1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
|
<html><body>
<style>
body, h1, h2, h3, div, span, p, pre, a {
margin: 0;
padding: 0;
border: 0;
font-weight: inherit;
font-style: inherit;
font-size: 100%;
font-family: inherit;
vertical-align: baseline;
}
body {
font-size: 13px;
padding: 1em;
}
h1 {
font-size: 26px;
margin-bottom: 1em;
}
h2 {
font-size: 24px;
margin-bottom: 1em;
}
h3 {
font-size: 20px;
margin-bottom: 1em;
margin-top: 1em;
}
pre, code {
line-height: 1.5;
font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
}
pre {
margin-top: 0.5em;
}
h1, h2, h3, p {
font-family: Arial, sans serif;
}
h1, h2, h3 {
border-bottom: solid #CCC 1px;
}
.toc_element {
margin-top: 0.5em;
}
.firstline {
margin-left: 2 em;
}
.method {
margin-top: 1em;
border: solid 1px #CCC;
padding: 1em;
background: #EEE;
}
.details {
font-weight: bold;
font-size: 14px;
}
</style>
<h1><a href="aiplatform_v1.html">Vertex AI API</a> . <a href="aiplatform_v1.projects.html">projects</a> . <a href="aiplatform_v1.projects.locations.html">locations</a> . <a href="aiplatform_v1.projects.locations.nasJobs.html">nasJobs</a></h1>
<h2>Instance Methods</h2>
<p class="toc_element">
<code><a href="aiplatform_v1.projects.locations.nasJobs.nasTrialDetails.html">nasTrialDetails()</a></code>
</p>
<p class="firstline">Returns the nasTrialDetails Resource.</p>
<p class="toc_element">
<code><a href="#cancel">cancel(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Cancels a NasJob. Starts asynchronous cancellation on the NasJob. The server makes a best effort to cancel the job, but success is not guaranteed. Clients can use JobService.GetNasJob or other methods to check whether the cancellation succeeded or whether the job completed despite cancellation. On successful cancellation, the NasJob is not deleted; instead it becomes a job with a NasJob.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`, and NasJob.state is set to `CANCELLED`.</p>
<p class="toc_element">
<code><a href="#close">close()</a></code></p>
<p class="firstline">Close httplib2 connections.</p>
<p class="toc_element">
<code><a href="#create">create(parent, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Creates a NasJob</p>
<p class="toc_element">
<code><a href="#delete">delete(name, x__xgafv=None)</a></code></p>
<p class="firstline">Deletes a NasJob.</p>
<p class="toc_element">
<code><a href="#get">get(name, x__xgafv=None)</a></code></p>
<p class="firstline">Gets a NasJob</p>
<p class="toc_element">
<code><a href="#list">list(parent, filter=None, pageSize=None, pageToken=None, readMask=None, x__xgafv=None)</a></code></p>
<p class="firstline">Lists NasJobs in a Location.</p>
<p class="toc_element">
<code><a href="#list_next">list_next()</a></code></p>
<p class="firstline">Retrieves the next page of results.</p>
<h3>Method Details</h3>
<div class="method">
<code class="details" id="cancel">cancel(name, body=None, x__xgafv=None)</code>
<pre>Cancels a NasJob. Starts asynchronous cancellation on the NasJob. The server makes a best effort to cancel the job, but success is not guaranteed. Clients can use JobService.GetNasJob or other methods to check whether the cancellation succeeded or whether the job completed despite cancellation. On successful cancellation, the NasJob is not deleted; instead it becomes a job with a NasJob.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`, and NasJob.state is set to `CANCELLED`.
Args:
name: string, Required. The name of the NasJob to cancel. Format: `projects/{project}/locations/{location}/nasJobs/{nas_job}` (required)
body: object, The request body.
The object takes the form of:
{ # Request message for JobService.CancelNasJob.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }
}</pre>
</div>
<div class="method">
<code class="details" id="close">close()</code>
<pre>Close httplib2 connections.</pre>
</div>
<div class="method">
<code class="details" id="create">create(parent, body=None, x__xgafv=None)</code>
<pre>Creates a NasJob
Args:
parent: string, Required. The resource name of the Location to create the NasJob in. Format: `projects/{project}/locations/{location}` (required)
body: object, The request body.
The object takes the form of:
{ # Represents a Neural Architecture Search (NAS) job.
"createTime": "A String", # Output only. Time when the NasJob was created.
"displayName": "A String", # Required. The display name of the NasJob. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"enableRestrictedImageTraining": True or False, # Optional. Enable a separation of Custom model training and restricted image training for tenant project.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key options for a NasJob. If this is set, then all resources created by the NasJob will be encrypted with the provided encryption key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"endTime": "A String", # Output only. Time when the NasJob entered any of the following states: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Output only. Only populated when job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"labels": { # The labels with user-defined metadata to organize NasJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"name": "A String", # Output only. Resource name of the NasJob.
"nasJobOutput": { # Represents a uCAIP NasJob output. # Output only. Output of the NasJob.
"multiTrialJobOutput": { # The output of a multi-trial Neural Architecture Search (NAS) jobs. # Output only. The output of this multi-trial Neural Architecture Search (NAS) job.
"searchTrials": [ # Output only. List of NasTrials that were started as part of search stage.
{ # Represents a uCAIP NasJob trial.
"endTime": "A String", # Output only. Time when the NasTrial's status changed to `SUCCEEDED` or `INFEASIBLE`.
"finalMeasurement": { # A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values. # Output only. The final measurement containing the objective value.
"elapsedDuration": "A String", # Output only. Time that the Trial has been running at the point of this Measurement.
"metrics": [ # Output only. A list of metrics got by evaluating the objective functions using suggested Parameter values.
{ # A message representing a metric in the measurement.
"metricId": "A String", # Output only. The ID of the Metric. The Metric should be defined in StudySpec's Metrics.
"value": 3.14, # Output only. The value for this metric.
},
],
"stepCount": "A String", # Output only. The number of steps the machine learning model has been trained for. Must be non-negative.
},
"id": "A String", # Output only. The identifier of the NasTrial assigned by the service.
"startTime": "A String", # Output only. Time when the NasTrial was started.
"state": "A String", # Output only. The detailed state of the NasTrial.
},
],
"trainTrials": [ # Output only. List of NasTrials that were started as part of train stage.
{ # Represents a uCAIP NasJob trial.
"endTime": "A String", # Output only. Time when the NasTrial's status changed to `SUCCEEDED` or `INFEASIBLE`.
"finalMeasurement": { # A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values. # Output only. The final measurement containing the objective value.
"elapsedDuration": "A String", # Output only. Time that the Trial has been running at the point of this Measurement.
"metrics": [ # Output only. A list of metrics got by evaluating the objective functions using suggested Parameter values.
{ # A message representing a metric in the measurement.
"metricId": "A String", # Output only. The ID of the Metric. The Metric should be defined in StudySpec's Metrics.
"value": 3.14, # Output only. The value for this metric.
},
],
"stepCount": "A String", # Output only. The number of steps the machine learning model has been trained for. Must be non-negative.
},
"id": "A String", # Output only. The identifier of the NasTrial assigned by the service.
"startTime": "A String", # Output only. Time when the NasTrial was started.
"state": "A String", # Output only. The detailed state of the NasTrial.
},
],
},
},
"nasJobSpec": { # Represents the spec of a NasJob. # Required. The specification of a NasJob.
"multiTrialAlgorithmSpec": { # The spec of multi-trial Neural Architecture Search (NAS). # The spec of multi-trial algorithms.
"metric": { # Represents a metric to optimize. # Metric specs for the NAS job. Validation for this field is done at `multi_trial_algorithm_spec` field.
"goal": "A String", # Required. The optimization goal of the metric.
"metricId": "A String", # Required. The ID of the metric. Must not contain whitespaces.
},
"multiTrialAlgorithm": "A String", # The multi-trial Neural Architecture Search (NAS) algorithm type. Defaults to `REINFORCEMENT_LEARNING`.
"searchTrialSpec": { # Represent spec for search trials. # Required. Spec for search trials.
"maxFailedTrialCount": 42, # The number of failed trials that need to be seen before failing the NasJob. If set to 0, Vertex AI decides how many trials must fail before the whole job fails.
"maxParallelTrialCount": 42, # Required. The maximum number of trials to run in parallel.
"maxTrialCount": 42, # Required. The maximum number of Neural Architecture Search (NAS) trials to run.
"searchTrialJobSpec": { # Represents the spec of a CustomJob. # Required. The spec of a search trial job. The same spec applies to all search trials.
"baseOutputDirectory": { # The Google Cloud Storage location where the output is to be written to. # The Cloud Storage location to store the output of this CustomJob or HyperparameterTuningJob. For HyperparameterTuningJob, the baseOutputDirectory of each child CustomJob backing a Trial is set to a subdirectory of name id under its parent HyperparameterTuningJob's baseOutputDirectory. The following Vertex AI environment variables will be passed to containers or python modules when this field is set: For CustomJob: * AIP_MODEL_DIR = `/model/` * AIP_CHECKPOINT_DIR = `/checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `/logs/` For CustomJob backing a Trial of HyperparameterTuningJob: * AIP_MODEL_DIR = `//model/` * AIP_CHECKPOINT_DIR = `//checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `//logs/`
"outputUriPrefix": "A String", # Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
},
"enableDashboardAccess": True or False, # Optional. Whether you want Vertex AI to enable access to the customized dashboard in training chief container. If set to `true`, you can access the dashboard at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"enableWebAccess": True or False, # Optional. Whether you want Vertex AI to enable [interactive shell access](https://cloud.google.com/vertex-ai/docs/training/monitor-debug-interactive-shell) to training containers. If set to `true`, you can access interactive shells at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"experiment": "A String", # Optional. The Experiment associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}`
"experimentRun": "A String", # Optional. The Experiment Run associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}-{experiment-run-name}`
"models": [ # Optional. The name of the Model resources for which to generate a mapping to artifact URIs. Applicable only to some of the Google-provided custom jobs. Format: `projects/{project}/locations/{location}/models/{model}` In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` If no version ID or alias is specified, the "default" version will be returned. The "default" version alias is created for the first version of the model, and can be moved to other versions later on. There will be exactly one default version.
"A String",
],
"network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network.
"persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected.
"protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations
"pscInterfaceConfig": { # Configuration for PSC-I. # Optional. Configuration for PSC-I for CustomJob.
"dnsPeeringConfigs": [ # Optional. DNS peering configurations. When specified, Vertex AI will attempt to configure DNS peering zones in the tenant project VPC to resolve the specified domains using the target network's Cloud DNS. The user must grant the dns.peer role to the Vertex AI Service Agent on the target project.
{ # DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's Cloud DNS.
"domain": "A String", # Required. The DNS name suffix of the zone being peered to, e.g., "my-internal-domain.corp.". Must end with a dot.
"targetNetwork": "A String", # Required. The VPC network name in the target_project where the DNS zone specified by 'domain' is visible.
"targetProject": "A String", # Required. The project ID hosting the Cloud DNS managed zone that contains the 'domain'. The Vertex AI Service Agent requires the dns.peer role on this project.
},
],
"networkAttachment": "A String", # Optional. The name of the Compute Engine [network attachment](https://cloud.google.com/vpc/docs/about-network-attachments) to attach to the resource within the region and user project. To specify this field, you must have already [created a network attachment] (https://cloud.google.com/vpc/docs/create-manage-network-attachments#create-network-attachments). This field is only used for resources using PSC-I.
},
"reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range'].
"A String",
],
"scheduling": { # All parameters related to queuing and scheduling of custom jobs. # Scheduling options for a CustomJob.
"disableRetries": True or False, # Optional. Indicates if the job should retry for internal errors after the job starts running. If true, overrides `Scheduling.restart_job_on_worker_restart` to false.
"maxWaitDuration": "A String", # Optional. This is the maximum duration that a job will wait for the requested resources to be provisioned if the scheduling strategy is set to [Strategy.DWS_FLEX_START]. If set to 0, the job will wait indefinitely. The default is 24 hours.
"restartJobOnWorkerRestart": True or False, # Optional. Restarts the entire CustomJob if a worker gets restarted. This feature can be used by distributed training jobs that are not resilient to workers leaving and joining a job.
"strategy": "A String", # Optional. This determines which type of scheduling strategy to use.
"timeout": "A String", # Optional. The maximum job running time. The default is 7 days.
},
"serviceAccount": "A String", # Specifies the service account for workload run-as account. Users submitting jobs must have act-as permission on this run-as account. If unspecified, the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) for the CustomJob's project is used.
"tensorboard": "A String", # Optional. The name of a Vertex AI Tensorboard resource to which this CustomJob will upload Tensorboard logs. Format: `projects/{project}/locations/{location}/tensorboards/{tensorboard}`
"workerPoolSpecs": [ # Required. The spec of the worker pools including machine type and Docker image. All worker pools except the first one are optional and can be skipped by providing an empty value.
{ # Represents the spec of a worker pool in a job.
"containerSpec": { # The spec of a Container. # The custom container task.
"args": [ # The arguments to be passed when starting the container.
"A String",
],
"command": [ # The command to be invoked when the container is started. It overrides the entrypoint instruction in Dockerfile when provided.
"A String",
],
"env": [ # Environment variables to be passed to the container. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"imageUri": "A String", # Required. The URI of a container image in the Container Registry that is to be run on each worker replica.
},
"diskSpec": { # Represents the spec of disk options. # Disk spec.
"bootDiskSizeGb": 42, # Size in GB of the boot disk (default is 100GB).
"bootDiskType": "A String", # Type of the boot disk. For non-A3U machines, the default value is "pd-ssd", for A3U machines, the default value is "hyperdisk-balanced". Valid values: "pd-ssd" (Persistent Disk Solid State Drive), "pd-standard" (Persistent Disk Hard Disk Drive) or "hyperdisk-balanced".
},
"machineSpec": { # Specification of a single machine. # Optional. Immutable. The specification of a single machine.
"acceleratorCount": 42, # The number of accelerators to attach to the machine.
"acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
"machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
"reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
"key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
"reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
"values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation or reservation block.
"A String",
],
},
"tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
},
"nfsMounts": [ # Optional. List of NFS mount spec.
{ # Represents a mount configuration for Network File System (NFS) to mount.
"mountPoint": "A String", # Required. Destination mount path. The NFS will be mounted for the user under /mnt/nfs/
"path": "A String", # Required. Source path exported from NFS server. Has to start with '/', and combined with the ip address, it indicates the source mount path in the form of `server:path`
"server": "A String", # Required. IP address of the NFS server.
},
],
"pythonPackageSpec": { # The spec of a Python packaged code. # The Python packaged task.
"args": [ # Command line arguments to be passed to the Python task.
"A String",
],
"env": [ # Environment variables to be passed to the python module. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"executorImageUri": "A String", # Required. The URI of a container image in Artifact Registry that will run the provided Python package. Vertex AI provides a wide range of executor images with pre-installed packages to meet users' various use cases. See the list of [pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). You must use an image from this list.
"packageUris": [ # Required. The Google Cloud Storage location of the Python package files which are the training program and its dependent packages. The maximum number of package URIs is 100.
"A String",
],
"pythonModule": "A String", # Required. The Python module name to run after installing the packages.
},
"replicaCount": "A String", # Optional. The number of worker replicas to use for this worker pool.
},
],
},
},
"trainTrialSpec": { # Represent spec for train trials. # Spec for train trials. Top N [TrainTrialSpec.max_parallel_trial_count] search trials will be trained for every M [TrainTrialSpec.frequency] trials searched.
"frequency": 42, # Required. Frequency of search trials to start train stage. Top N [TrainTrialSpec.max_parallel_trial_count] search trials will be trained for every M [TrainTrialSpec.frequency] trials searched.
"maxParallelTrialCount": 42, # Required. The maximum number of trials to run in parallel.
"trainTrialJobSpec": { # Represents the spec of a CustomJob. # Required. The spec of a train trial job. The same spec applies to all train trials.
"baseOutputDirectory": { # The Google Cloud Storage location where the output is to be written to. # The Cloud Storage location to store the output of this CustomJob or HyperparameterTuningJob. For HyperparameterTuningJob, the baseOutputDirectory of each child CustomJob backing a Trial is set to a subdirectory of name id under its parent HyperparameterTuningJob's baseOutputDirectory. The following Vertex AI environment variables will be passed to containers or python modules when this field is set: For CustomJob: * AIP_MODEL_DIR = `/model/` * AIP_CHECKPOINT_DIR = `/checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `/logs/` For CustomJob backing a Trial of HyperparameterTuningJob: * AIP_MODEL_DIR = `//model/` * AIP_CHECKPOINT_DIR = `//checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `//logs/`
"outputUriPrefix": "A String", # Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
},
"enableDashboardAccess": True or False, # Optional. Whether you want Vertex AI to enable access to the customized dashboard in training chief container. If set to `true`, you can access the dashboard at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"enableWebAccess": True or False, # Optional. Whether you want Vertex AI to enable [interactive shell access](https://cloud.google.com/vertex-ai/docs/training/monitor-debug-interactive-shell) to training containers. If set to `true`, you can access interactive shells at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"experiment": "A String", # Optional. The Experiment associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}`
"experimentRun": "A String", # Optional. The Experiment Run associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}-{experiment-run-name}`
"models": [ # Optional. The name of the Model resources for which to generate a mapping to artifact URIs. Applicable only to some of the Google-provided custom jobs. Format: `projects/{project}/locations/{location}/models/{model}` In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` If no version ID or alias is specified, the "default" version will be returned. The "default" version alias is created for the first version of the model, and can be moved to other versions later on. There will be exactly one default version.
"A String",
],
"network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network.
"persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected.
"protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations
"pscInterfaceConfig": { # Configuration for PSC-I. # Optional. Configuration for PSC-I for CustomJob.
"dnsPeeringConfigs": [ # Optional. DNS peering configurations. When specified, Vertex AI will attempt to configure DNS peering zones in the tenant project VPC to resolve the specified domains using the target network's Cloud DNS. The user must grant the dns.peer role to the Vertex AI Service Agent on the target project.
{ # DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's Cloud DNS.
"domain": "A String", # Required. The DNS name suffix of the zone being peered to, e.g., "my-internal-domain.corp.". Must end with a dot.
"targetNetwork": "A String", # Required. The VPC network name in the target_project where the DNS zone specified by 'domain' is visible.
"targetProject": "A String", # Required. The project ID hosting the Cloud DNS managed zone that contains the 'domain'. The Vertex AI Service Agent requires the dns.peer role on this project.
},
],
"networkAttachment": "A String", # Optional. The name of the Compute Engine [network attachment](https://cloud.google.com/vpc/docs/about-network-attachments) to attach to the resource within the region and user project. To specify this field, you must have already [created a network attachment] (https://cloud.google.com/vpc/docs/create-manage-network-attachments#create-network-attachments). This field is only used for resources using PSC-I.
},
"reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range'].
"A String",
],
"scheduling": { # All parameters related to queuing and scheduling of custom jobs. # Scheduling options for a CustomJob.
"disableRetries": True or False, # Optional. Indicates if the job should retry for internal errors after the job starts running. If true, overrides `Scheduling.restart_job_on_worker_restart` to false.
"maxWaitDuration": "A String", # Optional. This is the maximum duration that a job will wait for the requested resources to be provisioned if the scheduling strategy is set to [Strategy.DWS_FLEX_START]. If set to 0, the job will wait indefinitely. The default is 24 hours.
"restartJobOnWorkerRestart": True or False, # Optional. Restarts the entire CustomJob if a worker gets restarted. This feature can be used by distributed training jobs that are not resilient to workers leaving and joining a job.
"strategy": "A String", # Optional. This determines which type of scheduling strategy to use.
"timeout": "A String", # Optional. The maximum job running time. The default is 7 days.
},
"serviceAccount": "A String", # Specifies the service account for workload run-as account. Users submitting jobs must have act-as permission on this run-as account. If unspecified, the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) for the CustomJob's project is used.
"tensorboard": "A String", # Optional. The name of a Vertex AI Tensorboard resource to which this CustomJob will upload Tensorboard logs. Format: `projects/{project}/locations/{location}/tensorboards/{tensorboard}`
"workerPoolSpecs": [ # Required. The spec of the worker pools including machine type and Docker image. All worker pools except the first one are optional and can be skipped by providing an empty value.
{ # Represents the spec of a worker pool in a job.
"containerSpec": { # The spec of a Container. # The custom container task.
"args": [ # The arguments to be passed when starting the container.
"A String",
],
"command": [ # The command to be invoked when the container is started. It overrides the entrypoint instruction in Dockerfile when provided.
"A String",
],
"env": [ # Environment variables to be passed to the container. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"imageUri": "A String", # Required. The URI of a container image in the Container Registry that is to be run on each worker replica.
},
"diskSpec": { # Represents the spec of disk options. # Disk spec.
"bootDiskSizeGb": 42, # Size in GB of the boot disk (default is 100GB).
"bootDiskType": "A String", # Type of the boot disk. For non-A3U machines, the default value is "pd-ssd", for A3U machines, the default value is "hyperdisk-balanced". Valid values: "pd-ssd" (Persistent Disk Solid State Drive), "pd-standard" (Persistent Disk Hard Disk Drive) or "hyperdisk-balanced".
},
"machineSpec": { # Specification of a single machine. # Optional. Immutable. The specification of a single machine.
"acceleratorCount": 42, # The number of accelerators to attach to the machine.
"acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
"machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
"reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
"key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
"reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
"values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation or reservation block.
"A String",
],
},
"tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
},
"nfsMounts": [ # Optional. List of NFS mount spec.
{ # Represents a mount configuration for Network File System (NFS) to mount.
"mountPoint": "A String", # Required. Destination mount path. The NFS will be mounted for the user under /mnt/nfs/
"path": "A String", # Required. Source path exported from NFS server. Has to start with '/', and combined with the ip address, it indicates the source mount path in the form of `server:path`
"server": "A String", # Required. IP address of the NFS server.
},
],
"pythonPackageSpec": { # The spec of a Python packaged code. # The Python packaged task.
"args": [ # Command line arguments to be passed to the Python task.
"A String",
],
"env": [ # Environment variables to be passed to the python module. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"executorImageUri": "A String", # Required. The URI of a container image in Artifact Registry that will run the provided Python package. Vertex AI provides a wide range of executor images with pre-installed packages to meet users' various use cases. See the list of [pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). You must use an image from this list.
"packageUris": [ # Required. The Google Cloud Storage location of the Python package files which are the training program and its dependent packages. The maximum number of package URIs is 100.
"A String",
],
"pythonModule": "A String", # Required. The Python module name to run after installing the packages.
},
"replicaCount": "A String", # Optional. The number of worker replicas to use for this worker pool.
},
],
},
},
},
"resumeNasJobId": "A String", # The ID of the existing NasJob in the same Project and Location which will be used to resume search. search_space_spec and nas_algorithm_spec are obtained from previous NasJob hence should not provide them again for this NasJob.
"searchSpaceSpec": "A String", # It defines the search space for Neural Architecture Search (NAS).
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"startTime": "A String", # Output only. Time when the NasJob for the first time entered the `JOB_STATE_RUNNING` state.
"state": "A String", # Output only. The detailed state of the job.
"updateTime": "A String", # Output only. Time when the NasJob was most recently updated.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Represents a Neural Architecture Search (NAS) job.
"createTime": "A String", # Output only. Time when the NasJob was created.
"displayName": "A String", # Required. The display name of the NasJob. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"enableRestrictedImageTraining": True or False, # Optional. Enable a separation of Custom model training and restricted image training for tenant project.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key options for a NasJob. If this is set, then all resources created by the NasJob will be encrypted with the provided encryption key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"endTime": "A String", # Output only. Time when the NasJob entered any of the following states: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Output only. Only populated when job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"labels": { # The labels with user-defined metadata to organize NasJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"name": "A String", # Output only. Resource name of the NasJob.
"nasJobOutput": { # Represents a uCAIP NasJob output. # Output only. Output of the NasJob.
"multiTrialJobOutput": { # The output of a multi-trial Neural Architecture Search (NAS) jobs. # Output only. The output of this multi-trial Neural Architecture Search (NAS) job.
"searchTrials": [ # Output only. List of NasTrials that were started as part of search stage.
{ # Represents a uCAIP NasJob trial.
"endTime": "A String", # Output only. Time when the NasTrial's status changed to `SUCCEEDED` or `INFEASIBLE`.
"finalMeasurement": { # A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values. # Output only. The final measurement containing the objective value.
"elapsedDuration": "A String", # Output only. Time that the Trial has been running at the point of this Measurement.
"metrics": [ # Output only. A list of metrics got by evaluating the objective functions using suggested Parameter values.
{ # A message representing a metric in the measurement.
"metricId": "A String", # Output only. The ID of the Metric. The Metric should be defined in StudySpec's Metrics.
"value": 3.14, # Output only. The value for this metric.
},
],
"stepCount": "A String", # Output only. The number of steps the machine learning model has been trained for. Must be non-negative.
},
"id": "A String", # Output only. The identifier of the NasTrial assigned by the service.
"startTime": "A String", # Output only. Time when the NasTrial was started.
"state": "A String", # Output only. The detailed state of the NasTrial.
},
],
"trainTrials": [ # Output only. List of NasTrials that were started as part of train stage.
{ # Represents a uCAIP NasJob trial.
"endTime": "A String", # Output only. Time when the NasTrial's status changed to `SUCCEEDED` or `INFEASIBLE`.
"finalMeasurement": { # A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values. # Output only. The final measurement containing the objective value.
"elapsedDuration": "A String", # Output only. Time that the Trial has been running at the point of this Measurement.
"metrics": [ # Output only. A list of metrics got by evaluating the objective functions using suggested Parameter values.
{ # A message representing a metric in the measurement.
"metricId": "A String", # Output only. The ID of the Metric. The Metric should be defined in StudySpec's Metrics.
"value": 3.14, # Output only. The value for this metric.
},
],
"stepCount": "A String", # Output only. The number of steps the machine learning model has been trained for. Must be non-negative.
},
"id": "A String", # Output only. The identifier of the NasTrial assigned by the service.
"startTime": "A String", # Output only. Time when the NasTrial was started.
"state": "A String", # Output only. The detailed state of the NasTrial.
},
],
},
},
"nasJobSpec": { # Represents the spec of a NasJob. # Required. The specification of a NasJob.
"multiTrialAlgorithmSpec": { # The spec of multi-trial Neural Architecture Search (NAS). # The spec of multi-trial algorithms.
"metric": { # Represents a metric to optimize. # Metric specs for the NAS job. Validation for this field is done at `multi_trial_algorithm_spec` field.
"goal": "A String", # Required. The optimization goal of the metric.
"metricId": "A String", # Required. The ID of the metric. Must not contain whitespaces.
},
"multiTrialAlgorithm": "A String", # The multi-trial Neural Architecture Search (NAS) algorithm type. Defaults to `REINFORCEMENT_LEARNING`.
"searchTrialSpec": { # Represent spec for search trials. # Required. Spec for search trials.
"maxFailedTrialCount": 42, # The number of failed trials that need to be seen before failing the NasJob. If set to 0, Vertex AI decides how many trials must fail before the whole job fails.
"maxParallelTrialCount": 42, # Required. The maximum number of trials to run in parallel.
"maxTrialCount": 42, # Required. The maximum number of Neural Architecture Search (NAS) trials to run.
"searchTrialJobSpec": { # Represents the spec of a CustomJob. # Required. The spec of a search trial job. The same spec applies to all search trials.
"baseOutputDirectory": { # The Google Cloud Storage location where the output is to be written to. # The Cloud Storage location to store the output of this CustomJob or HyperparameterTuningJob. For HyperparameterTuningJob, the baseOutputDirectory of each child CustomJob backing a Trial is set to a subdirectory of name id under its parent HyperparameterTuningJob's baseOutputDirectory. The following Vertex AI environment variables will be passed to containers or python modules when this field is set: For CustomJob: * AIP_MODEL_DIR = `/model/` * AIP_CHECKPOINT_DIR = `/checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `/logs/` For CustomJob backing a Trial of HyperparameterTuningJob: * AIP_MODEL_DIR = `//model/` * AIP_CHECKPOINT_DIR = `//checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `//logs/`
"outputUriPrefix": "A String", # Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
},
"enableDashboardAccess": True or False, # Optional. Whether you want Vertex AI to enable access to the customized dashboard in training chief container. If set to `true`, you can access the dashboard at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"enableWebAccess": True or False, # Optional. Whether you want Vertex AI to enable [interactive shell access](https://cloud.google.com/vertex-ai/docs/training/monitor-debug-interactive-shell) to training containers. If set to `true`, you can access interactive shells at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"experiment": "A String", # Optional. The Experiment associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}`
"experimentRun": "A String", # Optional. The Experiment Run associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}-{experiment-run-name}`
"models": [ # Optional. The name of the Model resources for which to generate a mapping to artifact URIs. Applicable only to some of the Google-provided custom jobs. Format: `projects/{project}/locations/{location}/models/{model}` In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` If no version ID or alias is specified, the "default" version will be returned. The "default" version alias is created for the first version of the model, and can be moved to other versions later on. There will be exactly one default version.
"A String",
],
"network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network.
"persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected.
"protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations
"pscInterfaceConfig": { # Configuration for PSC-I. # Optional. Configuration for PSC-I for CustomJob.
"dnsPeeringConfigs": [ # Optional. DNS peering configurations. When specified, Vertex AI will attempt to configure DNS peering zones in the tenant project VPC to resolve the specified domains using the target network's Cloud DNS. The user must grant the dns.peer role to the Vertex AI Service Agent on the target project.
{ # DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's Cloud DNS.
"domain": "A String", # Required. The DNS name suffix of the zone being peered to, e.g., "my-internal-domain.corp.". Must end with a dot.
"targetNetwork": "A String", # Required. The VPC network name in the target_project where the DNS zone specified by 'domain' is visible.
"targetProject": "A String", # Required. The project ID hosting the Cloud DNS managed zone that contains the 'domain'. The Vertex AI Service Agent requires the dns.peer role on this project.
},
],
"networkAttachment": "A String", # Optional. The name of the Compute Engine [network attachment](https://cloud.google.com/vpc/docs/about-network-attachments) to attach to the resource within the region and user project. To specify this field, you must have already [created a network attachment] (https://cloud.google.com/vpc/docs/create-manage-network-attachments#create-network-attachments). This field is only used for resources using PSC-I.
},
"reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range'].
"A String",
],
"scheduling": { # All parameters related to queuing and scheduling of custom jobs. # Scheduling options for a CustomJob.
"disableRetries": True or False, # Optional. Indicates if the job should retry for internal errors after the job starts running. If true, overrides `Scheduling.restart_job_on_worker_restart` to false.
"maxWaitDuration": "A String", # Optional. This is the maximum duration that a job will wait for the requested resources to be provisioned if the scheduling strategy is set to [Strategy.DWS_FLEX_START]. If set to 0, the job will wait indefinitely. The default is 24 hours.
"restartJobOnWorkerRestart": True or False, # Optional. Restarts the entire CustomJob if a worker gets restarted. This feature can be used by distributed training jobs that are not resilient to workers leaving and joining a job.
"strategy": "A String", # Optional. This determines which type of scheduling strategy to use.
"timeout": "A String", # Optional. The maximum job running time. The default is 7 days.
},
"serviceAccount": "A String", # Specifies the service account for workload run-as account. Users submitting jobs must have act-as permission on this run-as account. If unspecified, the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) for the CustomJob's project is used.
"tensorboard": "A String", # Optional. The name of a Vertex AI Tensorboard resource to which this CustomJob will upload Tensorboard logs. Format: `projects/{project}/locations/{location}/tensorboards/{tensorboard}`
"workerPoolSpecs": [ # Required. The spec of the worker pools including machine type and Docker image. All worker pools except the first one are optional and can be skipped by providing an empty value.
{ # Represents the spec of a worker pool in a job.
"containerSpec": { # The spec of a Container. # The custom container task.
"args": [ # The arguments to be passed when starting the container.
"A String",
],
"command": [ # The command to be invoked when the container is started. It overrides the entrypoint instruction in Dockerfile when provided.
"A String",
],
"env": [ # Environment variables to be passed to the container. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"imageUri": "A String", # Required. The URI of a container image in the Container Registry that is to be run on each worker replica.
},
"diskSpec": { # Represents the spec of disk options. # Disk spec.
"bootDiskSizeGb": 42, # Size in GB of the boot disk (default is 100GB).
"bootDiskType": "A String", # Type of the boot disk. For non-A3U machines, the default value is "pd-ssd", for A3U machines, the default value is "hyperdisk-balanced". Valid values: "pd-ssd" (Persistent Disk Solid State Drive), "pd-standard" (Persistent Disk Hard Disk Drive) or "hyperdisk-balanced".
},
"machineSpec": { # Specification of a single machine. # Optional. Immutable. The specification of a single machine.
"acceleratorCount": 42, # The number of accelerators to attach to the machine.
"acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
"machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
"reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
"key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
"reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
"values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation or reservation block.
"A String",
],
},
"tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
},
"nfsMounts": [ # Optional. List of NFS mount spec.
{ # Represents a mount configuration for Network File System (NFS) to mount.
"mountPoint": "A String", # Required. Destination mount path. The NFS will be mounted for the user under /mnt/nfs/
"path": "A String", # Required. Source path exported from NFS server. Has to start with '/', and combined with the ip address, it indicates the source mount path in the form of `server:path`
"server": "A String", # Required. IP address of the NFS server.
},
],
"pythonPackageSpec": { # The spec of a Python packaged code. # The Python packaged task.
"args": [ # Command line arguments to be passed to the Python task.
"A String",
],
"env": [ # Environment variables to be passed to the python module. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"executorImageUri": "A String", # Required. The URI of a container image in Artifact Registry that will run the provided Python package. Vertex AI provides a wide range of executor images with pre-installed packages to meet users' various use cases. See the list of [pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). You must use an image from this list.
"packageUris": [ # Required. The Google Cloud Storage location of the Python package files which are the training program and its dependent packages. The maximum number of package URIs is 100.
"A String",
],
"pythonModule": "A String", # Required. The Python module name to run after installing the packages.
},
"replicaCount": "A String", # Optional. The number of worker replicas to use for this worker pool.
},
],
},
},
"trainTrialSpec": { # Represent spec for train trials. # Spec for train trials. Top N [TrainTrialSpec.max_parallel_trial_count] search trials will be trained for every M [TrainTrialSpec.frequency] trials searched.
"frequency": 42, # Required. Frequency of search trials to start train stage. Top N [TrainTrialSpec.max_parallel_trial_count] search trials will be trained for every M [TrainTrialSpec.frequency] trials searched.
"maxParallelTrialCount": 42, # Required. The maximum number of trials to run in parallel.
"trainTrialJobSpec": { # Represents the spec of a CustomJob. # Required. The spec of a train trial job. The same spec applies to all train trials.
"baseOutputDirectory": { # The Google Cloud Storage location where the output is to be written to. # The Cloud Storage location to store the output of this CustomJob or HyperparameterTuningJob. For HyperparameterTuningJob, the baseOutputDirectory of each child CustomJob backing a Trial is set to a subdirectory of name id under its parent HyperparameterTuningJob's baseOutputDirectory. The following Vertex AI environment variables will be passed to containers or python modules when this field is set: For CustomJob: * AIP_MODEL_DIR = `/model/` * AIP_CHECKPOINT_DIR = `/checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `/logs/` For CustomJob backing a Trial of HyperparameterTuningJob: * AIP_MODEL_DIR = `//model/` * AIP_CHECKPOINT_DIR = `//checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `//logs/`
"outputUriPrefix": "A String", # Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
},
"enableDashboardAccess": True or False, # Optional. Whether you want Vertex AI to enable access to the customized dashboard in training chief container. If set to `true`, you can access the dashboard at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"enableWebAccess": True or False, # Optional. Whether you want Vertex AI to enable [interactive shell access](https://cloud.google.com/vertex-ai/docs/training/monitor-debug-interactive-shell) to training containers. If set to `true`, you can access interactive shells at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"experiment": "A String", # Optional. The Experiment associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}`
"experimentRun": "A String", # Optional. The Experiment Run associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}-{experiment-run-name}`
"models": [ # Optional. The name of the Model resources for which to generate a mapping to artifact URIs. Applicable only to some of the Google-provided custom jobs. Format: `projects/{project}/locations/{location}/models/{model}` In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` If no version ID or alias is specified, the "default" version will be returned. The "default" version alias is created for the first version of the model, and can be moved to other versions later on. There will be exactly one default version.
"A String",
],
"network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network.
"persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected.
"protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations
"pscInterfaceConfig": { # Configuration for PSC-I. # Optional. Configuration for PSC-I for CustomJob.
"dnsPeeringConfigs": [ # Optional. DNS peering configurations. When specified, Vertex AI will attempt to configure DNS peering zones in the tenant project VPC to resolve the specified domains using the target network's Cloud DNS. The user must grant the dns.peer role to the Vertex AI Service Agent on the target project.
{ # DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's Cloud DNS.
"domain": "A String", # Required. The DNS name suffix of the zone being peered to, e.g., "my-internal-domain.corp.". Must end with a dot.
"targetNetwork": "A String", # Required. The VPC network name in the target_project where the DNS zone specified by 'domain' is visible.
"targetProject": "A String", # Required. The project ID hosting the Cloud DNS managed zone that contains the 'domain'. The Vertex AI Service Agent requires the dns.peer role on this project.
},
],
"networkAttachment": "A String", # Optional. The name of the Compute Engine [network attachment](https://cloud.google.com/vpc/docs/about-network-attachments) to attach to the resource within the region and user project. To specify this field, you must have already [created a network attachment] (https://cloud.google.com/vpc/docs/create-manage-network-attachments#create-network-attachments). This field is only used for resources using PSC-I.
},
"reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range'].
"A String",
],
"scheduling": { # All parameters related to queuing and scheduling of custom jobs. # Scheduling options for a CustomJob.
"disableRetries": True or False, # Optional. Indicates if the job should retry for internal errors after the job starts running. If true, overrides `Scheduling.restart_job_on_worker_restart` to false.
"maxWaitDuration": "A String", # Optional. This is the maximum duration that a job will wait for the requested resources to be provisioned if the scheduling strategy is set to [Strategy.DWS_FLEX_START]. If set to 0, the job will wait indefinitely. The default is 24 hours.
"restartJobOnWorkerRestart": True or False, # Optional. Restarts the entire CustomJob if a worker gets restarted. This feature can be used by distributed training jobs that are not resilient to workers leaving and joining a job.
"strategy": "A String", # Optional. This determines which type of scheduling strategy to use.
"timeout": "A String", # Optional. The maximum job running time. The default is 7 days.
},
"serviceAccount": "A String", # Specifies the service account for workload run-as account. Users submitting jobs must have act-as permission on this run-as account. If unspecified, the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) for the CustomJob's project is used.
"tensorboard": "A String", # Optional. The name of a Vertex AI Tensorboard resource to which this CustomJob will upload Tensorboard logs. Format: `projects/{project}/locations/{location}/tensorboards/{tensorboard}`
"workerPoolSpecs": [ # Required. The spec of the worker pools including machine type and Docker image. All worker pools except the first one are optional and can be skipped by providing an empty value.
{ # Represents the spec of a worker pool in a job.
"containerSpec": { # The spec of a Container. # The custom container task.
"args": [ # The arguments to be passed when starting the container.
"A String",
],
"command": [ # The command to be invoked when the container is started. It overrides the entrypoint instruction in Dockerfile when provided.
"A String",
],
"env": [ # Environment variables to be passed to the container. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"imageUri": "A String", # Required. The URI of a container image in the Container Registry that is to be run on each worker replica.
},
"diskSpec": { # Represents the spec of disk options. # Disk spec.
"bootDiskSizeGb": 42, # Size in GB of the boot disk (default is 100GB).
"bootDiskType": "A String", # Type of the boot disk. For non-A3U machines, the default value is "pd-ssd", for A3U machines, the default value is "hyperdisk-balanced". Valid values: "pd-ssd" (Persistent Disk Solid State Drive), "pd-standard" (Persistent Disk Hard Disk Drive) or "hyperdisk-balanced".
},
"machineSpec": { # Specification of a single machine. # Optional. Immutable. The specification of a single machine.
"acceleratorCount": 42, # The number of accelerators to attach to the machine.
"acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
"machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
"reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
"key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
"reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
"values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation or reservation block.
"A String",
],
},
"tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
},
"nfsMounts": [ # Optional. List of NFS mount spec.
{ # Represents a mount configuration for Network File System (NFS) to mount.
"mountPoint": "A String", # Required. Destination mount path. The NFS will be mounted for the user under /mnt/nfs/
"path": "A String", # Required. Source path exported from NFS server. Has to start with '/', and combined with the ip address, it indicates the source mount path in the form of `server:path`
"server": "A String", # Required. IP address of the NFS server.
},
],
"pythonPackageSpec": { # The spec of a Python packaged code. # The Python packaged task.
"args": [ # Command line arguments to be passed to the Python task.
"A String",
],
"env": [ # Environment variables to be passed to the python module. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"executorImageUri": "A String", # Required. The URI of a container image in Artifact Registry that will run the provided Python package. Vertex AI provides a wide range of executor images with pre-installed packages to meet users' various use cases. See the list of [pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). You must use an image from this list.
"packageUris": [ # Required. The Google Cloud Storage location of the Python package files which are the training program and its dependent packages. The maximum number of package URIs is 100.
"A String",
],
"pythonModule": "A String", # Required. The Python module name to run after installing the packages.
},
"replicaCount": "A String", # Optional. The number of worker replicas to use for this worker pool.
},
],
},
},
},
"resumeNasJobId": "A String", # The ID of the existing NasJob in the same Project and Location which will be used to resume search. search_space_spec and nas_algorithm_spec are obtained from previous NasJob hence should not provide them again for this NasJob.
"searchSpaceSpec": "A String", # It defines the search space for Neural Architecture Search (NAS).
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"startTime": "A String", # Output only. Time when the NasJob for the first time entered the `JOB_STATE_RUNNING` state.
"state": "A String", # Output only. The detailed state of the job.
"updateTime": "A String", # Output only. Time when the NasJob was most recently updated.
}</pre>
</div>
<div class="method">
<code class="details" id="delete">delete(name, x__xgafv=None)</code>
<pre>Deletes a NasJob.
Args:
name: string, Required. The name of the NasJob resource to be deleted. Format: `projects/{project}/locations/{location}/nasJobs/{nas_job}` (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}</pre>
</div>
<div class="method">
<code class="details" id="get">get(name, x__xgafv=None)</code>
<pre>Gets a NasJob
Args:
name: string, Required. The name of the NasJob resource. Format: `projects/{project}/locations/{location}/nasJobs/{nas_job}` (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Represents a Neural Architecture Search (NAS) job.
"createTime": "A String", # Output only. Time when the NasJob was created.
"displayName": "A String", # Required. The display name of the NasJob. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"enableRestrictedImageTraining": True or False, # Optional. Enable a separation of Custom model training and restricted image training for tenant project.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key options for a NasJob. If this is set, then all resources created by the NasJob will be encrypted with the provided encryption key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"endTime": "A String", # Output only. Time when the NasJob entered any of the following states: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Output only. Only populated when job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"labels": { # The labels with user-defined metadata to organize NasJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"name": "A String", # Output only. Resource name of the NasJob.
"nasJobOutput": { # Represents a uCAIP NasJob output. # Output only. Output of the NasJob.
"multiTrialJobOutput": { # The output of a multi-trial Neural Architecture Search (NAS) jobs. # Output only. The output of this multi-trial Neural Architecture Search (NAS) job.
"searchTrials": [ # Output only. List of NasTrials that were started as part of search stage.
{ # Represents a uCAIP NasJob trial.
"endTime": "A String", # Output only. Time when the NasTrial's status changed to `SUCCEEDED` or `INFEASIBLE`.
"finalMeasurement": { # A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values. # Output only. The final measurement containing the objective value.
"elapsedDuration": "A String", # Output only. Time that the Trial has been running at the point of this Measurement.
"metrics": [ # Output only. A list of metrics got by evaluating the objective functions using suggested Parameter values.
{ # A message representing a metric in the measurement.
"metricId": "A String", # Output only. The ID of the Metric. The Metric should be defined in StudySpec's Metrics.
"value": 3.14, # Output only. The value for this metric.
},
],
"stepCount": "A String", # Output only. The number of steps the machine learning model has been trained for. Must be non-negative.
},
"id": "A String", # Output only. The identifier of the NasTrial assigned by the service.
"startTime": "A String", # Output only. Time when the NasTrial was started.
"state": "A String", # Output only. The detailed state of the NasTrial.
},
],
"trainTrials": [ # Output only. List of NasTrials that were started as part of train stage.
{ # Represents a uCAIP NasJob trial.
"endTime": "A String", # Output only. Time when the NasTrial's status changed to `SUCCEEDED` or `INFEASIBLE`.
"finalMeasurement": { # A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values. # Output only. The final measurement containing the objective value.
"elapsedDuration": "A String", # Output only. Time that the Trial has been running at the point of this Measurement.
"metrics": [ # Output only. A list of metrics got by evaluating the objective functions using suggested Parameter values.
{ # A message representing a metric in the measurement.
"metricId": "A String", # Output only. The ID of the Metric. The Metric should be defined in StudySpec's Metrics.
"value": 3.14, # Output only. The value for this metric.
},
],
"stepCount": "A String", # Output only. The number of steps the machine learning model has been trained for. Must be non-negative.
},
"id": "A String", # Output only. The identifier of the NasTrial assigned by the service.
"startTime": "A String", # Output only. Time when the NasTrial was started.
"state": "A String", # Output only. The detailed state of the NasTrial.
},
],
},
},
"nasJobSpec": { # Represents the spec of a NasJob. # Required. The specification of a NasJob.
"multiTrialAlgorithmSpec": { # The spec of multi-trial Neural Architecture Search (NAS). # The spec of multi-trial algorithms.
"metric": { # Represents a metric to optimize. # Metric specs for the NAS job. Validation for this field is done at `multi_trial_algorithm_spec` field.
"goal": "A String", # Required. The optimization goal of the metric.
"metricId": "A String", # Required. The ID of the metric. Must not contain whitespaces.
},
"multiTrialAlgorithm": "A String", # The multi-trial Neural Architecture Search (NAS) algorithm type. Defaults to `REINFORCEMENT_LEARNING`.
"searchTrialSpec": { # Represent spec for search trials. # Required. Spec for search trials.
"maxFailedTrialCount": 42, # The number of failed trials that need to be seen before failing the NasJob. If set to 0, Vertex AI decides how many trials must fail before the whole job fails.
"maxParallelTrialCount": 42, # Required. The maximum number of trials to run in parallel.
"maxTrialCount": 42, # Required. The maximum number of Neural Architecture Search (NAS) trials to run.
"searchTrialJobSpec": { # Represents the spec of a CustomJob. # Required. The spec of a search trial job. The same spec applies to all search trials.
"baseOutputDirectory": { # The Google Cloud Storage location where the output is to be written to. # The Cloud Storage location to store the output of this CustomJob or HyperparameterTuningJob. For HyperparameterTuningJob, the baseOutputDirectory of each child CustomJob backing a Trial is set to a subdirectory of name id under its parent HyperparameterTuningJob's baseOutputDirectory. The following Vertex AI environment variables will be passed to containers or python modules when this field is set: For CustomJob: * AIP_MODEL_DIR = `/model/` * AIP_CHECKPOINT_DIR = `/checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `/logs/` For CustomJob backing a Trial of HyperparameterTuningJob: * AIP_MODEL_DIR = `//model/` * AIP_CHECKPOINT_DIR = `//checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `//logs/`
"outputUriPrefix": "A String", # Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
},
"enableDashboardAccess": True or False, # Optional. Whether you want Vertex AI to enable access to the customized dashboard in training chief container. If set to `true`, you can access the dashboard at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"enableWebAccess": True or False, # Optional. Whether you want Vertex AI to enable [interactive shell access](https://cloud.google.com/vertex-ai/docs/training/monitor-debug-interactive-shell) to training containers. If set to `true`, you can access interactive shells at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"experiment": "A String", # Optional. The Experiment associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}`
"experimentRun": "A String", # Optional. The Experiment Run associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}-{experiment-run-name}`
"models": [ # Optional. The name of the Model resources for which to generate a mapping to artifact URIs. Applicable only to some of the Google-provided custom jobs. Format: `projects/{project}/locations/{location}/models/{model}` In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` If no version ID or alias is specified, the "default" version will be returned. The "default" version alias is created for the first version of the model, and can be moved to other versions later on. There will be exactly one default version.
"A String",
],
"network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network.
"persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected.
"protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations
"pscInterfaceConfig": { # Configuration for PSC-I. # Optional. Configuration for PSC-I for CustomJob.
"dnsPeeringConfigs": [ # Optional. DNS peering configurations. When specified, Vertex AI will attempt to configure DNS peering zones in the tenant project VPC to resolve the specified domains using the target network's Cloud DNS. The user must grant the dns.peer role to the Vertex AI Service Agent on the target project.
{ # DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's Cloud DNS.
"domain": "A String", # Required. The DNS name suffix of the zone being peered to, e.g., "my-internal-domain.corp.". Must end with a dot.
"targetNetwork": "A String", # Required. The VPC network name in the target_project where the DNS zone specified by 'domain' is visible.
"targetProject": "A String", # Required. The project ID hosting the Cloud DNS managed zone that contains the 'domain'. The Vertex AI Service Agent requires the dns.peer role on this project.
},
],
"networkAttachment": "A String", # Optional. The name of the Compute Engine [network attachment](https://cloud.google.com/vpc/docs/about-network-attachments) to attach to the resource within the region and user project. To specify this field, you must have already [created a network attachment] (https://cloud.google.com/vpc/docs/create-manage-network-attachments#create-network-attachments). This field is only used for resources using PSC-I.
},
"reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range'].
"A String",
],
"scheduling": { # All parameters related to queuing and scheduling of custom jobs. # Scheduling options for a CustomJob.
"disableRetries": True or False, # Optional. Indicates if the job should retry for internal errors after the job starts running. If true, overrides `Scheduling.restart_job_on_worker_restart` to false.
"maxWaitDuration": "A String", # Optional. This is the maximum duration that a job will wait for the requested resources to be provisioned if the scheduling strategy is set to [Strategy.DWS_FLEX_START]. If set to 0, the job will wait indefinitely. The default is 24 hours.
"restartJobOnWorkerRestart": True or False, # Optional. Restarts the entire CustomJob if a worker gets restarted. This feature can be used by distributed training jobs that are not resilient to workers leaving and joining a job.
"strategy": "A String", # Optional. This determines which type of scheduling strategy to use.
"timeout": "A String", # Optional. The maximum job running time. The default is 7 days.
},
"serviceAccount": "A String", # Specifies the service account for workload run-as account. Users submitting jobs must have act-as permission on this run-as account. If unspecified, the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) for the CustomJob's project is used.
"tensorboard": "A String", # Optional. The name of a Vertex AI Tensorboard resource to which this CustomJob will upload Tensorboard logs. Format: `projects/{project}/locations/{location}/tensorboards/{tensorboard}`
"workerPoolSpecs": [ # Required. The spec of the worker pools including machine type and Docker image. All worker pools except the first one are optional and can be skipped by providing an empty value.
{ # Represents the spec of a worker pool in a job.
"containerSpec": { # The spec of a Container. # The custom container task.
"args": [ # The arguments to be passed when starting the container.
"A String",
],
"command": [ # The command to be invoked when the container is started. It overrides the entrypoint instruction in Dockerfile when provided.
"A String",
],
"env": [ # Environment variables to be passed to the container. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"imageUri": "A String", # Required. The URI of a container image in the Container Registry that is to be run on each worker replica.
},
"diskSpec": { # Represents the spec of disk options. # Disk spec.
"bootDiskSizeGb": 42, # Size in GB of the boot disk (default is 100GB).
"bootDiskType": "A String", # Type of the boot disk. For non-A3U machines, the default value is "pd-ssd", for A3U machines, the default value is "hyperdisk-balanced". Valid values: "pd-ssd" (Persistent Disk Solid State Drive), "pd-standard" (Persistent Disk Hard Disk Drive) or "hyperdisk-balanced".
},
"machineSpec": { # Specification of a single machine. # Optional. Immutable. The specification of a single machine.
"acceleratorCount": 42, # The number of accelerators to attach to the machine.
"acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
"machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
"reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
"key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
"reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
"values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation or reservation block.
"A String",
],
},
"tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
},
"nfsMounts": [ # Optional. List of NFS mount spec.
{ # Represents a mount configuration for Network File System (NFS) to mount.
"mountPoint": "A String", # Required. Destination mount path. The NFS will be mounted for the user under /mnt/nfs/
"path": "A String", # Required. Source path exported from NFS server. Has to start with '/', and combined with the ip address, it indicates the source mount path in the form of `server:path`
"server": "A String", # Required. IP address of the NFS server.
},
],
"pythonPackageSpec": { # The spec of a Python packaged code. # The Python packaged task.
"args": [ # Command line arguments to be passed to the Python task.
"A String",
],
"env": [ # Environment variables to be passed to the python module. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"executorImageUri": "A String", # Required. The URI of a container image in Artifact Registry that will run the provided Python package. Vertex AI provides a wide range of executor images with pre-installed packages to meet users' various use cases. See the list of [pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). You must use an image from this list.
"packageUris": [ # Required. The Google Cloud Storage location of the Python package files which are the training program and its dependent packages. The maximum number of package URIs is 100.
"A String",
],
"pythonModule": "A String", # Required. The Python module name to run after installing the packages.
},
"replicaCount": "A String", # Optional. The number of worker replicas to use for this worker pool.
},
],
},
},
"trainTrialSpec": { # Represent spec for train trials. # Spec for train trials. Top N [TrainTrialSpec.max_parallel_trial_count] search trials will be trained for every M [TrainTrialSpec.frequency] trials searched.
"frequency": 42, # Required. Frequency of search trials to start train stage. Top N [TrainTrialSpec.max_parallel_trial_count] search trials will be trained for every M [TrainTrialSpec.frequency] trials searched.
"maxParallelTrialCount": 42, # Required. The maximum number of trials to run in parallel.
"trainTrialJobSpec": { # Represents the spec of a CustomJob. # Required. The spec of a train trial job. The same spec applies to all train trials.
"baseOutputDirectory": { # The Google Cloud Storage location where the output is to be written to. # The Cloud Storage location to store the output of this CustomJob or HyperparameterTuningJob. For HyperparameterTuningJob, the baseOutputDirectory of each child CustomJob backing a Trial is set to a subdirectory of name id under its parent HyperparameterTuningJob's baseOutputDirectory. The following Vertex AI environment variables will be passed to containers or python modules when this field is set: For CustomJob: * AIP_MODEL_DIR = `/model/` * AIP_CHECKPOINT_DIR = `/checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `/logs/` For CustomJob backing a Trial of HyperparameterTuningJob: * AIP_MODEL_DIR = `//model/` * AIP_CHECKPOINT_DIR = `//checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `//logs/`
"outputUriPrefix": "A String", # Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
},
"enableDashboardAccess": True or False, # Optional. Whether you want Vertex AI to enable access to the customized dashboard in training chief container. If set to `true`, you can access the dashboard at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"enableWebAccess": True or False, # Optional. Whether you want Vertex AI to enable [interactive shell access](https://cloud.google.com/vertex-ai/docs/training/monitor-debug-interactive-shell) to training containers. If set to `true`, you can access interactive shells at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"experiment": "A String", # Optional. The Experiment associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}`
"experimentRun": "A String", # Optional. The Experiment Run associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}-{experiment-run-name}`
"models": [ # Optional. The name of the Model resources for which to generate a mapping to artifact URIs. Applicable only to some of the Google-provided custom jobs. Format: `projects/{project}/locations/{location}/models/{model}` In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` If no version ID or alias is specified, the "default" version will be returned. The "default" version alias is created for the first version of the model, and can be moved to other versions later on. There will be exactly one default version.
"A String",
],
"network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network.
"persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected.
"protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations
"pscInterfaceConfig": { # Configuration for PSC-I. # Optional. Configuration for PSC-I for CustomJob.
"dnsPeeringConfigs": [ # Optional. DNS peering configurations. When specified, Vertex AI will attempt to configure DNS peering zones in the tenant project VPC to resolve the specified domains using the target network's Cloud DNS. The user must grant the dns.peer role to the Vertex AI Service Agent on the target project.
{ # DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's Cloud DNS.
"domain": "A String", # Required. The DNS name suffix of the zone being peered to, e.g., "my-internal-domain.corp.". Must end with a dot.
"targetNetwork": "A String", # Required. The VPC network name in the target_project where the DNS zone specified by 'domain' is visible.
"targetProject": "A String", # Required. The project ID hosting the Cloud DNS managed zone that contains the 'domain'. The Vertex AI Service Agent requires the dns.peer role on this project.
},
],
"networkAttachment": "A String", # Optional. The name of the Compute Engine [network attachment](https://cloud.google.com/vpc/docs/about-network-attachments) to attach to the resource within the region and user project. To specify this field, you must have already [created a network attachment] (https://cloud.google.com/vpc/docs/create-manage-network-attachments#create-network-attachments). This field is only used for resources using PSC-I.
},
"reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range'].
"A String",
],
"scheduling": { # All parameters related to queuing and scheduling of custom jobs. # Scheduling options for a CustomJob.
"disableRetries": True or False, # Optional. Indicates if the job should retry for internal errors after the job starts running. If true, overrides `Scheduling.restart_job_on_worker_restart` to false.
"maxWaitDuration": "A String", # Optional. This is the maximum duration that a job will wait for the requested resources to be provisioned if the scheduling strategy is set to [Strategy.DWS_FLEX_START]. If set to 0, the job will wait indefinitely. The default is 24 hours.
"restartJobOnWorkerRestart": True or False, # Optional. Restarts the entire CustomJob if a worker gets restarted. This feature can be used by distributed training jobs that are not resilient to workers leaving and joining a job.
"strategy": "A String", # Optional. This determines which type of scheduling strategy to use.
"timeout": "A String", # Optional. The maximum job running time. The default is 7 days.
},
"serviceAccount": "A String", # Specifies the service account for workload run-as account. Users submitting jobs must have act-as permission on this run-as account. If unspecified, the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) for the CustomJob's project is used.
"tensorboard": "A String", # Optional. The name of a Vertex AI Tensorboard resource to which this CustomJob will upload Tensorboard logs. Format: `projects/{project}/locations/{location}/tensorboards/{tensorboard}`
"workerPoolSpecs": [ # Required. The spec of the worker pools including machine type and Docker image. All worker pools except the first one are optional and can be skipped by providing an empty value.
{ # Represents the spec of a worker pool in a job.
"containerSpec": { # The spec of a Container. # The custom container task.
"args": [ # The arguments to be passed when starting the container.
"A String",
],
"command": [ # The command to be invoked when the container is started. It overrides the entrypoint instruction in Dockerfile when provided.
"A String",
],
"env": [ # Environment variables to be passed to the container. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"imageUri": "A String", # Required. The URI of a container image in the Container Registry that is to be run on each worker replica.
},
"diskSpec": { # Represents the spec of disk options. # Disk spec.
"bootDiskSizeGb": 42, # Size in GB of the boot disk (default is 100GB).
"bootDiskType": "A String", # Type of the boot disk. For non-A3U machines, the default value is "pd-ssd", for A3U machines, the default value is "hyperdisk-balanced". Valid values: "pd-ssd" (Persistent Disk Solid State Drive), "pd-standard" (Persistent Disk Hard Disk Drive) or "hyperdisk-balanced".
},
"machineSpec": { # Specification of a single machine. # Optional. Immutable. The specification of a single machine.
"acceleratorCount": 42, # The number of accelerators to attach to the machine.
"acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
"machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
"reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
"key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
"reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
"values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation or reservation block.
"A String",
],
},
"tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
},
"nfsMounts": [ # Optional. List of NFS mount spec.
{ # Represents a mount configuration for Network File System (NFS) to mount.
"mountPoint": "A String", # Required. Destination mount path. The NFS will be mounted for the user under /mnt/nfs/
"path": "A String", # Required. Source path exported from NFS server. Has to start with '/', and combined with the ip address, it indicates the source mount path in the form of `server:path`
"server": "A String", # Required. IP address of the NFS server.
},
],
"pythonPackageSpec": { # The spec of a Python packaged code. # The Python packaged task.
"args": [ # Command line arguments to be passed to the Python task.
"A String",
],
"env": [ # Environment variables to be passed to the python module. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"executorImageUri": "A String", # Required. The URI of a container image in Artifact Registry that will run the provided Python package. Vertex AI provides a wide range of executor images with pre-installed packages to meet users' various use cases. See the list of [pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). You must use an image from this list.
"packageUris": [ # Required. The Google Cloud Storage location of the Python package files which are the training program and its dependent packages. The maximum number of package URIs is 100.
"A String",
],
"pythonModule": "A String", # Required. The Python module name to run after installing the packages.
},
"replicaCount": "A String", # Optional. The number of worker replicas to use for this worker pool.
},
],
},
},
},
"resumeNasJobId": "A String", # The ID of the existing NasJob in the same Project and Location which will be used to resume search. search_space_spec and nas_algorithm_spec are obtained from previous NasJob hence should not provide them again for this NasJob.
"searchSpaceSpec": "A String", # It defines the search space for Neural Architecture Search (NAS).
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"startTime": "A String", # Output only. Time when the NasJob for the first time entered the `JOB_STATE_RUNNING` state.
"state": "A String", # Output only. The detailed state of the job.
"updateTime": "A String", # Output only. Time when the NasJob was most recently updated.
}</pre>
</div>
<div class="method">
<code class="details" id="list">list(parent, filter=None, pageSize=None, pageToken=None, readMask=None, x__xgafv=None)</code>
<pre>Lists NasJobs in a Location.
Args:
parent: string, Required. The resource name of the Location to list the NasJobs from. Format: `projects/{project}/locations/{location}` (required)
filter: string, The standard list filter. Supported fields: * `display_name` supports `=`, `!=` comparisons, and `:` wildcard. * `state` supports `=`, `!=` comparisons. * `create_time` supports `=`, `!=`,`<`, `<=`,`>`, `>=` comparisons. `create_time` must be in RFC 3339 format. * `labels` supports general map functions that is: `labels.key=value` - key:value equality `labels.key:* - key existence Some examples of using the filter are: * `state="JOB_STATE_SUCCEEDED" AND display_name:"my_job_*"` * `state!="JOB_STATE_FAILED" OR display_name="my_job"` * `NOT display_name="my_job"` * `create_time>"2021-05-18T00:00:00Z"` * `labels.keyA=valueA` * `labels.keyB:*`
pageSize: integer, The standard list page size.
pageToken: string, The standard list page token. Typically obtained via ListNasJobsResponse.next_page_token of the previous JobService.ListNasJobs call.
readMask: string, Mask specifying which fields to read.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for JobService.ListNasJobs
"nasJobs": [ # List of NasJobs in the requested page. NasJob.nas_job_output of the jobs will not be returned.
{ # Represents a Neural Architecture Search (NAS) job.
"createTime": "A String", # Output only. Time when the NasJob was created.
"displayName": "A String", # Required. The display name of the NasJob. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"enableRestrictedImageTraining": True or False, # Optional. Enable a separation of Custom model training and restricted image training for tenant project.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key options for a NasJob. If this is set, then all resources created by the NasJob will be encrypted with the provided encryption key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"endTime": "A String", # Output only. Time when the NasJob entered any of the following states: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Output only. Only populated when job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"labels": { # The labels with user-defined metadata to organize NasJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"name": "A String", # Output only. Resource name of the NasJob.
"nasJobOutput": { # Represents a uCAIP NasJob output. # Output only. Output of the NasJob.
"multiTrialJobOutput": { # The output of a multi-trial Neural Architecture Search (NAS) jobs. # Output only. The output of this multi-trial Neural Architecture Search (NAS) job.
"searchTrials": [ # Output only. List of NasTrials that were started as part of search stage.
{ # Represents a uCAIP NasJob trial.
"endTime": "A String", # Output only. Time when the NasTrial's status changed to `SUCCEEDED` or `INFEASIBLE`.
"finalMeasurement": { # A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values. # Output only. The final measurement containing the objective value.
"elapsedDuration": "A String", # Output only. Time that the Trial has been running at the point of this Measurement.
"metrics": [ # Output only. A list of metrics got by evaluating the objective functions using suggested Parameter values.
{ # A message representing a metric in the measurement.
"metricId": "A String", # Output only. The ID of the Metric. The Metric should be defined in StudySpec's Metrics.
"value": 3.14, # Output only. The value for this metric.
},
],
"stepCount": "A String", # Output only. The number of steps the machine learning model has been trained for. Must be non-negative.
},
"id": "A String", # Output only. The identifier of the NasTrial assigned by the service.
"startTime": "A String", # Output only. Time when the NasTrial was started.
"state": "A String", # Output only. The detailed state of the NasTrial.
},
],
"trainTrials": [ # Output only. List of NasTrials that were started as part of train stage.
{ # Represents a uCAIP NasJob trial.
"endTime": "A String", # Output only. Time when the NasTrial's status changed to `SUCCEEDED` or `INFEASIBLE`.
"finalMeasurement": { # A message representing a Measurement of a Trial. A Measurement contains the Metrics got by executing a Trial using suggested hyperparameter values. # Output only. The final measurement containing the objective value.
"elapsedDuration": "A String", # Output only. Time that the Trial has been running at the point of this Measurement.
"metrics": [ # Output only. A list of metrics got by evaluating the objective functions using suggested Parameter values.
{ # A message representing a metric in the measurement.
"metricId": "A String", # Output only. The ID of the Metric. The Metric should be defined in StudySpec's Metrics.
"value": 3.14, # Output only. The value for this metric.
},
],
"stepCount": "A String", # Output only. The number of steps the machine learning model has been trained for. Must be non-negative.
},
"id": "A String", # Output only. The identifier of the NasTrial assigned by the service.
"startTime": "A String", # Output only. Time when the NasTrial was started.
"state": "A String", # Output only. The detailed state of the NasTrial.
},
],
},
},
"nasJobSpec": { # Represents the spec of a NasJob. # Required. The specification of a NasJob.
"multiTrialAlgorithmSpec": { # The spec of multi-trial Neural Architecture Search (NAS). # The spec of multi-trial algorithms.
"metric": { # Represents a metric to optimize. # Metric specs for the NAS job. Validation for this field is done at `multi_trial_algorithm_spec` field.
"goal": "A String", # Required. The optimization goal of the metric.
"metricId": "A String", # Required. The ID of the metric. Must not contain whitespaces.
},
"multiTrialAlgorithm": "A String", # The multi-trial Neural Architecture Search (NAS) algorithm type. Defaults to `REINFORCEMENT_LEARNING`.
"searchTrialSpec": { # Represent spec for search trials. # Required. Spec for search trials.
"maxFailedTrialCount": 42, # The number of failed trials that need to be seen before failing the NasJob. If set to 0, Vertex AI decides how many trials must fail before the whole job fails.
"maxParallelTrialCount": 42, # Required. The maximum number of trials to run in parallel.
"maxTrialCount": 42, # Required. The maximum number of Neural Architecture Search (NAS) trials to run.
"searchTrialJobSpec": { # Represents the spec of a CustomJob. # Required. The spec of a search trial job. The same spec applies to all search trials.
"baseOutputDirectory": { # The Google Cloud Storage location where the output is to be written to. # The Cloud Storage location to store the output of this CustomJob or HyperparameterTuningJob. For HyperparameterTuningJob, the baseOutputDirectory of each child CustomJob backing a Trial is set to a subdirectory of name id under its parent HyperparameterTuningJob's baseOutputDirectory. The following Vertex AI environment variables will be passed to containers or python modules when this field is set: For CustomJob: * AIP_MODEL_DIR = `/model/` * AIP_CHECKPOINT_DIR = `/checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `/logs/` For CustomJob backing a Trial of HyperparameterTuningJob: * AIP_MODEL_DIR = `//model/` * AIP_CHECKPOINT_DIR = `//checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `//logs/`
"outputUriPrefix": "A String", # Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
},
"enableDashboardAccess": True or False, # Optional. Whether you want Vertex AI to enable access to the customized dashboard in training chief container. If set to `true`, you can access the dashboard at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"enableWebAccess": True or False, # Optional. Whether you want Vertex AI to enable [interactive shell access](https://cloud.google.com/vertex-ai/docs/training/monitor-debug-interactive-shell) to training containers. If set to `true`, you can access interactive shells at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"experiment": "A String", # Optional. The Experiment associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}`
"experimentRun": "A String", # Optional. The Experiment Run associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}-{experiment-run-name}`
"models": [ # Optional. The name of the Model resources for which to generate a mapping to artifact URIs. Applicable only to some of the Google-provided custom jobs. Format: `projects/{project}/locations/{location}/models/{model}` In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` If no version ID or alias is specified, the "default" version will be returned. The "default" version alias is created for the first version of the model, and can be moved to other versions later on. There will be exactly one default version.
"A String",
],
"network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network.
"persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected.
"protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations
"pscInterfaceConfig": { # Configuration for PSC-I. # Optional. Configuration for PSC-I for CustomJob.
"dnsPeeringConfigs": [ # Optional. DNS peering configurations. When specified, Vertex AI will attempt to configure DNS peering zones in the tenant project VPC to resolve the specified domains using the target network's Cloud DNS. The user must grant the dns.peer role to the Vertex AI Service Agent on the target project.
{ # DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's Cloud DNS.
"domain": "A String", # Required. The DNS name suffix of the zone being peered to, e.g., "my-internal-domain.corp.". Must end with a dot.
"targetNetwork": "A String", # Required. The VPC network name in the target_project where the DNS zone specified by 'domain' is visible.
"targetProject": "A String", # Required. The project ID hosting the Cloud DNS managed zone that contains the 'domain'. The Vertex AI Service Agent requires the dns.peer role on this project.
},
],
"networkAttachment": "A String", # Optional. The name of the Compute Engine [network attachment](https://cloud.google.com/vpc/docs/about-network-attachments) to attach to the resource within the region and user project. To specify this field, you must have already [created a network attachment] (https://cloud.google.com/vpc/docs/create-manage-network-attachments#create-network-attachments). This field is only used for resources using PSC-I.
},
"reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range'].
"A String",
],
"scheduling": { # All parameters related to queuing and scheduling of custom jobs. # Scheduling options for a CustomJob.
"disableRetries": True or False, # Optional. Indicates if the job should retry for internal errors after the job starts running. If true, overrides `Scheduling.restart_job_on_worker_restart` to false.
"maxWaitDuration": "A String", # Optional. This is the maximum duration that a job will wait for the requested resources to be provisioned if the scheduling strategy is set to [Strategy.DWS_FLEX_START]. If set to 0, the job will wait indefinitely. The default is 24 hours.
"restartJobOnWorkerRestart": True or False, # Optional. Restarts the entire CustomJob if a worker gets restarted. This feature can be used by distributed training jobs that are not resilient to workers leaving and joining a job.
"strategy": "A String", # Optional. This determines which type of scheduling strategy to use.
"timeout": "A String", # Optional. The maximum job running time. The default is 7 days.
},
"serviceAccount": "A String", # Specifies the service account for workload run-as account. Users submitting jobs must have act-as permission on this run-as account. If unspecified, the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) for the CustomJob's project is used.
"tensorboard": "A String", # Optional. The name of a Vertex AI Tensorboard resource to which this CustomJob will upload Tensorboard logs. Format: `projects/{project}/locations/{location}/tensorboards/{tensorboard}`
"workerPoolSpecs": [ # Required. The spec of the worker pools including machine type and Docker image. All worker pools except the first one are optional and can be skipped by providing an empty value.
{ # Represents the spec of a worker pool in a job.
"containerSpec": { # The spec of a Container. # The custom container task.
"args": [ # The arguments to be passed when starting the container.
"A String",
],
"command": [ # The command to be invoked when the container is started. It overrides the entrypoint instruction in Dockerfile when provided.
"A String",
],
"env": [ # Environment variables to be passed to the container. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"imageUri": "A String", # Required. The URI of a container image in the Container Registry that is to be run on each worker replica.
},
"diskSpec": { # Represents the spec of disk options. # Disk spec.
"bootDiskSizeGb": 42, # Size in GB of the boot disk (default is 100GB).
"bootDiskType": "A String", # Type of the boot disk. For non-A3U machines, the default value is "pd-ssd", for A3U machines, the default value is "hyperdisk-balanced". Valid values: "pd-ssd" (Persistent Disk Solid State Drive), "pd-standard" (Persistent Disk Hard Disk Drive) or "hyperdisk-balanced".
},
"machineSpec": { # Specification of a single machine. # Optional. Immutable. The specification of a single machine.
"acceleratorCount": 42, # The number of accelerators to attach to the machine.
"acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
"machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
"reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
"key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
"reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
"values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation or reservation block.
"A String",
],
},
"tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
},
"nfsMounts": [ # Optional. List of NFS mount spec.
{ # Represents a mount configuration for Network File System (NFS) to mount.
"mountPoint": "A String", # Required. Destination mount path. The NFS will be mounted for the user under /mnt/nfs/
"path": "A String", # Required. Source path exported from NFS server. Has to start with '/', and combined with the ip address, it indicates the source mount path in the form of `server:path`
"server": "A String", # Required. IP address of the NFS server.
},
],
"pythonPackageSpec": { # The spec of a Python packaged code. # The Python packaged task.
"args": [ # Command line arguments to be passed to the Python task.
"A String",
],
"env": [ # Environment variables to be passed to the python module. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"executorImageUri": "A String", # Required. The URI of a container image in Artifact Registry that will run the provided Python package. Vertex AI provides a wide range of executor images with pre-installed packages to meet users' various use cases. See the list of [pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). You must use an image from this list.
"packageUris": [ # Required. The Google Cloud Storage location of the Python package files which are the training program and its dependent packages. The maximum number of package URIs is 100.
"A String",
],
"pythonModule": "A String", # Required. The Python module name to run after installing the packages.
},
"replicaCount": "A String", # Optional. The number of worker replicas to use for this worker pool.
},
],
},
},
"trainTrialSpec": { # Represent spec for train trials. # Spec for train trials. Top N [TrainTrialSpec.max_parallel_trial_count] search trials will be trained for every M [TrainTrialSpec.frequency] trials searched.
"frequency": 42, # Required. Frequency of search trials to start train stage. Top N [TrainTrialSpec.max_parallel_trial_count] search trials will be trained for every M [TrainTrialSpec.frequency] trials searched.
"maxParallelTrialCount": 42, # Required. The maximum number of trials to run in parallel.
"trainTrialJobSpec": { # Represents the spec of a CustomJob. # Required. The spec of a train trial job. The same spec applies to all train trials.
"baseOutputDirectory": { # The Google Cloud Storage location where the output is to be written to. # The Cloud Storage location to store the output of this CustomJob or HyperparameterTuningJob. For HyperparameterTuningJob, the baseOutputDirectory of each child CustomJob backing a Trial is set to a subdirectory of name id under its parent HyperparameterTuningJob's baseOutputDirectory. The following Vertex AI environment variables will be passed to containers or python modules when this field is set: For CustomJob: * AIP_MODEL_DIR = `/model/` * AIP_CHECKPOINT_DIR = `/checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `/logs/` For CustomJob backing a Trial of HyperparameterTuningJob: * AIP_MODEL_DIR = `//model/` * AIP_CHECKPOINT_DIR = `//checkpoints/` * AIP_TENSORBOARD_LOG_DIR = `//logs/`
"outputUriPrefix": "A String", # Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
},
"enableDashboardAccess": True or False, # Optional. Whether you want Vertex AI to enable access to the customized dashboard in training chief container. If set to `true`, you can access the dashboard at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"enableWebAccess": True or False, # Optional. Whether you want Vertex AI to enable [interactive shell access](https://cloud.google.com/vertex-ai/docs/training/monitor-debug-interactive-shell) to training containers. If set to `true`, you can access interactive shells at the URIs given by CustomJob.web_access_uris or Trial.web_access_uris (within HyperparameterTuningJob.trials).
"experiment": "A String", # Optional. The Experiment associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}`
"experimentRun": "A String", # Optional. The Experiment Run associated with this job. Format: `projects/{project}/locations/{location}/metadataStores/{metadataStores}/contexts/{experiment-name}-{experiment-run-name}`
"models": [ # Optional. The name of the Model resources for which to generate a mapping to artifact URIs. Applicable only to some of the Google-provided custom jobs. Format: `projects/{project}/locations/{location}/models/{model}` In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` If no version ID or alias is specified, the "default" version will be returned. The "default" version alias is created for the first version of the model, and can be moved to other versions later on. There will be exactly one default version.
"A String",
],
"network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network.
"persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected.
"protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations
"pscInterfaceConfig": { # Configuration for PSC-I. # Optional. Configuration for PSC-I for CustomJob.
"dnsPeeringConfigs": [ # Optional. DNS peering configurations. When specified, Vertex AI will attempt to configure DNS peering zones in the tenant project VPC to resolve the specified domains using the target network's Cloud DNS. The user must grant the dns.peer role to the Vertex AI Service Agent on the target project.
{ # DNS peering configuration. These configurations are used to create DNS peering zones in the Vertex tenant project VPC, enabling resolution of records within the specified domain hosted in the target network's Cloud DNS.
"domain": "A String", # Required. The DNS name suffix of the zone being peered to, e.g., "my-internal-domain.corp.". Must end with a dot.
"targetNetwork": "A String", # Required. The VPC network name in the target_project where the DNS zone specified by 'domain' is visible.
"targetProject": "A String", # Required. The project ID hosting the Cloud DNS managed zone that contains the 'domain'. The Vertex AI Service Agent requires the dns.peer role on this project.
},
],
"networkAttachment": "A String", # Optional. The name of the Compute Engine [network attachment](https://cloud.google.com/vpc/docs/about-network-attachments) to attach to the resource within the region and user project. To specify this field, you must have already [created a network attachment] (https://cloud.google.com/vpc/docs/create-manage-network-attachments#create-network-attachments). This field is only used for resources using PSC-I.
},
"reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range'].
"A String",
],
"scheduling": { # All parameters related to queuing and scheduling of custom jobs. # Scheduling options for a CustomJob.
"disableRetries": True or False, # Optional. Indicates if the job should retry for internal errors after the job starts running. If true, overrides `Scheduling.restart_job_on_worker_restart` to false.
"maxWaitDuration": "A String", # Optional. This is the maximum duration that a job will wait for the requested resources to be provisioned if the scheduling strategy is set to [Strategy.DWS_FLEX_START]. If set to 0, the job will wait indefinitely. The default is 24 hours.
"restartJobOnWorkerRestart": True or False, # Optional. Restarts the entire CustomJob if a worker gets restarted. This feature can be used by distributed training jobs that are not resilient to workers leaving and joining a job.
"strategy": "A String", # Optional. This determines which type of scheduling strategy to use.
"timeout": "A String", # Optional. The maximum job running time. The default is 7 days.
},
"serviceAccount": "A String", # Specifies the service account for workload run-as account. Users submitting jobs must have act-as permission on this run-as account. If unspecified, the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) for the CustomJob's project is used.
"tensorboard": "A String", # Optional. The name of a Vertex AI Tensorboard resource to which this CustomJob will upload Tensorboard logs. Format: `projects/{project}/locations/{location}/tensorboards/{tensorboard}`
"workerPoolSpecs": [ # Required. The spec of the worker pools including machine type and Docker image. All worker pools except the first one are optional and can be skipped by providing an empty value.
{ # Represents the spec of a worker pool in a job.
"containerSpec": { # The spec of a Container. # The custom container task.
"args": [ # The arguments to be passed when starting the container.
"A String",
],
"command": [ # The command to be invoked when the container is started. It overrides the entrypoint instruction in Dockerfile when provided.
"A String",
],
"env": [ # Environment variables to be passed to the container. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"imageUri": "A String", # Required. The URI of a container image in the Container Registry that is to be run on each worker replica.
},
"diskSpec": { # Represents the spec of disk options. # Disk spec.
"bootDiskSizeGb": 42, # Size in GB of the boot disk (default is 100GB).
"bootDiskType": "A String", # Type of the boot disk. For non-A3U machines, the default value is "pd-ssd", for A3U machines, the default value is "hyperdisk-balanced". Valid values: "pd-ssd" (Persistent Disk Solid State Drive), "pd-standard" (Persistent Disk Hard Disk Drive) or "hyperdisk-balanced".
},
"machineSpec": { # Specification of a single machine. # Optional. Immutable. The specification of a single machine.
"acceleratorCount": 42, # The number of accelerators to attach to the machine.
"acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
"machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
"reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
"key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
"reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
"values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation or reservation block.
"A String",
],
},
"tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
},
"nfsMounts": [ # Optional. List of NFS mount spec.
{ # Represents a mount configuration for Network File System (NFS) to mount.
"mountPoint": "A String", # Required. Destination mount path. The NFS will be mounted for the user under /mnt/nfs/
"path": "A String", # Required. Source path exported from NFS server. Has to start with '/', and combined with the ip address, it indicates the source mount path in the form of `server:path`
"server": "A String", # Required. IP address of the NFS server.
},
],
"pythonPackageSpec": { # The spec of a Python packaged code. # The Python packaged task.
"args": [ # Command line arguments to be passed to the Python task.
"A String",
],
"env": [ # Environment variables to be passed to the python module. Maximum limit is 100.
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"executorImageUri": "A String", # Required. The URI of a container image in Artifact Registry that will run the provided Python package. Vertex AI provides a wide range of executor images with pre-installed packages to meet users' various use cases. See the list of [pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). You must use an image from this list.
"packageUris": [ # Required. The Google Cloud Storage location of the Python package files which are the training program and its dependent packages. The maximum number of package URIs is 100.
"A String",
],
"pythonModule": "A String", # Required. The Python module name to run after installing the packages.
},
"replicaCount": "A String", # Optional. The number of worker replicas to use for this worker pool.
},
],
},
},
},
"resumeNasJobId": "A String", # The ID of the existing NasJob in the same Project and Location which will be used to resume search. search_space_spec and nas_algorithm_spec are obtained from previous NasJob hence should not provide them again for this NasJob.
"searchSpaceSpec": "A String", # It defines the search space for Neural Architecture Search (NAS).
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"startTime": "A String", # Output only. Time when the NasJob for the first time entered the `JOB_STATE_RUNNING` state.
"state": "A String", # Output only. The detailed state of the job.
"updateTime": "A String", # Output only. Time when the NasJob was most recently updated.
},
],
"nextPageToken": "A String", # A token to retrieve the next page of results. Pass to ListNasJobsRequest.page_token to obtain that page.
}</pre>
</div>
<div class="method">
<code class="details" id="list_next">list_next()</code>
<pre>Retrieves the next page of results.
Args:
previous_request: The request for the previous page. (required)
previous_response: The response from the request for the previous page. (required)
Returns:
A request object that you can call 'execute()' on to request the next
page. Returns None if there are no more items in the collection.
</pre>
</div>
</body></html>
|
