Skip to content
API Reference
Fine Tuning

Jobs

Create fine-tuning job
fine_tuning.jobs.create(**kwargs) -> FineTuningJob { id, created_at, error, 16 more }
POST/fine_tuning/jobs
List fine-tuning jobs
fine_tuning.jobs.list(**kwargs) -> CursorPage<FineTuningJob { id, created_at, error, 16 more } >
GET/fine_tuning/jobs
Retrieve fine-tuning job
fine_tuning.jobs.retrieve(fine_tuning_job_id) -> FineTuningJob { id, created_at, error, 16 more }
GET/fine_tuning/jobs/{fine_tuning_job_id}
List fine-tuning events
fine_tuning.jobs.list_events(fine_tuning_job_id, **kwargs) -> CursorPage<FineTuningJobEvent { id, created_at, level, 4 more } >
GET/fine_tuning/jobs/{fine_tuning_job_id}/events
Cancel fine-tuning
fine_tuning.jobs.cancel(fine_tuning_job_id) -> FineTuningJob { id, created_at, error, 16 more }
POST/fine_tuning/jobs/{fine_tuning_job_id}/cancel
Pause fine-tuning
fine_tuning.jobs.pause(fine_tuning_job_id) -> FineTuningJob { id, created_at, error, 16 more }
POST/fine_tuning/jobs/{fine_tuning_job_id}/pause
Resume fine-tuning
fine_tuning.jobs.resume(fine_tuning_job_id) -> FineTuningJob { id, created_at, error, 16 more }
POST/fine_tuning/jobs/{fine_tuning_job_id}/resume
ModelsExpand Collapse
class FineTuningJob { id, created_at, error, 16 more }

The fine_tuning.job object represents a fine-tuning job that has been created through the API.

id: String

The object identifier, which can be referenced in the API endpoints.

created_at: Integer

The Unix timestamp (in seconds) for when the fine-tuning job was created.

error: { code, message, param}

For fine-tuning jobs that have failed, this will contain more information on the cause of the failure.

code: String

A machine-readable error code.

message: String

A human-readable error message.

param: String

The parameter that was invalid, usually training_file or validation_file. This field will be null if the failure was not parameter-specific.

fine_tuned_model: String

The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running.

finished_at: Integer

The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running.

hyperparameters: { batch_size, learning_rate_multiplier, n_epochs}

The hyperparameters used for the fine-tuning job. This value will only be returned when running supervised jobs.

batch_size: :auto | Integer

Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

Accepts one of the following:
BatchSize = :auto
Integer
learning_rate_multiplier: :auto | Float

Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

Accepts one of the following:
LearningRateMultiplier = :auto
Float
n_epochs: :auto | Integer

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

Accepts one of the following:
NEpochs = :auto
Integer
model: String

The base model that is being fine-tuned.

object: :"fine_tuning.job"

The object type, which is always "fine_tuning.job".

organization_id: String

The organization that owns the fine-tuning job.

result_files: Array[String]

The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the Files API.

seed: Integer

The seed used for the fine-tuning job.

status: :validating_files | :queued | :running | 3 more

The current status of the fine-tuning job, which can be either validating_files, queued, running, succeeded, failed, or cancelled.

Accepts one of the following:
:validating_files
:queued
:running
:succeeded
:failed
:cancelled
trained_tokens: Integer

The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running.

training_file: String

The file ID used for training. You can retrieve the training data with the Files API.

validation_file: String

The file ID used for validation. You can retrieve the validation results with the Files API.

estimated_finish: Integer

The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job is not running.

integrations: Array[FineTuningJobWandbIntegrationObject { type, wandb } ]

A list of integrations to enable for this fine-tuning job.

type: :wandb

The type of the integration being enabled for the fine-tuning job

wandb: FineTuningJobWandbIntegration { project, entity, name, tags }

The settings for your integration with Weights and Biases. This payload specifies the project that metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags to your run, and set a default entity (team, username, etc) to be associated with your run.

metadata: Metadata

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

method_: { type, dpo, reinforcement, supervised}

The method used for fine-tuning.

type: :supervised | :dpo | :reinforcement

The type of method. Is either supervised, dpo, or reinforcement.

Accepts one of the following:
:supervised
:dpo
:reinforcement
dpo: DpoMethod { hyperparameters }

Configuration for the DPO fine-tuning method.

reinforcement: ReinforcementMethod { grader, hyperparameters }

Configuration for the reinforcement fine-tuning method.

supervised: SupervisedMethod { hyperparameters }

Configuration for the supervised fine-tuning method.

class FineTuningJobEvent { id, created_at, level, 4 more }

Fine-tuning job event object

id: String

The object identifier.

created_at: Integer

The Unix timestamp (in seconds) for when the fine-tuning job was created.

level: :info | :warn | :error

The log level of the event.

Accepts one of the following:
:info
:warn
:error
message: String

The message of the event.

object: :"fine_tuning.job.event"

The object type, which is always "fine_tuning.job.event".

data: untyped

The data associated with the event.

type: :message | :metrics

The type of event.

Accepts one of the following:
:message
:metrics
class FineTuningJobWandbIntegration { project, entity, name, tags }

The settings for your integration with Weights and Biases. This payload specifies the project that metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags to your run, and set a default entity (team, username, etc) to be associated with your run.

project: String

The name of the project that the new run will be created under.

entity: String

The entity to use for the run. This allows you to set the team or username of the WandB user that you would like associated with the run. If not set, the default entity for the registered WandB API key is used.

name: String

A display name to set for the run. If not set, we will use the Job ID as the name.

tags: Array[String]

A list of tags to be attached to the newly created run. These tags are passed through directly to WandB. Some default tags are generated by OpenAI: "openai/finetune", "openai/{base-model}", "openai/{ftjob-abcdef}".

class FineTuningJobWandbIntegrationObject { type, wandb }
type: :wandb

The type of the integration being enabled for the fine-tuning job

wandb: FineTuningJobWandbIntegration { project, entity, name, tags }

The settings for your integration with Weights and Biases. This payload specifies the project that metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags to your run, and set a default entity (team, username, etc) to be associated with your run.

JobsCheckpoints

List fine-tuning checkpoints
fine_tuning.jobs.checkpoints.list(fine_tuning_job_id, **kwargs) -> CursorPage<FineTuningJobCheckpoint { id, created_at, fine_tuned_model_checkpoint, 4 more } >
GET/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints
ModelsExpand Collapse
class FineTuningJobCheckpoint { id, created_at, fine_tuned_model_checkpoint, 4 more }

The fine_tuning.job.checkpoint object represents a model checkpoint for a fine-tuning job that is ready to use.

id: String

The checkpoint identifier, which can be referenced in the API endpoints.

created_at: Integer

The Unix timestamp (in seconds) for when the checkpoint was created.

fine_tuned_model_checkpoint: String

The name of the fine-tuned checkpoint model that is created.

fine_tuning_job_id: String

The name of the fine-tuning job that this checkpoint was created from.

metrics: { full_valid_loss, full_valid_mean_token_accuracy, step, 4 more}

Metrics at the step number during the fine-tuning job.

full_valid_loss: Float
full_valid_mean_token_accuracy: Float
step: Float
train_loss: Float
train_mean_token_accuracy: Float
valid_loss: Float
valid_mean_token_accuracy: Float
object: :"fine_tuning.job.checkpoint"

The object type, which is always "fine_tuning.job.checkpoint".

step_number: Integer

The step number that the checkpoint was created at.