Reference documentation and code samples for the Document AI V1beta3 API class Google::Cloud::DocumentAI::V1beta3::TrainProcessorVersionRequest::FoundationModelTuningOptions.
Options to control foundation model tuning of the processor.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#learning_rate_multiplier
def learning_rate_multiplier() -> ::Float
Returns
- (::Float) — Optional. The multiplier to apply to the recommended learning rate. Valid values are between 0.1 and 10. If not provided, recommended learning rate will be used.
#learning_rate_multiplier=
def learning_rate_multiplier=(value) -> ::Float
Parameter
- value (::Float) — Optional. The multiplier to apply to the recommended learning rate. Valid values are between 0.1 and 10. If not provided, recommended learning rate will be used.
Returns
- (::Float) — Optional. The multiplier to apply to the recommended learning rate. Valid values are between 0.1 and 10. If not provided, recommended learning rate will be used.
#train_steps
def train_steps() -> ::Integer
Returns
- (::Integer) — Optional. The number of steps to run for model tuning. Valid values are between 1 and 400. If not provided, recommended steps will be used.
#train_steps=
def train_steps=(value) -> ::Integer
Parameter
- value (::Integer) — Optional. The number of steps to run for model tuning. Valid values are between 1 and 400. If not provided, recommended steps will be used.
Returns
- (::Integer) — Optional. The number of steps to run for model tuning. Valid values are between 1 and 400. If not provided, recommended steps will be used.