CreateFineTuneParameters

CreateFineTuneParameters

Parameter struct used for creating Fine-tune jobs.

public struct CreateFineTuneParameters 

Initializers

init(trainingFile:validationFile:model:nEpochs:batchSize:learningRateMultiplier:promptLossWeight:computeClassificationMetrics:classificationNClasses:classificationPositiveClass:classificationBetas:suffix:)

public init(
        trainingFile: String,
        validationFile: String? = nil,
        model: String = "curie",
        nEpochs: Int = 4,
        batchSize: Int? = nil,
        learningRateMultiplier: Double? = nil,
        promptLossWeight: Double = 0.01,
        computeClassificationMetrics: Bool = false,
        classificationNClasses: Int? = nil,
        classificationPositiveClass: String? = nil,
        classificationBetas: [Double]? = nil,
        suffix: String? = nil
    ) 

Properties

trainingFile

The ID of an uploaded file that contains training data.

public var trainingFile: String

See upload file for how to upload a file.

Your dataset must be formatted as a JSONL file, where each training example is a JSON object with the keys "prompt" and "completion". Additionally, you must upload your file with the purpose fine-tune.

See the fine-tuning guide for more details.

validationFile

The ID of an uploaded file that contains validation data.

public var validationFile: String?

If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the fine-tuning results file. Your train and validation data should be mutually exclusive.

Your dataset must be formatted as a JSONL file, where each validation example is a JSON object with the keys "prompt" and "completion". Additionally, you must upload your file with the purpose fine-tune

See the fine-tuning guide for more details..

model

The name of the base model to fine-tune. You can select one of "ada", "babbage", "curie", "davinci", or a fine-tuned model created after 2022-04-21.

public var model: String

To learn more about these models, see the Models documentation.

nEpochs

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

public var nEpochs: Int

batchSize

The batch size to use for training.

public var batchSize: Int?

The batch size is the number of training examples used to train a single forward and backward pass.

By default, the batch size will be dynamically configured to be ~0.2% of the number of examples in the training set, capped at 256 - in general, we've found that larger batch sizes tend to work better for larger datasets.

learningRateMultiplier

The learning rate multiplier to use for training.

public var learningRateMultiplier: Double?

The fine-tuning learning rate is the original learning rate used for pretraining multiplied by this value.

By default, the learning rate multiplier is the 0.05, 0.1, or 0.2 depending on final batch_size (larger learning rates tend to perform better with larger batch sizes). We recommend experimenting with values in the range 0.02 to 0.2 to see what produces the best results.

promptLossWeight

The weight to use for loss on the prompt tokens.

public var promptLossWeight: Double

This controls how much the model tries to learn to generate the prompt (as compared to the completion which always has a weight of 1.0), and can add a stabilizing effect to training when completions are short.

If prompts are extremely long (relative to completions), it may make sense to reduce this weight so as to avoid over-prioritizing learning the prompt.

computeClassificationMetrics

If set, we calculate classification-specific metrics such as accuracy and F-1 score using the validation set at the end of every epoch.

public var computeClassificationMetrics: Bool

These metrics can be viewed in the results file.

In order to compute classification metrics, you must provide a validation_file. Additionally, you must specify classification_n_classes for multiclass classification or classification_positive_class for binary classification.

classificationNClasses

The number of classes in a classification task.

public var classificationNClasses: Int?

This parameter is required for multiclass classification.

classificationPositiveClass

The positive class in binary classification.

public var classificationPositiveClass: String?

This parameter is needed to generate precision, recall, and F1 metrics when doing binary classification.

classificationBetas

If this is provided, we calculate F-beta scores at the specified beta values.

public var classificationBetas: [Double]?

The F-beta score is a generalization of F-1 score. This is only used for binary classification.

With a beta of 1 (i.e. the F-1 score), precision and recall are given the same weight. A larger beta score puts more weight on recall and less on precision. A smaller beta score puts more weight on precision and less on recall.

suffix

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

public var suffix: String?

For example, a suffix of "custom-model-name" would produce a model name like ada:ft-your-org:custom-model-name-2022-02-15-04-21-04.

body

The body of the URL used for OpenAI API requests.

public var body: [String: Any]