Create fine-tuning job

POSThttps:/api.openai.com/v1/fine_tuning/jobs

Creates a fine-tuning job which begins the process of creating a new 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

Request body

model
string
The name of the model to fine-tune. You can select one of the supported models.
- model
  string
  Required
- model
  string
  Required
  babbage-002
  string
  davinci-002
  string
  gpt-3.5-turbo
  string
  gpt-4o-mini
  string
training_file
string
Required
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. Additionally, you must upload your file with the purpose fine-tune.
The contents of the file should differ depending on if the model uses the chat, completions format, or if the fine-tuning method uses the preference format.
See the fine-tuning guide for more details.
hyperparameters
object
Deprecated
The hyperparameters used for the fine-tuning job. This value is now deprecated in favor of method, and should be passed in under the method parameter.
- batch_size
  string or integer
  Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
  batch_size
  string
  auto
  string
  batch_size
  integer
- learning_rate_multiplier
  string or number
  Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.
  learning_rate_multiplier
  string
  auto
  string
  learning_rate_multiplier
  number
- n_epochs
  string or integer
  The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.
  n_epochs
  string
  auto
  string
  n_epochs
  integer
suffix
string or null
Defaults: null
A string of up to 64 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 ft:gpt-4o-mini:openai:custom-model-name:7p4lURel.
validation_file
string or null
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. The same data should not be present in both train and validation files.
Your dataset must be formatted as a JSONL file. You must upload your file with the purpose fine-tune.
See the fine-tuning guide for more details.
integrations
array or null
A list of integrations to enable for your fine-tuning job.
- items
  object
  type
  string
  The type of integration to enable. Currently, only "wandb" (Weights and Biases) is supported.
  type
  string
  Required
  wandb
  string
  wandb
  object
  Required
  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
  Required
  The name of the project that the new run will be created under.
  name
  string or null
  A display name to set for the run. If not set, we will use the Job ID as the name.
  entity
  string or null
  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.
  tags
  array
  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}".
  items
  string
seed
integer or null
The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed is not specified, one will be generated for you.
method
object
The method used for fine-tuning.
- type
  string
  The type of method. Is either supervised or dpo.
  supervised
  string
  dpo
  string
- supervised
  object
  Configuration for the supervised fine-tuning method.
  hyperparameters
  object
  The hyperparameters used for the fine-tuning job.
  batch_size
  string or integer
  Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
  batch_size
  string
  auto
  string
  batch_size
  integer
  learning_rate_multiplier
  string or number
  Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.
  learning_rate_multiplier
  string
  auto
  string
  learning_rate_multiplier
  number
  n_epochs
  string or integer
  The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.
  n_epochs
  string
  auto
  string
  n_epochs
  integer
- dpo
  object
  Configuration for the DPO fine-tuning method.
  hyperparameters
  object
  The hyperparameters used for the fine-tuning job.
  beta
  string or number
  The beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model.
  beta
  string
  auto
  string
  beta
  number
  batch_size
  string or integer
  Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
  batch_size
  string
  auto
  string
  batch_size
  integer
  learning_rate_multiplier
  string or number
  Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.
  learning_rate_multiplier
  string
  auto
  string
  learning_rate_multiplier
  number
  n_epochs
  string or integer
  The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.
  n_epochs
  string
  auto
  string
  n_epochs
  integer
metadata
object or null
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.

Response

A fine-tuning.job object.

Example request

1curl https://api.openai.com/v1/fine_tuning/jobs \
2  -H "Content-Type: application/json" \
3  -H "Authorization: Bearer $OPENAI_API_KEY" \
4  -d '{
5    "training_file": "file-BK7bzQj3FfZFXr7DbL6xJwfo",
6    "model": "gpt-4o-mini"
7  }'

Example response

1{
2  "object": "fine_tuning.job",
3  "id": "ftjob-abc123",
4  "model": "gpt-4o-mini-2024-07-18",
5  "created_at": 1721764800,
6  "fine_tuned_model": null,
7  "organization_id": "org-123",
8  "result_files": [],
9  "status": "queued",
10  "validation_file": null,
11  "training_file": "file-abc123",
12  "method": {
13    "type": "supervised",
14    "supervised": {
15      "hyperparameters": {
16        "batch_size": "auto",
17        "learning_rate_multiplier": "auto",
18        "n_epochs": "auto",
19      }
20    }
21  },
22  "metadata": null
23}

Built with