Struct ReinforcementHyperparameters 

pub struct ReinforcementHyperparameters {
    pub batch_size: Option<String>,
    pub compute_multiplier: Option<String>,
    pub eval_interval: Option<String>,
    pub eval_samples: Option<String>,
    pub learning_rate_multiplier: Option<String>,
    pub n_epochs: Option<String>,
    pub reasoning_effort: Option<ReinforcementHyperparametersReasoningEffort>,
}

The hyperparameters used for the reinforcement fine-tuning job.

Fields

batch_size: Option<String>

Number of examples in each batch.

compute_multiplier: Option<String>

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

eval_interval: Option<String>

The number of training steps between evaluation runs.

eval_samples: Option<String>

Number of evaluation samples to generate per training step.

learning_rate_multiplier: Option<String>

Scaling factor for the learning rate.

n_epochs: Option<String>

The number of epochs to train the model for.

reasoning_effort: Option<ReinforcementHyperparametersReasoningEffort>

Level of reasoning effort.

Trait Implementations

impl Clone for ReinforcementHyperparameters

fn clone(&self) -> ReinforcementHyperparameters

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ReinforcementHyperparameters

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ReinforcementHyperparameters

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ReinforcementHyperparameters

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.