@spec cancel_fine_tune(String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t()
) ::
  {:ok, ExOpenAI.Components.FineTune.t()} | {:error, any()}

Immediately cancel a fine-tune job.

Endpoint: https://api.openai.com/v1/fine-tunes/{fine_tune_id}/cancel

Method: POST

Docs: https://platform.openai.com/docs/api-reference/fine_tunes

Required Arguments:

• fine_tune_id

Example: ft-AF1WoRqd3aJAHsqc9NY7iL8F

Optional Arguments:

• openai_api_key: OpenAI API key to pass directly. If this is specified, it will override the api_key config value.

• openai_organization_key: OpenAI API key to pass directly. If this is specified, it will override the organization_key config value.

@spec create_fine_tune(String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  validation_file: String.t(),
  suffix: String.t(),
  prompt_loss_weight: float(),
  model: (:davinci | :curie | :babbage | :ada) | String.t(),
  learning_rate_multiplier: float(),
  hyperparameters: %{n_epochs: integer() | :auto},
  compute_classification_metrics: boolean(),
  classification_positive_class: String.t(),
  classification_n_classes: integer(),
  classification_betas: [float()],
  batch_size: integer(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.FineTune.t()} | {:error, any()}

Creates a job that fine-tunes a specified model from a given dataset.

Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete.

Learn more about fine-tuning

Endpoint: https://api.openai.com/v1/fine-tunes

Method: POST

Docs: https://platform.openai.com/docs/api-reference/fine_tunes

Required Arguments:

• training_file: The ID of an uploaded file that contains training data.

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.

Example: file-abc123

Optional Arguments:

• stream_to: PID or function of where to stream content to

• batch_size: 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.

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.

• classification_betas: 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.

Example: [0.6, 1, 1.5, 2]

• classification_n_classes: The number of classes in a classification task.

This parameter is required for multiclass classification.

• classification_positive_class: The positive class in binary classification.

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

• compute_classification_metrics: 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.

• hyperparameters: The hyperparameters used for the fine-tuning job.

• learning_rate_multiplier: 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.

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.

• 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 and before 2023-08-22. To learn more about these models, see the Models documentation.

• prompt_loss_weight: 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.

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.

• suffix: 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.

• validation_file: The ID of an uploaded file that contains validation data.

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.

Example: "file-abc123"

• openai_api_key: OpenAI API key to pass directly. If this is specified, it will override the api_key config value.

• openai_organization_key: OpenAI API key to pass directly. If this is specified, it will override the organization_key config value.

@spec list_fine_tune_events(String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t(),
  stream: boolean(),
  stream_to: (... -> any()) | pid()
) :: {:ok, ExOpenAI.Components.ListFineTuneEventsResponse.t()} | {:error, any()}

Get fine-grained status updates for a fine-tune job.

Endpoint: https://api.openai.com/v1/fine-tunes/{fine_tune_id}/events

Method: GET

Docs: https://platform.openai.com/docs/api-reference/fine_tunes

Required Arguments:

• fine_tune_id

Example: ft-AF1WoRqd3aJAHsqc9NY7iL8F

Optional Arguments:

• stream_to: PID or function of where to stream content to

• stream

• openai_api_key: OpenAI API key to pass directly. If this is specified, it will override the api_key config value.

• openai_organization_key: OpenAI API key to pass directly. If this is specified, it will override the organization_key config value.

@spec list_fine_tunes(openai_organization_key: String.t(), openai_api_key: String.t()) ::
  {:ok, ExOpenAI.Components.ListFineTunesResponse.t()} | {:error, any()}

List your organization's fine-tuning jobs

Endpoint: https://api.openai.com/v1/fine-tunes

Method: GET

Docs: https://platform.openai.com/docs/api-reference/fine_tunes

Required Arguments:

Optional Arguments:

• openai_api_key: OpenAI API key to pass directly. If this is specified, it will override the api_key config value.

• openai_organization_key: OpenAI API key to pass directly. If this is specified, it will override the organization_key config value.

@spec retrieve_fine_tune(String.t(),
  openai_organization_key: String.t(),
  openai_api_key: String.t()
) ::
  {:ok, ExOpenAI.Components.FineTune.t()} | {:error, any()}

Gets info about the fine-tune job.

Learn more about fine-tuning

Endpoint: https://api.openai.com/v1/fine-tunes/{fine_tune_id}

Method: GET

Docs: https://platform.openai.com/docs/api-reference/fine_tunes

Required Arguments:

• fine_tune_id

Example: ft-AF1WoRqd3aJAHsqc9NY7iL8F

Optional Arguments:

• openai_api_key: OpenAI API key to pass directly. If this is specified, it will override the api_key config value.

• openai_organization_key: OpenAI API key to pass directly. If this is specified, it will override the organization_key config value.