@ralphschuler.ai function caller.index.<internal>.OpenAI.FineTunes.FineTune.Hyperparams

Interface: Hyperparams

FineTunes.FineTune.Hyperparams

The hyperparameters used for the fine-tuning job. See the fine-tuning guide for more details.

Table of contents

Properties

• batch_size
• classification_n_classes
• classification_positive_class
• compute_classification_metrics
• learning_rate_multiplier
• n_epochs
• prompt_loss_weight

Properties

batch_size

• batch_size: number

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.

Defined in

node_modules/openai/resources/fine-tunes.d.ts:116

---

classification_n_classes

• Optional classification_n_classes: number

The number of classes to use for computing classification metrics.

Defined in

node_modules/openai/resources/fine-tunes.d.ts:133

---

classification_positive_class

• Optional classification_positive_class: string

The positive class to use for computing classification metrics.

Defined in

node_modules/openai/resources/fine-tunes.d.ts:137

---

compute_classification_metrics

• Optional compute_classification_metrics: boolean

The classification metrics to compute using the validation dataset at the end of every epoch.

Defined in

node_modules/openai/resources/fine-tunes.d.ts:142

---

learning_rate_multiplier

• learning_rate_multiplier: number

The learning rate multiplier to use for training.

Defined in

node_modules/openai/resources/fine-tunes.d.ts:120

---

n_epochs

• n_epochs: number

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

Defined in

node_modules/openai/resources/fine-tunes.d.ts:125

---

prompt_loss_weight

• prompt_loss_weight: number

The weight to use for loss on the prompt tokens.

Defined in

node_modules/openai/resources/fine-tunes.d.ts:129