OpenAI.FineTunes (openai_client v0.5.3)
Manage fine-tuning jobs to tailor a model to your specific training data.
Related guide: Fine-tune models
Link to this section Summary
Functions
Immediately cancel a fine-tune job
Creates a job that fine-tunes a specified model from a given dataset.
List your organization's fine-tuning jobs
Get fine-grained status updates for a fine-tune job.
Gets info about the fine-tuning job
Link to this section Types
Link to this type
create_params()
@type create_params() :: %{ :training_file => String.t(), optional(:validation_file) => String.t(), optional(:model) => String.t(), optional(:n_epochs) => integer(), optional(:batch_size) => integer(), optional(:learning_rate_multiplier) => float(), optional(:prompt_loss_weight) => float(), optional(:compute_classification_metrics) => boolean(), optional(:classification_n_classes) => integer(), optional(:classification_positive_class) => String.t(), optional(:classification_betas) => integer() | float(), optional(:suffix) => String.t() }
Link to this section Functions
Link to this function
cancel(client, id, opts \\ [])
@spec cancel(OpenAI.Client.t(), String.t(), Keyword.t()) :: OpenAI.Client.result()
Immediately cancel a fine-tune job
Link to this function
create(client, params, opts \\ [])
@spec create(OpenAI.Client.t(), create_params(), Keyword.t()) :: OpenAI.Client.result()
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.
Link to this function
list(client, opts \\ [])
@spec list(OpenAI.Client.t(), Keyword.t()) :: OpenAI.Client.result()
List your organization's fine-tuning jobs
Link to this function
list_events(client, id, opts \\ [])
@spec list_events(OpenAI.Client.t(), String.t(), Keyword.t()) :: OpenAI.Client.result()
Get fine-grained status updates for a fine-tune job.
Link to this function
retrieve(client, id, opts \\ [])
@spec retrieve(OpenAI.Client.t(), String.t(), Keyword.t()) :: OpenAI.Client.result()
Gets info about the fine-tuning job