Interface TextGenerationJobConfig.Builder
-
- All Superinterfaces:
Buildable
,CopyableBuilder<TextGenerationJobConfig.Builder,TextGenerationJobConfig>
,SdkBuilder<TextGenerationJobConfig.Builder,TextGenerationJobConfig>
,SdkPojo
- Enclosing class:
- TextGenerationJobConfig
public static interface TextGenerationJobConfig.Builder extends SdkPojo, CopyableBuilder<TextGenerationJobConfig.Builder,TextGenerationJobConfig>
-
-
Method Summary
All Methods Instance Methods Abstract Methods Default Methods Modifier and Type Method Description TextGenerationJobConfig.Builder
baseModelName(String baseModelName)
The name of the base model to fine-tune.default TextGenerationJobConfig.Builder
completionCriteria(Consumer<AutoMLJobCompletionCriteria.Builder> completionCriteria)
How long a fine-tuning job is allowed to run.TextGenerationJobConfig.Builder
completionCriteria(AutoMLJobCompletionCriteria completionCriteria)
How long a fine-tuning job is allowed to run.default TextGenerationJobConfig.Builder
modelAccessConfig(Consumer<ModelAccessConfig.Builder> modelAccessConfig)
Sets the value of the ModelAccessConfig property for this object.TextGenerationJobConfig.Builder
modelAccessConfig(ModelAccessConfig modelAccessConfig)
Sets the value of the ModelAccessConfig property for this object.TextGenerationJobConfig.Builder
textGenerationHyperParameters(Map<String,String> textGenerationHyperParameters)
The hyperparameters used to configure and optimize the learning process of the base model.-
Methods inherited from interface software.amazon.awssdk.utils.builder.CopyableBuilder
copy
-
Methods inherited from interface software.amazon.awssdk.utils.builder.SdkBuilder
applyMutation, build
-
Methods inherited from interface software.amazon.awssdk.core.SdkPojo
equalsBySdkFields, sdkFields
-
-
-
-
Method Detail
-
completionCriteria
TextGenerationJobConfig.Builder completionCriteria(AutoMLJobCompletionCriteria completionCriteria)
How long a fine-tuning job is allowed to run. For
TextGenerationJobConfig
problem types, theMaxRuntimePerTrainingJobInSeconds
attribute ofAutoMLJobCompletionCriteria
defaults to 72h (259200s).- Parameters:
completionCriteria
- How long a fine-tuning job is allowed to run. ForTextGenerationJobConfig
problem types, theMaxRuntimePerTrainingJobInSeconds
attribute ofAutoMLJobCompletionCriteria
defaults to 72h (259200s).- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
completionCriteria
default TextGenerationJobConfig.Builder completionCriteria(Consumer<AutoMLJobCompletionCriteria.Builder> completionCriteria)
How long a fine-tuning job is allowed to run. For
This is a convenience method that creates an instance of theTextGenerationJobConfig
problem types, theMaxRuntimePerTrainingJobInSeconds
attribute ofAutoMLJobCompletionCriteria
defaults to 72h (259200s).AutoMLJobCompletionCriteria.Builder
avoiding the need to create one manually viaAutoMLJobCompletionCriteria.builder()
.When the
Consumer
completes,SdkBuilder.build()
is called immediately and its result is passed tocompletionCriteria(AutoMLJobCompletionCriteria)
.- Parameters:
completionCriteria
- a consumer that will call methods onAutoMLJobCompletionCriteria.Builder
- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
completionCriteria(AutoMLJobCompletionCriteria)
-
baseModelName
TextGenerationJobConfig.Builder baseModelName(String baseModelName)
The name of the base model to fine-tune. Autopilot supports fine-tuning a variety of large language models. For information on the list of supported models, see Text generation models supporting fine-tuning in Autopilot. If no
BaseModelName
is provided, the default model used is Falcon7BInstruct.- Parameters:
baseModelName
- The name of the base model to fine-tune. Autopilot supports fine-tuning a variety of large language models. For information on the list of supported models, see Text generation models supporting fine-tuning in Autopilot. If noBaseModelName
is provided, the default model used is Falcon7BInstruct.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
textGenerationHyperParameters
TextGenerationJobConfig.Builder textGenerationHyperParameters(Map<String,String> textGenerationHyperParameters)
The hyperparameters used to configure and optimize the learning process of the base model. You can set any combination of the following hyperparameters for all base models. For more information on each supported hyperparameter, see Optimize the learning process of your text generation models with hyperparameters.
-
"epochCount"
: The number of times the model goes through the entire training dataset. Its value should be a string containing an integer value within the range of "1" to "10". -
"batchSize"
: The number of data samples used in each iteration of training. Its value should be a string containing an integer value within the range of "1" to "64". -
"learningRate"
: The step size at which a model's parameters are updated during training. Its value should be a string containing a floating-point value within the range of "0" to "1". -
"learningRateWarmupSteps"
: The number of training steps during which the learning rate gradually increases before reaching its target or maximum value. Its value should be a string containing an integer value within the range of "0" to "250".
Here is an example where all four hyperparameters are configured.
{ "epochCount":"5", "learningRate":"0.5", "batchSize": "32", "learningRateWarmupSteps": "10" }
- Parameters:
textGenerationHyperParameters
- The hyperparameters used to configure and optimize the learning process of the base model. You can set any combination of the following hyperparameters for all base models. For more information on each supported hyperparameter, see Optimize the learning process of your text generation models with hyperparameters.-
"epochCount"
: The number of times the model goes through the entire training dataset. Its value should be a string containing an integer value within the range of "1" to "10". -
"batchSize"
: The number of data samples used in each iteration of training. Its value should be a string containing an integer value within the range of "1" to "64". -
"learningRate"
: The step size at which a model's parameters are updated during training. Its value should be a string containing a floating-point value within the range of "0" to "1". -
"learningRateWarmupSteps"
: The number of training steps during which the learning rate gradually increases before reaching its target or maximum value. Its value should be a string containing an integer value within the range of "0" to "250".
Here is an example where all four hyperparameters are configured.
{ "epochCount":"5", "learningRate":"0.5", "batchSize": "32", "learningRateWarmupSteps": "10" }
-
- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
-
modelAccessConfig
TextGenerationJobConfig.Builder modelAccessConfig(ModelAccessConfig modelAccessConfig)
Sets the value of the ModelAccessConfig property for this object.- Parameters:
modelAccessConfig
- The new value for the ModelAccessConfig property for this object.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
modelAccessConfig
default TextGenerationJobConfig.Builder modelAccessConfig(Consumer<ModelAccessConfig.Builder> modelAccessConfig)
Sets the value of the ModelAccessConfig property for this object. This is a convenience method that creates an instance of theModelAccessConfig.Builder
avoiding the need to create one manually viaModelAccessConfig.builder()
.When the
Consumer
completes,SdkBuilder.build()
is called immediately and its result is passed tomodelAccessConfig(ModelAccessConfig)
.- Parameters:
modelAccessConfig
- a consumer that will call methods onModelAccessConfig.Builder
- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
modelAccessConfig(ModelAccessConfig)
-
-