Class TextGenerationJobConfig
- All Implemented Interfaces:
Serializable
,SdkPojo
,ToCopyableBuilder<TextGenerationJobConfig.Builder,
TextGenerationJobConfig>
The collection of settings used by an AutoML job V2 for the text generation problem type.
The text generation models that support fine-tuning in Autopilot are currently accessible exclusively in regions supported by Canvas. Refer to the documentation of Canvas for the full list of its supported Regions.
- See Also:
-
Nested Class Summary
-
Method Summary
Modifier and TypeMethodDescriptionfinal String
The name of the base model to fine-tune.builder()
How long a fine-tuning job is allowed to run.final boolean
final boolean
equalsBySdkFields
(Object obj) Indicates whether some other object is "equal to" this one by SDK fields.final <T> Optional
<T> getValueForField
(String fieldName, Class<T> clazz) final int
hashCode()
final boolean
For responses, this returns true if the service returned a value for the TextGenerationHyperParameters property.final ModelAccessConfig
Returns the value of the ModelAccessConfig property for this object.static Class
<? extends TextGenerationJobConfig.Builder> The hyperparameters used to configure and optimize the learning process of the base model.Take this object and create a builder that contains all of the current property values of this object.final String
toString()
Returns a string representation of this object.Methods inherited from interface software.amazon.awssdk.utils.builder.ToCopyableBuilder
copy
-
Method Details
-
completionCriteria
How long a fine-tuning job is allowed to run. For
TextGenerationJobConfig
problem types, theMaxRuntimePerTrainingJobInSeconds
attribute ofAutoMLJobCompletionCriteria
defaults to 72h (259200s).- Returns:
- How long a fine-tuning job is allowed to run. For
TextGenerationJobConfig
problem types, theMaxRuntimePerTrainingJobInSeconds
attribute ofAutoMLJobCompletionCriteria
defaults to 72h (259200s).
-
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.- Returns:
- 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.
-
hasTextGenerationHyperParameters
public final boolean hasTextGenerationHyperParameters()For responses, this returns true if the service returned a value for the TextGenerationHyperParameters property. This DOES NOT check that the value is non-empty (for which, you should check theisEmpty()
method on the property). This is useful because the SDK will never return a null collection or map, but you may need to differentiate between the service returning nothing (or null) and the service returning an empty collection or map. For requests, this returns true if a value for the property was specified in the request builder, and false if a value was not specified. -
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" }
Attempts to modify the collection returned by this method will result in an UnsupportedOperationException.
This method will never return null. If you would like to know whether the service returned this field (so that you can differentiate between null and empty), you can use the
hasTextGenerationHyperParameters()
method.- Returns:
- 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" }
-
-
-
modelAccessConfig
Returns the value of the ModelAccessConfig property for this object.- Returns:
- The value of the ModelAccessConfig property for this object.
-
toBuilder
Description copied from interface:ToCopyableBuilder
Take this object and create a builder that contains all of the current property values of this object.- Specified by:
toBuilder
in interfaceToCopyableBuilder<TextGenerationJobConfig.Builder,
TextGenerationJobConfig> - Returns:
- a builder for type T
-
builder
-
serializableBuilderClass
-
hashCode
public final int hashCode() -
equals
-
equalsBySdkFields
Description copied from interface:SdkPojo
Indicates whether some other object is "equal to" this one by SDK fields. An SDK field is a modeled, non-inherited field in anSdkPojo
class, and is generated based on a service model.If an
SdkPojo
class does not have any inherited fields,equalsBySdkFields
andequals
are essentially the same.- Specified by:
equalsBySdkFields
in interfaceSdkPojo
- Parameters:
obj
- the object to be compared with- Returns:
- true if the other object equals to this object by sdk fields, false otherwise.
-
toString
Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be redacted from this string using a placeholder value. -
getValueForField
-
sdkFields
-