Class: OpenAI::Models::FineTuning::JobCreateParams

Inherits:

Internal::Type::BaseModel

• Object
• Internal::Type::BaseModel
• OpenAI::Models::FineTuning::JobCreateParams

Extended by:

Internal::Type::RequestParameters::Converter

Includes:

Internal::Type::RequestParameters

Defined in:

lib/openai/models/fine_tuning/job_create_params.rb,
sig/openai/models/fine_tuning/job_create_params.rbs

Overview

See Also:

• OpenAI::Resources::FineTuning::Jobs#create

Defined Under Namespace

Modules: Model Classes: Hyperparameters, Integration, Method

Instance Attribute Summary

• #hyperparameters ⇒ OpenAI::FineTuning::JobCreateParams::Hyperparameters^?

  The hyperparameters used for the fine-tuning job.

• #integrations ⇒ ::Array[OpenAI::FineTuning::JobCreateParams::Integration]^?

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

• #metadata ⇒ OpenAI::Models::metadata^?

  Set of 16 key-value pairs that can be attached to an object.

• #method_ ⇒ OpenAI::FineTuning::JobCreateParams::Method^?

  The method used for fine-tuning.

• #model ⇒ OpenAI::Models::FineTuning::JobCreateParams::model

  The name of the model to fine-tune.

• #seed ⇒ Integer^?

  The seed controls the reproducibility of the job.

• #suffix ⇒ String^?

  A string of up to 64 characters that will be added to your fine-tuned model name.

• #training_file ⇒ String

  The ID of an uploaded file that contains training data.

• #validation_file ⇒ String^?

  The ID of an uploaded file that contains validation data.

Attributes included from Internal::Type::RequestParameters

#request_options

Attributes inherited from Internal::Type::BaseModel

#last_response

Class Method Summary

• .variants ⇒ Array(Symbol, :auto, Integer)

Instance Method Summary

• #initialize(project:, entity: nil, name: nil, tags: nil) ⇒ Object constructor
• #to_hash ⇒ {

Methods included from Internal::Type::RequestParameters::Converter

dump_request

Methods included from Internal::Type::RequestParameters

included

Methods inherited from Internal::Type::BaseModel

==, #==, #[], #_request_id, #_set_last_response, coerce, #deconstruct_keys, #deep_to_h, dump, #encode_with, fields, hash, #hash, inherited, #inspect, inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, coerce_with_error, dump, #dump, #inspect, inspect, meta_info, new_coerce_state, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

#initialize(project:, entity: nil, name: nil, tags: nil) ⇒ Object

Parameters:

• model —

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

• training_file —

  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 —

  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 —

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

• 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.

• method_ —

  The method used for fine-tuning.

• seed —

  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 —

  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 —

  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.

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 114

Instance Attribute Details

#hyperparameters ⇒ OpenAI::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.

Returns:

• (OpenAI::FineTuning::JobCreateParams::Hyperparameters, nil)

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 49

optional :hyperparameters, -> { OpenAI::FineTuning::JobCreateParams::Hyperparameters }

#integrations ⇒ ::Array[OpenAI::FineTuning::JobCreateParams::Integration]^?

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

Returns:

• (::Array[OpenAI::FineTuning::JobCreateParams::Integration], nil)

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 55

optional(
  :integrations,
  -> { OpenAI::Internal::Type::ArrayOf[OpenAI::FineTuning::JobCreateParams::Integration] },
  nil?: true
)

#metadata ⇒ OpenAI::Models::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.

Returns:

• (OpenAI::Models::metadata, nil)

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 70

optional :metadata, OpenAI::Internal::Type::HashOf[String], nil?: true

#method_ ⇒ OpenAI::FineTuning::JobCreateParams::Method^?

The method used for fine-tuning.

Returns:

• (OpenAI::FineTuning::JobCreateParams::Method, nil)

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 76

optional :method_, -> { OpenAI::FineTuning::JobCreateParams::Method }, api_name: :method

#model ⇒ OpenAI::Models::FineTuning::JobCreateParams::model

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

Returns:

• (OpenAI::Models::FineTuning::JobCreateParams::model)

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 16

required :model, union: -> { OpenAI::FineTuning::JobCreateParams::Model }

#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.

Returns:

• (Integer, nil)

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 84

optional :seed, Integer, nil?: true

#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.

Returns:

• (String, nil)

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 94

optional :suffix, String, nil?: true

#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.

Returns:

• (String)

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 40

required :training_file, String

#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.

Returns:

• (String, nil)

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 112

optional :validation_file, String, nil?: true

Class Method Details

.variants ⇒ Array(Symbol, :auto, Integer)

Returns:

• (Array(Symbol, :auto, Integer))

# File 'lib/openai/models/fine_tuning/job_create_params.rb', line 302

Instance Method Details

#to_hash ⇒ {

Returns:

• ({)

# File 'sig/openai/models/fine_tuning/job_create_params.rbs', line 177

def to_hash: -> {