Skip to content
API Reference
Fine Tuning

Jobs

Create fine-tuning job
client.FineTuning.Jobs.New(ctx, body) (*FineTuningJob, error)
POST/fine_tuning/jobs
List fine-tuning jobs
client.FineTuning.Jobs.List(ctx, query) (*CursorPage[FineTuningJob], error)
GET/fine_tuning/jobs
Retrieve fine-tuning job
client.FineTuning.Jobs.Get(ctx, fineTuningJobID) (*FineTuningJob, error)
GET/fine_tuning/jobs/{fine_tuning_job_id}
List fine-tuning events
client.FineTuning.Jobs.ListEvents(ctx, fineTuningJobID, query) (*CursorPage[FineTuningJobEvent], error)
GET/fine_tuning/jobs/{fine_tuning_job_id}/events
Cancel fine-tuning
client.FineTuning.Jobs.Cancel(ctx, fineTuningJobID) (*FineTuningJob, error)
POST/fine_tuning/jobs/{fine_tuning_job_id}/cancel
Pause fine-tuning
client.FineTuning.Jobs.Pause(ctx, fineTuningJobID) (*FineTuningJob, error)
POST/fine_tuning/jobs/{fine_tuning_job_id}/pause
Resume fine-tuning
client.FineTuning.Jobs.Resume(ctx, fineTuningJobID) (*FineTuningJob, error)
POST/fine_tuning/jobs/{fine_tuning_job_id}/resume
ModelsExpand Collapse
type FineTuningJob struct{…}

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.

CreatedAt int64

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

Error FineTuningJobError

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.

FineTunedModel 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.

FinishedAt int64

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 FineTuningJobHyperparameters

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

BatchSize FineTuningJobHyperparametersBatchSizeUnionoptional

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:
type Auto string
int64
LearningRateMultiplier FineTuningJobHyperparametersLearningRateMultiplierUnionoptional

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

Accepts one of the following:
type Auto string
float64
NEpochs FineTuningJobHyperparametersNEpochsUnionoptional

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:
type Auto string
int64
Model string

The base model that is being fine-tuned.

Object FineTuningJob

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

OrganizationID string

The organization that owns the fine-tuning job.

ResultFiles []string

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

Seed int64

The seed used for the fine-tuning job.

Status FineTuningJobStatus

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:
const FineTuningJobStatusValidatingFiles FineTuningJobStatus = "validating_files"
const FineTuningJobStatusQueued FineTuningJobStatus = "queued"
const FineTuningJobStatusRunning FineTuningJobStatus = "running"
const FineTuningJobStatusSucceeded FineTuningJobStatus = "succeeded"
const FineTuningJobStatusFailed FineTuningJobStatus = "failed"
const FineTuningJobStatusCancelled FineTuningJobStatus = "cancelled"
TrainedTokens int64

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.

TrainingFile string

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

ValidationFile string

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

EstimatedFinish int64optional

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 []FineTuningJobWandbIntegrationObjectoptional

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

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 Metadataoptional

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 FineTuningJobMethodoptional

The method used for fine-tuning.

Type string

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

Accepts one of the following:
const FineTuningJobMethodTypeSupervised FineTuningJobMethodType = "supervised"
const FineTuningJobMethodTypeDpo FineTuningJobMethodType = "dpo"
const FineTuningJobMethodTypeReinforcement FineTuningJobMethodType = "reinforcement"
Dpo DpoMethodoptional

Configuration for the DPO fine-tuning method.

Reinforcement ReinforcementMethodoptional

Configuration for the reinforcement fine-tuning method.

Supervised SupervisedMethodoptional

Configuration for the supervised fine-tuning method.

type FineTuningJobEvent struct{…}

Fine-tuning job event object

ID string

The object identifier.

CreatedAt int64

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

Level FineTuningJobEventLevel

The log level of the event.

Accepts one of the following:
const FineTuningJobEventLevelInfo FineTuningJobEventLevel = "info"
const FineTuningJobEventLevelWarn FineTuningJobEventLevel = "warn"
const FineTuningJobEventLevelError FineTuningJobEventLevel = "error"
Message string

The message of the event.

Object FineTuningJobEvent

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

Data anyoptional

The data associated with the event.

Type FineTuningJobEventTypeoptional

The type of event.

Accepts one of the following:
const FineTuningJobEventTypeMessage FineTuningJobEventType = "message"
const FineTuningJobEventTypeMetrics FineTuningJobEventType = "metrics"
type FineTuningJobWandbIntegration struct{…}

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 stringoptional

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 stringoptional

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

Tags []stringoptional

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}".

type FineTuningJobWandbIntegrationObject struct{…}
Type Wandb

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

Wandb FineTuningJobWandbIntegration

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
client.FineTuning.Jobs.Checkpoints.List(ctx, fineTuningJobID, query) (*CursorPage[FineTuningJobCheckpoint], error)
GET/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints
ModelsExpand Collapse
type FineTuningJobCheckpoint struct{…}

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.

CreatedAt int64

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

FineTunedModelCheckpoint string

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

FineTuningJobID string

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

Metrics FineTuningJobCheckpointMetrics

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

FullValidLoss float64optional
FullValidMeanTokenAccuracy float64optional
Step float64optional
TrainLoss float64optional
TrainMeanTokenAccuracy float64optional
ValidLoss float64optional
ValidMeanTokenAccuracy float64optional
Object FineTuningJobCheckpoint

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

StepNumber int64

The step number that the checkpoint was created at.