Struct CreateFineTuneRequest

pub struct CreateFineTuneRequest {
    pub training_file: String,
    pub validation_file: Option<String>,
    pub model: Option<String>,
    pub n_epochs: Option<u32>,
    pub batch_size: Option<u32>,
    pub learning_rate_multiplier: Option<f64>,
    pub prompt_loss_weight: Option<f64>,
    pub compute_classification_metrics: Option<bool>,
    pub classification_n_classes: Option<u32>,
    pub classification_positive_class: Option<String>,
    pub classification_betas: Option<Vec<f64>>,
    pub suffix: Option<String>,
}

A request struct for creating a fine-tune job.

Required parameter: training_file (the file ID of your training data).

Other fields are optional or have defaults. See OpenAI Docs for details on each parameter.

Fields

training_file: String

The ID of an uploaded file that contains training data.

See the Files API to upload a file and get this ID.
Required.

validation_file: Option<String>

The ID of an uploaded file that contains validation data. If None, no validation is used.

model: Option<String>

The model to start fine-tuning from (e.g. “curie”).
Defaults to “curie” if None.

n_epochs: Option<u32>

The number of epochs to train the model for.

batch_size: Option<u32>

The batch size to use for training.

learning_rate_multiplier: Option<f64>

The learning rate multiplier to use. The fine-tune API will pick a default based on dataset size if None.

prompt_loss_weight: Option<f64>

The weight to assign to the prompt loss relative to the completion loss.

compute_classification_metrics: Option<bool>

If true, calculates classification-specific metrics such as accuracy and F-1, assuming the training data is intended for classification.

classification_n_classes: Option<u32>

The number of classes in a classification task.

classification_positive_class: Option<String>

The positive class in a binary classification task.

classification_betas: Option<Vec<f64>>

If this is specified, calculates F-beta scores at the specified beta values.

suffix: Option<String>

A string of up to 40 characters that will be added to your fine-tuned model name.

Trait Implementations

impl Clone for CreateFineTuneRequest

fn clone(&self) -> CreateFineTuneRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CreateFineTuneRequest

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

Formats the value using the given formatter.

impl Default for CreateFineTuneRequest

fn default() -> CreateFineTuneRequest

Returns the “default value” for a type.

impl Serialize for CreateFineTuneRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.