« blib/lib/Paws/SageMaker/TrainingJob.pm
↑ Summary
blib/lib/Paws/SageMaker/TrainingJobStatusCounters.pm »
| 1 | # Generated by default/object.tt | ||
| 2 | package Paws::SageMaker::TrainingJobDefinition; | ||
| 3 | use Moose; | ||
| 4 | has HyperParameters => (is => 'ro', isa => 'Paws::SageMaker::HyperParameters'); | ||
| 5 | has InputDataConfig => (is => 'ro', isa => 'ArrayRef[Paws::SageMaker::Channel]', required => 1); | ||
| 6 | has OutputDataConfig => (is => 'ro', isa => 'Paws::SageMaker::OutputDataConfig', required => 1); | ||
| 7 | has ResourceConfig => (is => 'ro', isa => 'Paws::SageMaker::ResourceConfig', required => 1); | ||
| 8 | has StoppingCondition => (is => 'ro', isa => 'Paws::SageMaker::StoppingCondition', required => 1); | ||
| 9 | has TrainingInputMode => (is => 'ro', isa => 'Str', required => 1); | ||
| 10 | |||
| 11 | 1; | ||
| 12 | |||
| 13 | ### main pod documentation begin ### | ||
| 14 | |||
| 15 | =head1 NAME | ||
| 16 | |||
| 17 | Paws::SageMaker::TrainingJobDefinition | ||
| 18 | |||
| 19 | =head1 USAGE | ||
| 20 | |||
| 21 | This class represents one of two things: | ||
| 22 | |||
| 23 | =head3 Arguments in a call to a service | ||
| 24 | |||
| 25 | Use the attributes of this class as arguments to methods. You shouldn't make instances of this class. | ||
| 26 | Each attribute should be used as a named argument in the calls that expect this type of object. | ||
| 27 | |||
| 28 | As an example, if Att1 is expected to be a Paws::SageMaker::TrainingJobDefinition object: | ||
| 29 | |||
| 30 | $service_obj->Method(Att1 => { HyperParameters => $value, ..., TrainingInputMode => $value }); | ||
| 31 | |||
| 32 | =head3 Results returned from an API call | ||
| 33 | |||
| 34 | Use accessors for each attribute. If Att1 is expected to be an Paws::SageMaker::TrainingJobDefinition object: | ||
| 35 | |||
| 36 | $result = $service_obj->Method(...); | ||
| 37 | $result->Att1->HyperParameters | ||
| 38 | |||
| 39 | =head1 DESCRIPTION | ||
| 40 | |||
| 41 | Defines the input needed to run a training job using the algorithm. | ||
| 42 | |||
| 43 | =head1 ATTRIBUTES | ||
| 44 | |||
| 45 | |||
| 46 | =head2 HyperParameters => L<Paws::SageMaker::HyperParameters> | ||
| 47 | |||
| 48 | The hyperparameters used for the training job. | ||
| 49 | |||
| 50 | |||
| 51 | =head2 B<REQUIRED> InputDataConfig => ArrayRef[L<Paws::SageMaker::Channel>] | ||
| 52 | |||
| 53 | An array of C<Channel> objects, each of which specifies an input | ||
| 54 | source. | ||
| 55 | |||
| 56 | |||
| 57 | =head2 B<REQUIRED> OutputDataConfig => L<Paws::SageMaker::OutputDataConfig> | ||
| 58 | |||
| 59 | the path to the S3 bucket where you want to store model artifacts. | ||
| 60 | Amazon SageMaker creates subfolders for the artifacts. | ||
| 61 | |||
| 62 | |||
| 63 | =head2 B<REQUIRED> ResourceConfig => L<Paws::SageMaker::ResourceConfig> | ||
| 64 | |||
| 65 | The resources, including the ML compute instances and ML storage | ||
| 66 | volumes, to use for model training. | ||
| 67 | |||
| 68 | |||
| 69 | =head2 B<REQUIRED> StoppingCondition => L<Paws::SageMaker::StoppingCondition> | ||
| 70 | |||
| 71 | Specifies a limit to how long a model training job can run. It also | ||
| 72 | specifies how long a managed Spot training job has to complete. When | ||
| 73 | the job reaches the time limit, Amazon SageMaker ends the training job. | ||
| 74 | Use this API to cap model training costs. | ||
| 75 | |||
| 76 | To stop a job, Amazon SageMaker sends the algorithm the SIGTERM signal, | ||
| 77 | which delays job termination for 120 seconds. Algorithms can use this | ||
| 78 | 120-second window to save the model artifacts. | ||
| 79 | |||
| 80 | |||
| 81 | =head2 B<REQUIRED> TrainingInputMode => Str | ||
| 82 | |||
| 83 | The input mode used by the algorithm for the training job. For the | ||
| 84 | input modes that Amazon SageMaker algorithms support, see Algorithms | ||
| 85 | (https://docs.aws.amazon.com/sagemaker/latest/dg/algos.html). | ||
| 86 | |||
| 87 | If an algorithm supports the C<File> input mode, Amazon SageMaker | ||
| 88 | downloads the training data from S3 to the provisioned ML storage | ||
| 89 | Volume, and mounts the directory to docker volume for training | ||
| 90 | container. If an algorithm supports the C<Pipe> input mode, Amazon | ||
| 91 | SageMaker streams data directly from S3 to the container. | ||
| 92 | |||
| 93 | |||
| 94 | |||
| 95 | =head1 SEE ALSO | ||
| 96 | |||
| 97 | This class forms part of L<Paws>, describing an object used in L<Paws::SageMaker> | ||
| 98 | |||
| 99 | =head1 BUGS and CONTRIBUTIONS | ||
| 100 | |||
| 101 | The source code is located here: L<https://github.com/pplu/aws-sdk-perl> | ||
| 102 | |||
| 103 | Please report bugs to: L<https://github.com/pplu/aws-sdk-perl/issues> | ||
| 104 | |||
| 105 | =cut | ||
| 106 |