java.lang.Object
- software.amazon.awssdk.services.bedrock.model.RFTHyperParameters

All Implemented Interfaces:

Serializable, SdkPojo, ToCopyableBuilder<RFTHyperParameters.Builder,RFTHyperParameters>
```
@Generated("software.amazon.awssdk:codegen")
public final class RFTHyperParameters
extends Object
implements SdkPojo, Serializable, ToCopyableBuilder<RFTHyperParameters.Builder,RFTHyperParameters>
```
Hyperparameters for controlling the reinforcement fine-tuning training process, including learning settings and evaluation intervals.

See Also:

Serialized Form

Nested Class Summary

Nested Classes
Modifier and Type Class Description

static interface RFTHyperParameters.Builder

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method	Description
`Integer`	`batchSize()`	Number of training samples processed in each batch during reinforcement fine-tuning (RFT) training.
`static RFTHyperParameters.Builder`	`builder()`
`Integer`	`epochCount()`	Number of training epochs to run during reinforcement fine-tuning.
`boolean`	`equals(Object obj)`
`boolean`	`equalsBySdkFields(Object obj)`
`Integer`	`evalInterval()`	Interval between evaluation runs during RFT training, measured in training steps.
`<T> Optional<T>`	`getValueForField(String fieldName, Class<T> clazz)`
`int`	`hashCode()`
`Integer`	`inferenceMaxTokens()`	Maximum number of tokens the model can generate in response to each prompt during RFT training.
`Float`	`learningRate()`	Learning rate for the reinforcement fine-tuning.
`Integer`	`maxPromptLength()`	Maximum length of input prompts during RFT training, measured in tokens.
`ReasoningEffort`	`reasoningEffort()`	Level of reasoning effort applied during RFT training.
`String`	`reasoningEffortAsString()`	Level of reasoning effort applied during RFT training.
`Map<String,SdkField<?>>`	`sdkFieldNameToField()`
`List<SdkField<?>>`	`sdkFields()`
`static Class<? extends RFTHyperParameters.Builder>`	`serializableBuilderClass()`
`RFTHyperParameters.Builder`	`toBuilder()`
`String`	`toString()`	Returns a string representation of this object.
`Integer`	`trainingSamplePerPrompt()`	Number of response samples generated per prompt during RFT training.

Methods inherited from class java.lang.Object
clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface software.amazon.awssdk.utils.builder.ToCopyableBuilder
copy

- Method Detail
  - epochCount
```
public final Integer epochCount()
```
    Number of training epochs to run during reinforcement fine-tuning. Higher values may improve performance but increase training time.
    
    Returns:
    
    Number of training epochs to run during reinforcement fine-tuning. Higher values may improve performance but increase training time.
  - batchSize
```
public final Integer batchSize()
```
    Number of training samples processed in each batch during reinforcement fine-tuning (RFT) training. Larger batches may improve training stability.
    
    Returns:
    
    Number of training samples processed in each batch during reinforcement fine-tuning (RFT) training. Larger batches may improve training stability.
  - learningRate
```
public final Float learningRate()
```
    Learning rate for the reinforcement fine-tuning. Controls how quickly the model adapts to reward signals.
    
    Returns:
    
    Learning rate for the reinforcement fine-tuning. Controls how quickly the model adapts to reward signals.
  - maxPromptLength
```
public final Integer maxPromptLength()
```
    Maximum length of input prompts during RFT training, measured in tokens. Longer prompts allow more context but increase memory usage and training-time.
    
    Returns:
    
    Maximum length of input prompts during RFT training, measured in tokens. Longer prompts allow more context but increase memory usage and training-time.
  - trainingSamplePerPrompt
```
public final Integer trainingSamplePerPrompt()
```
    Number of response samples generated per prompt during RFT training. More samples provide better reward signal estimation.
    
    Returns:
    
    Number of response samples generated per prompt during RFT training. More samples provide better reward signal estimation.
  - inferenceMaxTokens
```
public final Integer inferenceMaxTokens()
```
    Maximum number of tokens the model can generate in response to each prompt during RFT training.
    
    Returns:
    
    Maximum number of tokens the model can generate in response to each prompt during RFT training.
  - reasoningEffort
```
public final ReasoningEffort reasoningEffort()
```
    Level of reasoning effort applied during RFT training. Higher values may improve response quality but increase training time.
    
    If the service returns an enum value that is not available in the current SDK version, reasoningEffort will return ReasoningEffort.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from reasoningEffortAsString().
    
    Returns:
    
    Level of reasoning effort applied during RFT training. Higher values may improve response quality but increase training time.
    
    See Also:
    
    ReasoningEffort
  - reasoningEffortAsString
```
public final String reasoningEffortAsString()
```
    Level of reasoning effort applied during RFT training. Higher values may improve response quality but increase training time.
    
    If the service returns an enum value that is not available in the current SDK version, reasoningEffort will return ReasoningEffort.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from reasoningEffortAsString().
    
    Returns:
    
    Level of reasoning effort applied during RFT training. Higher values may improve response quality but increase training time.
    
    See Also:
    
    ReasoningEffort
  - evalInterval
```
public final Integer evalInterval()
```
    Interval between evaluation runs during RFT training, measured in training steps. More frequent evaluation provides better monitoring.
    
    Returns:
    
    Interval between evaluation runs during RFT training, measured in training steps. More frequent evaluation provides better monitoring.
  - toBuilder
```
public RFTHyperParameters.Builder toBuilder()
```
    Specified by:
    
    toBuilder in interface ToCopyableBuilder<RFTHyperParameters.Builder,RFTHyperParameters>
  - builder
```
public static RFTHyperParameters.Builder builder()
```
  - serializableBuilderClass
```
public static Class<? extends RFTHyperParameters.Builder> serializableBuilderClass()
```
  - hashCode
```
public final int hashCode()
```
    Overrides:
    
    hashCode in class Object
  - equals
```
public final boolean equals(Object obj)
```
    Overrides:
    
    equals in class Object
  - equalsBySdkFields
```
public final boolean equalsBySdkFields(Object obj)
```
    Specified by:
    
    equalsBySdkFields in interface SdkPojo
  - toString
```
public final String 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.
    
    Overrides:
    
    toString in class Object
  - getValueForField
```
public final <T> Optional<T> getValueForField(String fieldName,
                                              Class<T> clazz)
```
  - sdkFields
```
public final List<SdkField<?>> sdkFields()
```
    Specified by:
    
    sdkFields in interface SdkPojo
  - sdkFieldNameToField
```
public final Map<String,SdkField<?>> sdkFieldNameToField()
```
    Specified by:
    
    sdkFieldNameToField in interface SdkPojo

Class RFTHyperParameters

Nested Class Summary

Method Summary

Methods inherited from class java.lang.Object

Methods inherited from interface software.amazon.awssdk.utils.builder.ToCopyableBuilder

Method Detail

epochCount

batchSize

learningRate

maxPromptLength

trainingSamplePerPrompt

inferenceMaxTokens

reasoningEffort

reasoningEffortAsString

evalInterval

toBuilder

builder

serializableBuilderClass

hashCode

equals

equalsBySdkFields

toString

getValueForField

sdkFields

sdkFieldNameToField