value": "my-billing-unit",
"exclude": false
}
],
"labels": [
{
"name": "stage",
"value": "initial-research",
"exclude": false
}
],
"tolerations": [
{
"name": "text",
"operator": "Equal",
"key": "text",
"value": "text",
"effect": "NoSchedule",
"seconds": 1,
"exclude": false
}
],
"terminateAfterPreemption": false,
"autoDeletionTimeAfterCompletionSeconds": 15,
"terminationGracePeriodSeconds": 20,
"backoffLimit": 3,
"restartPolicy": "Always",
"ports": [
{
"container": 8080,
"serviceType": "LoadBalancer",
"external": 30080,
"toolType": "pytorch",
"toolName": "my-pytorch",
"name": "port-instance-a",
"exclude": false
}
],
"exposedUrls": [
{
"container": 8080,
"url": "https://my-url.com",
"authorizedUsers": [
"user-a",
"user-b"
],
"authorizedGroups": [
"group-a",
"group-b"
],
"toolType": "jupyter",
"toolName": "my-pytorch",
"name": "url-instance-a",
"exclude": false
}
],
"relatedUrls": [
{
"url": "https://my-url.com",
"type": "wandb",
"name": "url-instance-a",
"exclude": false
}
],
"priorityClass": "build",
"completions": 1,
"parallelism": 1,
"compute": {
"gpuDevicesRequest": 1,
"gpuRequestType": "portion",
"gpuPortionRequest": 0.5,
"gpuPortionLimit": 0.5,
"gpuMemoryRequest": "10M",
"gpuMemoryLimit": "10M",
"cpuCoreRequest": 0.5,
"cpuCoreLimit": 2,
"cpuMemoryRequest": "20M",
"cpuMemoryLimit": "30M",
"largeShmRequest": false,
"extendedResources": [
{
"resource": "hardware-vendor.example/foo",
"quantity": 2,
"exclude": false
}
]
},
"storage": {
"dataVolume": [
{
"id": "123e4567-e89b-12d3-a456-426614174000",
"mountPath": "/mnt/data",
"exclude": false
}
],
"pvc": [
{
"name": "storage-instance-a",
"path": "/container/my-claim",
"existingPvc": false,
"claimName": "my-claim",
"readOnly": false,
"ephemeral": false,
"claimInfo": {
"size": "1G",
"storageClass": "my-storage-class",
"accessModes": {
"readWriteOnce": true,
"readOnlyMany": false,
"readWriteMany": false
},
"volumeMode": "Filesystem"
},
"exclude": false
}
],
"hostPath": [
{
"name": "storage-instance-a",
"path": "/container/directory",
"readOnly": true,
"mountPath": "/local/directory",
"mountPropagation": "None",
"exclude": false
}
],
"nfs": [
{
"name": "storage-instance-a",
"path": "/container/nfs",
"readOnly": true,
"server": "my.nfs.com",
"mountPath": "/local/nfs",
"exclude": false
}
],
"git": [
{
"name": "storage-instance-a",
"repository": "https://github.com/my-git/my-repo",
"branch": "main",
"revision": "text",
"path": "/container/my-repository",
"passwordSecret": "my-password-secret",
"secretKeyOfUser": "User",
"secretKeyOfPassword": "Password",
"exclude": false
}
],
"configMapVolume": [
{
"name": "storage-instance-a",
"configMap": "text",
"mountPath": "text",
"subPath": "text",
"exclude": false
}
],
"secretVolume": [
{
"name": "storage-instance-a",
"mountPath": "text",
"secret": "text",
"exclude": false
}
],
"s3": [
{
"name": "storage-instance-a",
"bucket": "my-bucket",
"path": "/container/my-bucket",
"url": "https://s3.amazonaws.com",
"accessKeySecret": "my-access-key-secret",
"secretKeyOfAccessKeyId": "AccessKeyId",
"secretKeyOfSecretKey": "SecretKey",
"exclude": false
}
]
},
"security": {
"uidGidSource": "fromTheImage",
"capabilities": [
"CHOWN",
"KILL"
],
"seccompProfileType": "RuntimeDefault",
"runAsNonRoot": true,
"readOnlyRootFilesystem": false,
"runAsUid": 500,
"runAsGid": 30,
"supplementalGroups": "2,3,5,8",
"allowPrivilegeEscalation": false,
"hostIpc": false,
"hostNetwork": false
}
}
}Delete a training using a workload id.
Authorizations
AuthorizationstringRequired
Bearer authentication
Path parameters
workloadIdstring · uuidRequired
The Universally Unique Identifier (UUID) of the workload.
Responses
202
Accepted.
application/json
codeinteger · min: 100 · max: 599Required
messagestringRequired
401
Unauthorized
application/json
403
Forbidden
application/json
404
The specified resource was not found
application/json
500
unexpected error
application/json
503
unexpected error
application/json
delete/api/v1/workloads/trainings/{workloadId}
DELETE /api/v1/workloads/trainings/{workloadId} HTTP/1.1
Host: app.run.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
{
"code": 202,
"message": "Request has been accepted."
}Suspend a training from running using a workload id.
Authorizations
AuthorizationstringRequired
Bearer authentication
Path parameters
workloadIdstring · uuidRequired
The Universally Unique Identifier (UUID) of the workload.
Responses
202
Accepted.
application/json
codeinteger · min: 100 · max: 599Required
messagestringRequired
401
Unauthorized
application/json
403
Forbidden
application/json
404
The specified resource was not found
application/json
500
unexpected error
application/json
503
unexpected error
application/json
post/api/v1/workloads/trainings/{workloadId}/suspend
POST /api/v1/workloads/trainings/{workloadId}/suspend HTTP/1.1
Host: app.run.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
{
"code": 202,
"message": "Request has been accepted."
}Resume a training that was suspended using a workload id.
Authorizations
AuthorizationstringRequired
Bearer authentication
Path parameters
workloadIdstring · uuidRequired
The Universally Unique Identifier (UUID) of the workload.
Responses
202
Accepted.
application/json
codeinteger · min: 100 · max: 599Required
messagestringRequired
401
Unauthorized
application/json
403
Forbidden
application/json
404
The specified resource was not found
application/json
500
unexpected error
application/json
503
unexpected error
application/json
post/api/v1/workloads/trainings/{workloadId}/resume
POST /api/v1/workloads/trainings/{workloadId}/resume HTTP/1.1
Host: app.run.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
{
"code": 202,
"message": "Request has been accepted."
}Last updated