/ 
OpenAPI-Client-OpenAI-0.28
⭐ Starred 7 / OpenAPI::Client::OpenAI::Path::fine_tuning-jobs

NAME

OpenAPI::Client::OpenAI::Path::fine_tuning-jobs - Documentation for the /fine_tuning/jobs path.

OPERATIONS

GET /fine_tuning/jobs

listPaginatedFineTuningJobs

$client->list_paginated_fine_tuning_jobs({
    body => { ... },
});

List your organization's fine-tuning jobs

Path/query parameters

  • after (in query, optional, string) - Identifier for the last job from the previous pagination request.

  • limit (in query, optional, integer) - Number of fine-tuning jobs to retrieve.

    Default: 20

  • metadata (in query, optional, object) - Optional metadata filter. To filter, use the syntax metadata[k]=v . Alternatively, set metadata=null to indicate no metadata.

Responses

200 - OK

Content-Type: application/json

Example:

{
   "data" : [
      "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"davinci-002\",\n  \"created_at\": 1692661014,\n  \"finished_at\": 1692661190,\n  \"fine_tuned_model\": \"ft:davinci-002:my-org:custom_suffix:7q8mpxmy\",\n  \"organization_id\": \"org-123\",\n  \"result_files\": [\n      \"file-abc123\"\n  ],\n  \"status\": \"succeeded\",\n  \"validation_file\": null,\n  \"training_file\": \"file-abc123\",\n  \"hyperparameters\": {\n      \"n_epochs\": 4,\n      \"batch_size\": 1,\n      \"learning_rate_multiplier\": 1.0\n  },\n  \"trained_tokens\": 5768,\n  \"integrations\": [],\n  \"seed\": 0,\n  \"estimated_finish\": 0,\n  \"method\": {\n    \"type\": \"supervised\",\n    \"supervised\": {\n      \"hyperparameters\": {\n        \"n_epochs\": 4,\n        \"batch_size\": 1,\n        \"learning_rate_multiplier\": 1.0\n      }\n    }\n  },\n  \"metadata\": {\n    \"key\": \"value\"\n  }\n}\n"
   ],
   "has_more" : false,
   "object" : "list"
}

POST /fine_tuning/jobs

createFineTuningJob

$client->create_fine_tuning_job({
    body => { ... },
});

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

Content-Type: application/json

Example:

"{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"created_at\": 1721764800,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-123\",\n  \"result_files\": [],\n  \"status\": \"queued\",\n  \"validation_file\": null,\n  \"training_file\": \"file-abc123\",\n  \"method\": {\n    \"type\": \"supervised\",\n    \"supervised\": {\n      \"hyperparameters\": {\n        \"batch_size\": \"auto\",\n        \"learning_rate_multiplier\": \"auto\",\n        \"n_epochs\": \"auto\",\n      }\n    }\n  },\n  \"metadata\": null\n}\n"

Responses

200 - OK

Content-Type: application/json

Example:

"{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"created_at\": 1721764800,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-123\",\n  \"result_files\": [],\n  \"status\": \"queued\",\n  \"validation_file\": null,\n  \"training_file\": \"file-abc123\",\n  \"method\": {\n    \"type\": \"supervised\",\n    \"supervised\": {\n      \"hyperparameters\": {\n        \"batch_size\": \"auto\",\n        \"learning_rate_multiplier\": \"auto\",\n        \"n_epochs\": \"auto\",\n      }\n    }\n  },\n  \"metadata\": null\n}\n"

SCHEMAS

CreateFineTuningJobRequest

Properties:

  • hyperparameters (object) - 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.

  • integrations (array of object) - A list of integrations to enable for your fine-tuning job.

  • metadata (Metadata)

    See "Metadata" below for shape.

  • method (FineTuneMethod)

    See "FineTuneMethod" below for shape.

  • model (anyOf, required) - The name of the model to fine-tune. You can select one of the supported models .

  • seed (integer) - 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.

  • suffix (string) - 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 .

    Default: null

  • 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.

  • validation_file (string) - 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.

FineTuneDPOHyperparameters

Properties:

  • batch_size (oneOf) - Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

    Default: auto

  • beta (oneOf) - The beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model.

    Default: auto

  • learning_rate_multiplier (oneOf) - Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

    Default: auto

  • n_epochs (oneOf) - The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

    Default: auto

FineTuneDPOMethod

Properties:

FineTuneMethod

Properties:

  • dpo (FineTuneDPOMethod)

    See "FineTuneDPOMethod" below for shape.

  • reinforcement (FineTuneReinforcementMethod)

    See "FineTuneReinforcementMethod" below for shape.

  • supervised (FineTuneSupervisedMethod)

    See "FineTuneSupervisedMethod" below for shape.

  • type (string, required) - The type of method. Is either supervised , dpo , or reinforcement .

    Allowed values: supervised, dpo, reinforcement

FineTuneReinforcementHyperparameters

Properties:

  • batch_size (oneOf) - Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

    Default: auto

  • compute_multiplier (oneOf) - Multiplier on amount of compute used for exploring search space during training.

    Default: auto

  • eval_interval (oneOf) - The number of training steps between evaluation runs.

    Default: auto

  • eval_samples (oneOf) - Number of evaluation samples to generate per training step.

    Default: auto

  • learning_rate_multiplier (oneOf) - Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

    Default: auto

  • n_epochs (oneOf) - The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

    Default: auto

  • reasoning_effort (string) - Level of reasoning effort.

    Allowed values: default, low, medium, high

    Default: default

FineTuneReinforcementMethod

Properties:

FineTuneSupervisedHyperparameters

Properties:

  • batch_size (oneOf) - Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

    Default: auto

  • learning_rate_multiplier (oneOf) - Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

    Default: auto

  • n_epochs (oneOf) - The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

    Default: auto

FineTuneSupervisedMethod

Properties:

FineTuningJob

Properties:

  • created_at (integer, required) - The Unix timestamp (in seconds) for when the fine-tuning job was created.

  • error (anyOf, required)

  • estimated_finish (anyOf)

  • fine_tuned_model (anyOf, required)

  • finished_at (anyOf, required)

  • hyperparameters (object, required) - The hyperparameters used for the fine-tuning job. This value will only be returned when running supervised jobs.

  • id (string, required) - The object identifier, which can be referenced in the API endpoints.

  • integrations (anyOf)

  • metadata (Metadata)

    See "Metadata" below for shape.

  • method (FineTuneMethod)

    See "FineTuneMethod" below for shape.

  • model (string, required) - The base model that is being fine-tuned.

  • object (string, required) - The object type, which is always "fine_tuning.job".

    Allowed values: fine_tuning.job

  • organization_id (string, required) - The organization that owns the fine-tuning job.

  • result_files (array of string, required) - The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the Files API .

  • seed (integer, required) - The seed used for the fine-tuning job.

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

    Allowed values: validating_files, queued, running, succeeded, failed, cancelled

  • trained_tokens (anyOf, required)

  • training_file (string, required) - The file ID used for training. You can retrieve the training data with the Files API .

  • validation_file (anyOf, required)

ListPaginatedFineTuningJobsResponse

Properties:

  • data (array of FineTuningJob, required)

  • has_more (boolean, required)

  • object (string, required)

    Allowed values: list

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.

SEE ALSO

OpenAPI::Client::OpenAI::Path

COPYRIGHT AND LICENSE

Copyright (C) 2023-2026 by Nelson Ferraz

This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.14.0 or, at your option, any later version of Perl 5 you may have available.