NAME

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

DESCRIPTION

This document describes the API endpoint at /fine_tuning/jobs.

See the examples/ directory in the distribution for examples of how to use this.

GET /fine_tuning/jobs

List your organization's fine-tuning jobs

Operation ID

listPaginatedFineTuningJobs

$client->listPaginatedFineTuningJobs( ... );

Parameters

• after (in query) (Optional) - Identifier for the last job from the previous pagination request. Type: string

• limit (in query) (Optional) - Number of fine-tuning jobs to retrieve. Type: integer

  Default: 20

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

  Type: object

Responses

Status Code: 200

OK

Content Types:

• application/json

  Example:

  {
     "data" : [
        {
           "method" : {
              "dpo" : {
                 "hyperparameters" : null
              },
              "supervised" : {
                 "hyperparameters" : null
              }
           },
           "result_files" : [
              "file-abc123"
           ],
           "error" : null,
           "integrations" : [
              null
           ],
           "hyperparameters" : null
        }
     ]
  }

POST /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](/docs/guides/fine-tuning)

Operation ID

createFineTuningJob

$client->createFineTuningJob( ... );

Request Body

Content Type: application/json

Example:

{
   "integrations" : [
      {
         "wandb" : {
            "tags" : [
               "custom-tag"
            ],
            "project" : "my-wandb-project"
         }
      }
   ],
   "hyperparameters" : null,
   "validation_file" : "file-abc123",
   "seed" : 42,
   "model" : "gpt-4o-mini",
   "training_file" : "file-abc123",
   "method" : {
      "dpo" : {
         "hyperparameters" : null
      },
      "supervised" : {
         "hyperparameters" : null
      }
   }
}

Responses

Status Code: 200

OK

Content Types:

• application/json

  Example:

  {
     "hyperparameters" : null,
     "integrations" : [
        null
     ],
     "error" : null,
     "result_files" : [
        "file-abc123"
     ],
     "method" : {
        "dpo" : {
           "hyperparameters" : null
        },
        "supervised" : {
           "hyperparameters" : null
        }
     }
  }

SEE ALSO

OpenAPI::Client::OpenAI::Path

COPYRIGHT AND LICENSE

Copyright (C) 2023-2025 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.

cpanm OpenAPI::Client::OpenAI

perl -MCPAN -e shell
install OpenAPI::Client::OpenAI