Class: OpenAI::Resources::FineTuning::Jobs

Inherits:
Object
  • Object
show all
Defined in:
lib/openai/resources/fine_tuning/jobs.rb,
lib/openai/resources/fine_tuning/jobs/checkpoints.rb,
sig/openai/resources/fine_tuning/jobs.rbs,
sig/openai/resources/fine_tuning/jobs/checkpoints.rbs

Overview

Manage fine-tuning jobs to tailor a model to your specific training data.

Defined Under Namespace

Classes: Checkpoints

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(client:) ⇒ Jobs

This method is part of a private API. You should avoid using this method if possible, as it may be removed or be changed in the future.

Returns a new instance of Jobs.

Parameters:



267
268
269
270
 
# File 'lib/openai/resources/fine_tuning/jobs.rb', line 267

def initialize(client:)
  @client = client
  @checkpoints = OpenAI::Resources::FineTuning::Jobs::Checkpoints.new(client: client)
end

Instance Attribute Details

#checkpoints ⇒ OpenAI::Resources::FineTuning::Jobs::Checkpoints (readonly)

Manage fine-tuning jobs to tailor a model to your specific training data.

Returns:



10
11
12
 
# File 'lib/openai/resources/fine_tuning/jobs.rb', line 10

def checkpoints
  @checkpoints
end

Instance Method Details

#cancel(fine_tuning_job_id, request_options: {}) ⇒ OpenAI::Models::FineTuning::FineTuningJob

Immediately cancel a fine-tune job.

Parameters:

  • fine_tuning_job_id (String) —

    The ID of the fine-tuning job to cancel.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



178
179
180
181
182
183
184
185
186
 
# File 'lib/openai/resources/fine_tuning/jobs.rb', line 178

def cancel(fine_tuning_job_id, params = {})
  @client.request(
    method: :post,
    path: ["fine_tuning/jobs/%1$s/cancel", fine_tuning_job_id],
    model: OpenAI::FineTuning::FineTuningJob,
    security: {bearer_auth: true},
    options: params[:request_options]
  )
end

#create(model:, training_file:, hyperparameters: nil, integrations: nil, metadata: nil, method_: nil, seed: nil, suffix: nil, validation_file: nil, request_options: {}) ⇒ OpenAI::Models::FineTuning::FineTuningJob

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

Parameters:

  • model (String, Symbol, OpenAI::Models::FineTuning::JobCreateParams::Model) —

    The name of the model to fine-tune. You can select one of the supported models.

  • training_file (String) —

    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 (OpenAI::Models::FineTuning::JobCreateParams::Hyperparameters) —

    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<OpenAI::Models::FineTuning::JobCreateParams::Integration>, nil) —

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

  • metadata (Hash{Symbol=>String}, nil) —

    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_ (OpenAI::Models::FineTuning::JobCreateParams::Method) —

    The method used for fine-tuning.

  • seed (Integer, nil) —

    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, nil) —

    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, nil) —

    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.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



97
98
99
100
101
102
103
104
105
106
107
 
# File 'lib/openai/resources/fine_tuning/jobs.rb', line 97

def create(params)
  parsed, options = OpenAI::FineTuning::JobCreateParams.dump_request(params)
  @client.request(
    method: :post,
    path: "fine_tuning/jobs",
    body: parsed,
    model: OpenAI::FineTuning::FineTuningJob,
    security: {bearer_auth: true},
    options: options
  )
end

#list(after: nil, limit: nil, metadata: nil, request_options: {}) ⇒ OpenAI::Internal::CursorPage<OpenAI::Models::FineTuning::FineTuningJob>

List your organization's fine-tuning jobs

Parameters:

  • after (String) —

    Identifier for the last job from the previous pagination request.

  • limit (Integer) —

    Number of fine-tuning jobs to retrieve.

  • metadata (Hash{Symbol=>String}, nil) —

    Optional metadata filter. To filter, use the syntax metadata[k]=v. Alternatively, set metadata=null to indicate no metadata.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



152
153
154
155
156
157
158
159
160
161
162
163
164
 
# File 'lib/openai/resources/fine_tuning/jobs.rb', line 152

def list(params = {})
  parsed, options = OpenAI::FineTuning::JobListParams.dump_request(params)
  query = OpenAI::Internal::Util.encode_query_params(parsed)
  @client.request(
    method: :get,
    path: "fine_tuning/jobs",
    query: query,
    page: OpenAI::Internal::CursorPage,
    model: OpenAI::FineTuning::FineTuningJob,
    security: {bearer_auth: true},
    options: options
  )
end

#list_events(fine_tuning_job_id, after: nil, limit: nil, request_options: {}) ⇒ OpenAI::Internal::CursorPage<OpenAI::Models::FineTuning::FineTuningJobEvent>

Get status updates for a fine-tuning job.

Parameters:

  • fine_tuning_job_id (String) —

    The ID of the fine-tuning job to get events for.

  • after (String) —

    Identifier for the last event from the previous pagination request.

  • limit (Integer) —

    Number of events to retrieve.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



206
207
208
209
210
211
212
213
214
215
216
217
218
 
# File 'lib/openai/resources/fine_tuning/jobs.rb', line 206

def list_events(fine_tuning_job_id, params = {})
  parsed, options = OpenAI::FineTuning::JobListEventsParams.dump_request(params)
  query = OpenAI::Internal::Util.encode_query_params(parsed)
  @client.request(
    method: :get,
    path: ["fine_tuning/jobs/%1$s/events", fine_tuning_job_id],
    query: query,
    page: OpenAI::Internal::CursorPage,
    model: OpenAI::FineTuning::FineTuningJobEvent,
    security: {bearer_auth: true},
    options: options
  )
end

#pause(fine_tuning_job_id, request_options: {}) ⇒ OpenAI::Models::FineTuning::FineTuningJob

Pause a fine-tune job.

Parameters:

  • fine_tuning_job_id (String) —

    The ID of the fine-tuning job to pause.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



232
233
234
235
236
237
238
239
240
 
# File 'lib/openai/resources/fine_tuning/jobs.rb', line 232

def pause(fine_tuning_job_id, params = {})
  @client.request(
    method: :post,
    path: ["fine_tuning/jobs/%1$s/pause", fine_tuning_job_id],
    model: OpenAI::FineTuning::FineTuningJob,
    security: {bearer_auth: true},
    options: params[:request_options]
  )
end

#resume(fine_tuning_job_id, request_options: {}) ⇒ OpenAI::Models::FineTuning::FineTuningJob

Resume a fine-tune job.

Parameters:

  • fine_tuning_job_id (String) —

    The ID of the fine-tuning job to resume.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



254
255
256
257
258
259
260
261
262
 
# File 'lib/openai/resources/fine_tuning/jobs.rb', line 254

def resume(fine_tuning_job_id, params = {})
  @client.request(
    method: :post,
    path: ["fine_tuning/jobs/%1$s/resume", fine_tuning_job_id],
    model: OpenAI::FineTuning::FineTuningJob,
    security: {bearer_auth: true},
    options: params[:request_options]
  )
end

#retrieve(fine_tuning_job_id, request_options: {}) ⇒ OpenAI::Models::FineTuning::FineTuningJob

Get info about a fine-tuning job.

Learn more about fine-tuning

Parameters:

  • fine_tuning_job_id (String) —

    The ID of the fine-tuning job.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



123
124
125
126
127
128
129
130
131
 
# File 'lib/openai/resources/fine_tuning/jobs.rb', line 123

def retrieve(fine_tuning_job_id, params = {})
  @client.request(
    method: :get,
    path: ["fine_tuning/jobs/%1$s", fine_tuning_job_id],
    model: OpenAI::FineTuning::FineTuningJob,
    security: {bearer_auth: true},
    options: params[:request_options]
  )
end