Class: OpenAI::Models::FineTuning::ReinforcementHyperparameters

Inherits:
Internal::Type::BaseModel show all
Defined in:
lib/openai/models/fine_tuning/reinforcement_hyperparameters.rb,
sig/openai/models/fine_tuning/reinforcement_hyperparameters.rbs

Defined Under Namespace

Modules: BatchSize, ComputeMultiplier, EvalInterval, EvalSamples, LearningRateMultiplier, NEpochs, ReasoningEffort

Instance Attribute Summary collapse

Attributes inherited from Internal::Type::BaseModel

#last_response

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from Internal::Type::BaseModel

==, #==, #[], #_request_id, #_set_last_response, coerce, #deconstruct_keys, #deep_to_h, dump, #encode_with, fields, hash, #hash, inherited, #inspect, inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, coerce_with_error, dump, #dump, #inspect, inspect, meta_info, new_coerce_state, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

#initialize(batch_size: nil, compute_multiplier: nil, eval_interval: nil, eval_samples: nil, learning_rate_multiplier: nil, n_epochs: nil, reasoning_effort: nil) ⇒ Object

Parameters:

  • batch_size (defaults to: nil) —

    Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

  • compute_multiplier (defaults to: nil) —

    Multiplier on amount of compute used for exploring search space during training.

  • eval_interval (defaults to: nil) —

    The number of training steps between evaluation runs.

  • eval_samples (defaults to: nil) —

    Number of evaluation samples to generate per training step.

  • learning_rate_multiplier (defaults to: nil) —

    Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

  • n_epochs (defaults to: nil) —

    The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

  • reasoning_effort (defaults to: nil) —

    Level of reasoning effort.




# File 'lib/openai/models/fine_tuning/reinforcement_hyperparameters.rb', line 58

Instance Attribute Details

#batch_size ⇒ OpenAI::Models::FineTuning::ReinforcementHyperparameters::batch_size?

Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

Returns:

  • (OpenAI::Models::FineTuning::ReinforcementHyperparameters::batch_size, nil) 


12
 
# File 'lib/openai/models/fine_tuning/reinforcement_hyperparameters.rb', line 12

optional :batch_size, union: -> { OpenAI::FineTuning::ReinforcementHyperparameters::BatchSize }

#compute_multiplier ⇒ OpenAI::Models::FineTuning::ReinforcementHyperparameters::compute_multiplier?

Multiplier on amount of compute used for exploring search space during training.

Returns:

  • (OpenAI::Models::FineTuning::ReinforcementHyperparameters::compute_multiplier, nil) 


18
19
20
21
 
# File 'lib/openai/models/fine_tuning/reinforcement_hyperparameters.rb', line 18

optional(
  :compute_multiplier,
  union: -> { OpenAI::FineTuning::ReinforcementHyperparameters::ComputeMultiplier }
)

#eval_interval ⇒ OpenAI::Models::FineTuning::ReinforcementHyperparameters::eval_interval?

The number of training steps between evaluation runs.

Returns:

  • (OpenAI::Models::FineTuning::ReinforcementHyperparameters::eval_interval, nil) 


27
 
# File 'lib/openai/models/fine_tuning/reinforcement_hyperparameters.rb', line 27

optional :eval_interval, union: -> { OpenAI::FineTuning::ReinforcementHyperparameters::EvalInterval }

#eval_samples ⇒ OpenAI::Models::FineTuning::ReinforcementHyperparameters::eval_samples?

Number of evaluation samples to generate per training step.

Returns:

  • (OpenAI::Models::FineTuning::ReinforcementHyperparameters::eval_samples, nil) 


33
 
# File 'lib/openai/models/fine_tuning/reinforcement_hyperparameters.rb', line 33

optional :eval_samples, union: -> { OpenAI::FineTuning::ReinforcementHyperparameters::EvalSamples }

#learning_rate_multiplier ⇒ OpenAI::Models::FineTuning::ReinforcementHyperparameters::learning_rate_multiplier?

Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

Returns:

  • (OpenAI::Models::FineTuning::ReinforcementHyperparameters::learning_rate_multiplier, nil) 


40
41
42
43
 
# File 'lib/openai/models/fine_tuning/reinforcement_hyperparameters.rb', line 40

optional(
  :learning_rate_multiplier,
  union: -> { OpenAI::FineTuning::ReinforcementHyperparameters::LearningRateMultiplier }
)

#n_epochs ⇒ OpenAI::Models::FineTuning::ReinforcementHyperparameters::n_epochs?

The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

Returns:

  • (OpenAI::Models::FineTuning::ReinforcementHyperparameters::n_epochs, nil) 


50
 
# File 'lib/openai/models/fine_tuning/reinforcement_hyperparameters.rb', line 50

optional :n_epochs, union: -> { OpenAI::FineTuning::ReinforcementHyperparameters::NEpochs }

#reasoning_effort ⇒ OpenAI::Models::FineTuning::ReinforcementHyperparameters::reasoning_effort?

Level of reasoning effort.

Returns:

  • (OpenAI::Models::FineTuning::ReinforcementHyperparameters::reasoning_effort, nil) 


56
 
# File 'lib/openai/models/fine_tuning/reinforcement_hyperparameters.rb', line 56

optional :reasoning_effort, enum: -> { OpenAI::FineTuning::ReinforcementHyperparameters::ReasoningEffort }

Class Method Details

.variants ⇒ Array(Symbol, :auto, Integer)

Returns:

  • (Array(Symbol, :auto, Integer)) 



# File 'lib/openai/models/fine_tuning/reinforcement_hyperparameters.rb', line 96

Instance Method Details

#to_hash ⇒ {

Returns:

  • ({) 


105
 
# File 'sig/openai/models/fine_tuning/reinforcement_hyperparameters.rbs', line 105

def to_hash: -> {