pub struct CreateFineTuneParameters {
pub training_file: String,
pub validation_file: Option<String>,
pub model: Option<String>,
pub epochs: Option<u32>,
pub batch_size: Option<u32>,
pub learning_rate_multiplier: Option<f32>,
pub prompt_loss_weight: Option<f32>,
pub compute_classification_metrics: Option<bool>,
pub classification_n_classes: Option<u32>,
pub classification_positive_class: Option<String>,
pub classification_beta: Option<f32>,
pub suffix: Option<String>,
}
Fields§
§training_file: String
The ID of an uploaded file that contains training data.
validation_file: Option<String>
The ID of an uploaded file that contains validation data.
model: Option<String>
The name of the base model to use for fine-tuning.
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<f32>
The learning rate multiplier to use for training. The fine-tuning learning rate is the original learning rate used for pretraining multiplied by this value.
prompt_loss_weight: Option<f32>
The weight to use for loss on the prompt tokens. 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.
compute_classification_metrics: Option<bool>
If set, we calculate classification-specific metrics such as accuracy and F-1 score using the validation set at the end of every epoch. 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.
classification_n_classes: Option<u32>
The number of classes in a classification task.
This parameter is required for multiclass classification.
classification_positive_class: Option<String>
The positive class in binary classification.
This parameter is needed to generate precision, recall, and F1 metrics when doing binary classification.
classification_beta: Option<f32>
If this is provided, we calculate F-beta scores at the specified beta values. 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: Option<String>
A string of up to 40 characters that will be added to your fine-tuned model name.
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.