FineTuneRequest class
Constructors
FineTuneRequest ({@JsonKey(name: 'training_file') required String trainingFile , @JsonKey(name: 'validation_file') String ?validationFile , String ?model , @JsonKey(name: 'n_epochs') int ?nEpochs , @JsonKey(name: 'batch_size') int ?batchSize , @JsonKey(name: 'learning_rate_multiplier') double ?learningRateMultiplier , @JsonKey(name: 'prompt_loss_weight') double ?promptLossWeight , @JsonKey(name: 'compute_classification_metrics') bool ?computeClassificationMetrics , @JsonKey(name: 'classification_n_classes') int ?classificationNClasses , @JsonKey(name: 'classification_positive_class') String ?classificationPositiveClass , @JsonKey(name: 'classification_betas') List <double ?classificationBetas , String ?suffix
const
factory
FineTuneRequest.fromJson (Map <String Object ? json
factory
Properties
batchSize → int ?
The batch size to use for training. The batch size is the number of
training examples used to train a single forward and backward pass.
no setter inherited
classificationBetas → List <double ?
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.
no setter inherited
classificationNClasses → int ?
The number of classes in a classification task.
no setter inherited
classificationPositiveClass → String ?
The positive class in binary classification.
no setter inherited
computeClassificationMetrics → 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.
no setter inherited
copyWith → $FineTuneRequestCopyWith<FineTuneRequest
no setter inherited
hashCode → int
The hash code for this object.
no setter inherited
learningRateMultiplier → double ?
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.
no setter inherited
model → String ?
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.
no setter inherited
nEpochs → int ?
The number of epochs to train the model for. An epoch refers to one
full cycle through the training dataset.
no setter inherited
promptLossWeight → double ?
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.
no setter inherited
runtimeType → Type
A representation of the runtime type of the object.
no setter inherited
suffix → String ?
A string of up to 40 characters that will be added to your fine-tuned
model name.
no setter inherited
trainingFile → String
The ID of an uploaded file that contains training data.
See upload file
for how to upload a file.
no setter inherited
validationFile → String ?
The ID of an uploaded file that contains validation data.
no setter inherited
unofficial_open_api 1.0.3 