Class FineTuningJobCreateParams.Method.Dpo.Hyperparameters
-
- All Implemented Interfaces:
public final class FineTuningJobCreateParams.Method.Dpo.HyperparametersThe hyperparameters used for the fine-tuning job.
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description public final classFineTuningJobCreateParams.Method.Dpo.Hyperparameters.BuilderA builder for Hyperparameters.
public final classFineTuningJobCreateParams.Method.Dpo.Hyperparameters.BatchSizeNumber of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
public final classFineTuningJobCreateParams.Method.Dpo.Hyperparameters.BetaThe beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model.
public final classFineTuningJobCreateParams.Method.Dpo.Hyperparameters.LearningRateMultiplierScaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.
public final classFineTuningJobCreateParams.Method.Dpo.Hyperparameters.NEpochsThe number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.
-
Method Summary
-
-
Method Detail
-
batchSize
final Optional<FineTuningJobCreateParams.Method.Dpo.Hyperparameters.BatchSize> batchSize()
Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
-
beta
final Optional<FineTuningJobCreateParams.Method.Dpo.Hyperparameters.Beta> beta()
The beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model.
-
learningRateMultiplier
final Optional<FineTuningJobCreateParams.Method.Dpo.Hyperparameters.LearningRateMultiplier> learningRateMultiplier()
Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.
-
nEpochs
final Optional<FineTuningJobCreateParams.Method.Dpo.Hyperparameters.NEpochs> nEpochs()
The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.
-
_batchSize
final JsonField<FineTuningJobCreateParams.Method.Dpo.Hyperparameters.BatchSize> _batchSize()
Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
-
_beta
final JsonField<FineTuningJobCreateParams.Method.Dpo.Hyperparameters.Beta> _beta()
The beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model.
-
_learningRateMultiplier
final JsonField<FineTuningJobCreateParams.Method.Dpo.Hyperparameters.LearningRateMultiplier> _learningRateMultiplier()
Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.
-
_nEpochs
final JsonField<FineTuningJobCreateParams.Method.Dpo.Hyperparameters.NEpochs> _nEpochs()
The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.
-
_additionalProperties
final Map<String, JsonValue> _additionalProperties()
-
validate
final FineTuningJobCreateParams.Method.Dpo.Hyperparameters validate()
-
toBuilder
final FineTuningJobCreateParams.Method.Dpo.Hyperparameters.Builder toBuilder()
-
builder
final static FineTuningJobCreateParams.Method.Dpo.Hyperparameters.Builder builder()
-
-
-
-