Fine Tuning

Methods

Domain Types

Dpo Hyperparameters

• class DpoHyperparameters:

  The hyperparameters used for the DPO fine-tuning job.

  • Optional<BatchSize> batchSize

    Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

    • JsonValue;

      • AUTO("auto")

    • long

  • Optional<Beta> beta

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

    • JsonValue;

      • AUTO("auto")

    • double

  • Optional<LearningRateMultiplier> learningRateMultiplier

    Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

    • JsonValue;

      • AUTO("auto")

    • double

  • Optional<NEpochs> nEpochs

    The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

    • JsonValue;

      • AUTO("auto")

    • long

Dpo Method

• class DpoMethod:

  Configuration for the DPO fine-tuning method.

  • Optional<DpoHyperparameters> hyperparameters

    The hyperparameters used for the DPO fine-tuning job.

    • Optional<BatchSize> batchSize

      Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<Beta> beta

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

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<LearningRateMultiplier> learningRateMultiplier

      Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<NEpochs> nEpochs

      The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

      • JsonValue;

        • AUTO("auto")

      • long

Reinforcement Hyperparameters

• class ReinforcementHyperparameters:

  The hyperparameters used for the reinforcement fine-tuning job.

  • Optional<BatchSize> batchSize

    Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

    • JsonValue;

      • AUTO("auto")

    • long

  • Optional<ComputeMultiplier> computeMultiplier

    Multiplier on amount of compute used for exploring search space during training.

    • JsonValue;

      • AUTO("auto")

    • double

  • Optional<EvalInterval> evalInterval

    The number of training steps between evaluation runs.

    • JsonValue;

      • AUTO("auto")

    • long

  • Optional<EvalSamples> evalSamples

    Number of evaluation samples to generate per training step.

    • JsonValue;

      • AUTO("auto")

    • long

  • Optional<LearningRateMultiplier> learningRateMultiplier

    Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

    • JsonValue;

      • AUTO("auto")

    • double

  • Optional<NEpochs> nEpochs

    The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

    • JsonValue;

      • AUTO("auto")

    • long

  • Optional<ReasoningEffort> reasoningEffort

    Level of reasoning effort.

    • DEFAULT("default")

    • LOW("low")

    • MEDIUM("medium")

    • HIGH("high")

Reinforcement Method

• class ReinforcementMethod:

  Configuration for the reinforcement fine-tuning method.

  • Grader grader

    The grader used for the fine-tuning job.

    • class StringCheckGrader:

      A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

      • String input

        The input text. This may include template strings.

      • String name

        The name of the grader.

      • Operation operation

        The string check operation to perform. One of eq, ne, like, or ilike.

        • EQ("eq")

        • NE("ne")

        • LIKE("like")

        • ILIKE("ilike")

      • String reference

        The reference text. This may include template strings.

      • JsonValue; type "string_check"constant

        The object type, which is always string_check.

        • STRING_CHECK("string_check")

    • class TextSimilarityGrader:

      A TextSimilarityGrader object which grades text based on similarity metrics.

      • EvaluationMetric evaluationMetric

        The evaluation metric to use. One of cosine, fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, or rouge_l.

        • COSINE("cosine")

        • FUZZY_MATCH("fuzzy_match")

        • BLEU("bleu")

        • GLEU("gleu")

        • METEOR("meteor")

        • ROUGE_1("rouge_1")

        • ROUGE_2("rouge_2")

        • ROUGE_3("rouge_3")

        • ROUGE_4("rouge_4")

        • ROUGE_5("rouge_5")

        • ROUGE_L("rouge_l")

      • String input

        The text being graded.

      • String name

        The name of the grader.

      • String reference

        The text being graded against.

      • JsonValue; type "text_similarity"constant

        The type of grader.

        • TEXT_SIMILARITY("text_similarity")

    • class PythonGrader:

      A PythonGrader object that runs a python script on the input.

      • String name

        The name of the grader.

      • String source

        The source code of the python script.

      • JsonValue; type "python"constant

        The object type, which is always python.

        • PYTHON("python")

      • Optional<String> imageTag

        The image tag to use for the python script.

    • class ScoreModelGrader:

      A ScoreModelGrader object that uses a model to assign a score to the input.

      • List<Input> input

        The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.

        • Content content

          Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

          • String

          • class ResponseInputText:

            A text input to the model.

            • String text

              The text input to the model.

            • JsonValue; type "input_text"constant

              The type of the input item. Always input_text.

              • INPUT_TEXT("input_text")

            • Optional<PromptCacheBreakpoint> promptCacheBreakpoint

              Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

              • JsonValue; mode "explicit"constant

                The breakpoint mode. Always explicit.

                • EXPLICIT("explicit")

          • class OutputText:

            A text output from the model.

            • String text

              The text output from the model.

            • JsonValue; type "output_text"constant

              The type of the output text. Always output_text.

              • OUTPUT_TEXT("output_text")

          • class InputImage:

            An image input block used within EvalItem content arrays.

            • String imageUrl

              The URL of the image input.

            • JsonValue; type "input_image"constant

              The type of the image input. Always input_image.

              • INPUT_IMAGE("input_image")

            • Optional<String> detail

              The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

          • class ResponseInputAudio:

            An audio input to the model.

            • InputAudio inputAudio

              • String data

                Base64-encoded audio data.

              • Format format

                The format of the audio data. Currently supported formats are mp3 and wav.

                • MP3("mp3")

                • WAV("wav")

            • JsonValue; type "input_audio"constant

              The type of the input item. Always input_audio.

              • INPUT_AUDIO("input_audio")

          • List<EvalContentItem>

            • String

            • class ResponseInputText:

              A text input to the model.

            • OutputText

              • String text

                The text output from the model.

              • JsonValue; type "output_text"constant

                The type of the output text. Always output_text.

                • OUTPUT_TEXT("output_text")

            • InputImage

              • String imageUrl

                The URL of the image input.

              • JsonValue; type "input_image"constant

                The type of the image input. Always input_image.

                • INPUT_IMAGE("input_image")

              • Optional<String> detail

                The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

            • class ResponseInputAudio:

              An audio input to the model.

        • Role role

          The role of the message input. One of user, assistant, system, or developer.

          • USER("user")

          • ASSISTANT("assistant")

          • SYSTEM("system")

          • DEVELOPER("developer")

        • Optional<Type> type

          The type of the message input. Always message.

          • MESSAGE("message")

      • String model

        The model to use for the evaluation.

      • String name

        The name of the grader.

      • JsonValue; type "score_model"constant

        The object type, which is always score_model.

        • SCORE_MODEL("score_model")

      • Optional<List<Double>> range

        The range of the score. Defaults to [0, 1].

      • Optional<SamplingParams> samplingParams

        The sampling parameters for the model.

        • Optional<Long> maxCompletionsTokens

          The maximum number of tokens the grader model may generate in its response.

        • Optional<ReasoningEffort> reasoningEffort

          Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

          • NONE("none")

          • MINIMAL("minimal")

          • LOW("low")

          • MEDIUM("medium")

          • HIGH("high")

          • XHIGH("xhigh")

          • MAX("max")

        • Optional<Long> seed

          A seed value to initialize the randomness, during sampling.

        • Optional<Double> temperature

          A higher temperature increases randomness in the outputs.

        • Optional<Double> topP

          An alternative to temperature for nucleus sampling; 1.0 includes all tokens.

    • class MultiGrader:

      A MultiGrader object combines the output of multiple graders to produce a single score.

      • String calculateOutput

        A formula to calculate the output based on grader results.

      • Graders graders

        A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

        • class StringCheckGrader:

          A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

        • class TextSimilarityGrader:

          A TextSimilarityGrader object which grades text based on similarity metrics.

        • class PythonGrader:

          A PythonGrader object that runs a python script on the input.

        • class ScoreModelGrader:

          A ScoreModelGrader object that uses a model to assign a score to the input.

        • class LabelModelGrader:

          A LabelModelGrader object which uses a model to assign labels to each item in the evaluation.

          • List<Input> input

            • Content content

              Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

              • String

              • class ResponseInputText:

                A text input to the model.

              • class OutputText:

                A text output from the model.

                • String text

                  The text output from the model.

                • JsonValue; type "output_text"constant

                  The type of the output text. Always output_text.

                  • OUTPUT_TEXT("output_text")

              • class InputImage:

                An image input block used within EvalItem content arrays.

                • String imageUrl

                  The URL of the image input.

                • JsonValue; type "input_image"constant

                  The type of the image input. Always input_image.

                  • INPUT_IMAGE("input_image")

                • Optional<String> detail

                  The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

              • class ResponseInputAudio:

                An audio input to the model.

              • List<EvalContentItem>

                • String

                • class ResponseInputText:

                  A text input to the model.

                • OutputText

                • InputImage

                • class ResponseInputAudio:

                  An audio input to the model.

            • Role role

              The role of the message input. One of user, assistant, system, or developer.

              • USER("user")

              • ASSISTANT("assistant")

              • SYSTEM("system")

              • DEVELOPER("developer")

            • Optional<Type> type

              The type of the message input. Always message.

              • MESSAGE("message")

          • List<String> labels

            The labels to assign to each item in the evaluation.

          • String model

            The model to use for the evaluation. Must support structured outputs.

          • String name

            The name of the grader.

          • List<String> passingLabels

            The labels that indicate a passing result. Must be a subset of labels.

          • JsonValue; type "label_model"constant

            The object type, which is always label_model.

            • LABEL_MODEL("label_model")

      • String name

        The name of the grader.

      • JsonValue; type "multi"constant

        The object type, which is always multi.

        • MULTI("multi")

  • Optional<ReinforcementHyperparameters> hyperparameters

    The hyperparameters used for the reinforcement fine-tuning job.

    • Optional<BatchSize> batchSize

      Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<ComputeMultiplier> computeMultiplier

      Multiplier on amount of compute used for exploring search space during training.

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<EvalInterval> evalInterval

      The number of training steps between evaluation runs.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<EvalSamples> evalSamples

      Number of evaluation samples to generate per training step.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<LearningRateMultiplier> learningRateMultiplier

      Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<NEpochs> nEpochs

      The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<ReasoningEffort> reasoningEffort

      Level of reasoning effort.

      • DEFAULT("default")

      • LOW("low")

      • MEDIUM("medium")

      • HIGH("high")

Supervised Hyperparameters

• class SupervisedHyperparameters:

  The hyperparameters used for the fine-tuning job.

  • Optional<BatchSize> batchSize

    Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

    • JsonValue;

      • AUTO("auto")

    • long

  • Optional<LearningRateMultiplier> learningRateMultiplier

    Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

    • JsonValue;

      • AUTO("auto")

    • double

  • Optional<NEpochs> nEpochs

    The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

    • JsonValue;

      • AUTO("auto")

    • long

Supervised Method

• class SupervisedMethod:

  Configuration for the supervised fine-tuning method.

  • Optional<SupervisedHyperparameters> hyperparameters

    The hyperparameters used for the fine-tuning job.

    • Optional<BatchSize> batchSize

      Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<LearningRateMultiplier> learningRateMultiplier

      Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<NEpochs> nEpochs

      The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

      • JsonValue;

        • AUTO("auto")

      • long

Jobs

Create fine-tuning job

FineTuningJob fineTuning().jobs().create(JobCreateParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

post /fine_tuning/jobs

Create fine-tuning job

Parameters

• JobCreateParams params

  • Model model

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

    • BABBAGE_002("babbage-002")

    • DAVINCI_002("davinci-002")

    • GPT_3_5_TURBO("gpt-3.5-turbo")

    • GPT_4O_MINI("gpt-4o-mini")

  • String trainingFile

    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.

  • Optional<Hyperparameters> 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.

    • Optional<BatchSize> batchSize

      Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<LearningRateMultiplier> learningRateMultiplier

      Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<NEpochs> nEpochs

      The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

      • JsonValue;

        • AUTO("auto")

      • long

  • Optional<List<Integration>> integrations

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

    • JsonValue; type "wandb"constant

      The type of integration to enable. Currently, only "wandb" (Weights and Biases) is supported.

      • WANDB("wandb")

    • Wandb wandb

      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.

      • String project

        The name of the project that the new run will be created under.

      • Optional<String> entity

        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.

      • Optional<String> name

        A display name to set for the run. If not set, we will use the Job ID as the name.

      • Optional<List<String>> tags

        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}".

  • Optional<Metadata> 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.

  • Optional<Method> method

    The method used for fine-tuning.

    • Type type

      The type of method. Is either supervised, dpo, or reinforcement.

      • SUPERVISED("supervised")

      • DPO("dpo")

      • REINFORCEMENT("reinforcement")

    • Optional<DpoMethod> dpo

      Configuration for the DPO fine-tuning method.

      • Optional<DpoHyperparameters> hyperparameters

        The hyperparameters used for the DPO fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<Beta> beta

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

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

    • Optional<ReinforcementMethod> reinforcement

      Configuration for the reinforcement fine-tuning method.

      • Grader grader

        The grader used for the fine-tuning job.

        • class StringCheckGrader:

          A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

          • String input

            The input text. This may include template strings.

          • String name

            The name of the grader.

          • Operation operation

            The string check operation to perform. One of eq, ne, like, or ilike.

            • EQ("eq")

            • NE("ne")

            • LIKE("like")

            • ILIKE("ilike")

          • String reference

            The reference text. This may include template strings.

          • JsonValue; type "string_check"constant

            The object type, which is always string_check.

            • STRING_CHECK("string_check")

        • class TextSimilarityGrader:

          A TextSimilarityGrader object which grades text based on similarity metrics.

          • EvaluationMetric evaluationMetric

            The evaluation metric to use. One of cosine, fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, or rouge_l.

            • COSINE("cosine")

            • FUZZY_MATCH("fuzzy_match")

            • BLEU("bleu")

            • GLEU("gleu")

            • METEOR("meteor")

            • ROUGE_1("rouge_1")

            • ROUGE_2("rouge_2")

            • ROUGE_3("rouge_3")

            • ROUGE_4("rouge_4")

            • ROUGE_5("rouge_5")

            • ROUGE_L("rouge_l")

          • String input

            The text being graded.

          • String name

            The name of the grader.

          • String reference

            The text being graded against.

          • JsonValue; type "text_similarity"constant

            The type of grader.

            • TEXT_SIMILARITY("text_similarity")

        • class PythonGrader:

          A PythonGrader object that runs a python script on the input.

          • String name

            The name of the grader.

          • String source

            The source code of the python script.

          • JsonValue; type "python"constant

            The object type, which is always python.

            • PYTHON("python")

          • Optional<String> imageTag

            The image tag to use for the python script.

        • class ScoreModelGrader:

          A ScoreModelGrader object that uses a model to assign a score to the input.

          • List<Input> input

            The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.

            • Content content

              Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

              • String

              • class ResponseInputText:

                A text input to the model.

                • String text

                  The text input to the model.

                • JsonValue; type "input_text"constant

                  The type of the input item. Always input_text.

                  • INPUT_TEXT("input_text")

                • Optional<PromptCacheBreakpoint> promptCacheBreakpoint

                  Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

                  • JsonValue; mode "explicit"constant

                    The breakpoint mode. Always explicit.

                    • EXPLICIT("explicit")

              • class OutputText:

                A text output from the model.

                • String text

                  The text output from the model.

                • JsonValue; type "output_text"constant

                  The type of the output text. Always output_text.

                  • OUTPUT_TEXT("output_text")

              • class InputImage:

                An image input block used within EvalItem content arrays.

                • String imageUrl

                  The URL of the image input.

                • JsonValue; type "input_image"constant

                  The type of the image input. Always input_image.

                  • INPUT_IMAGE("input_image")

                • Optional<String> detail

                  The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

              • class ResponseInputAudio:

                An audio input to the model.

                • InputAudio inputAudio

                  • String data

                    Base64-encoded audio data.

                  • Format format

                    The format of the audio data. Currently supported formats are mp3 and wav.

                    • MP3("mp3")

                    • WAV("wav")

                • JsonValue; type "input_audio"constant

                  The type of the input item. Always input_audio.

                  • INPUT_AUDIO("input_audio")

              • List<EvalContentItem>

                • String

                • class ResponseInputText:

                  A text input to the model.

                • OutputText

                  • String text

                    The text output from the model.

                  • JsonValue; type "output_text"constant

                    The type of the output text. Always output_text.

                    • OUTPUT_TEXT("output_text")

                • InputImage

                  • String imageUrl

                    The URL of the image input.

                  • JsonValue; type "input_image"constant

                    The type of the image input. Always input_image.

                    • INPUT_IMAGE("input_image")

                  • Optional<String> detail

                    The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                • class ResponseInputAudio:

                  An audio input to the model.

            • Role role

              The role of the message input. One of user, assistant, system, or developer.

              • USER("user")

              • ASSISTANT("assistant")

              • SYSTEM("system")

              • DEVELOPER("developer")

            • Optional<Type> type

              The type of the message input. Always message.

              • MESSAGE("message")

          • String model

            The model to use for the evaluation.

          • String name

            The name of the grader.

          • JsonValue; type "score_model"constant

            The object type, which is always score_model.

            • SCORE_MODEL("score_model")

          • Optional<List<Double>> range

            The range of the score. Defaults to [0, 1].

          • Optional<SamplingParams> samplingParams

            The sampling parameters for the model.

            • Optional<Long> maxCompletionsTokens

              The maximum number of tokens the grader model may generate in its response.

            • Optional<ReasoningEffort> reasoningEffort

              Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

              • NONE("none")

              • MINIMAL("minimal")

              • LOW("low")

              • MEDIUM("medium")

              • HIGH("high")

              • XHIGH("xhigh")

              • MAX("max")

            • Optional<Long> seed

              A seed value to initialize the randomness, during sampling.

            • Optional<Double> temperature

              A higher temperature increases randomness in the outputs.

            • Optional<Double> topP

              An alternative to temperature for nucleus sampling; 1.0 includes all tokens.

        • class MultiGrader:

          A MultiGrader object combines the output of multiple graders to produce a single score.

          • String calculateOutput

            A formula to calculate the output based on grader results.

          • Graders graders

            A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class StringCheckGrader:

              A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class TextSimilarityGrader:

              A TextSimilarityGrader object which grades text based on similarity metrics.

            • class PythonGrader:

              A PythonGrader object that runs a python script on the input.

            • class ScoreModelGrader:

              A ScoreModelGrader object that uses a model to assign a score to the input.

            • class LabelModelGrader:

              A LabelModelGrader object which uses a model to assign labels to each item in the evaluation.

              • List<Input> input

                • Content content

                  Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

                  • String

                  • class ResponseInputText:

                    A text input to the model.

                  • class OutputText:

                    A text output from the model.

                    • String text

                      The text output from the model.

                    • JsonValue; type "output_text"constant

                      The type of the output text. Always output_text.

                      • OUTPUT_TEXT("output_text")

                  • class InputImage:

                    An image input block used within EvalItem content arrays.

                    • String imageUrl

                      The URL of the image input.

                    • JsonValue; type "input_image"constant

                      The type of the image input. Always input_image.

                      • INPUT_IMAGE("input_image")

                    • Optional<String> detail

                      The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                  • class ResponseInputAudio:

                    An audio input to the model.

                  • List<EvalContentItem>

                    • String

                    • class ResponseInputText:

                      A text input to the model.

                    • OutputText

                    • InputImage

                    • class ResponseInputAudio:

                      An audio input to the model.

                • Role role

                  The role of the message input. One of user, assistant, system, or developer.

                  • USER("user")

                  • ASSISTANT("assistant")

                  • SYSTEM("system")

                  • DEVELOPER("developer")

                • Optional<Type> type

                  The type of the message input. Always message.

                  • MESSAGE("message")

              • List<String> labels

                The labels to assign to each item in the evaluation.

              • String model

                The model to use for the evaluation. Must support structured outputs.

              • String name

                The name of the grader.

              • List<String> passingLabels

                The labels that indicate a passing result. Must be a subset of labels.

              • JsonValue; type "label_model"constant

                The object type, which is always label_model.

                • LABEL_MODEL("label_model")

          • String name

            The name of the grader.

          • JsonValue; type "multi"constant

            The object type, which is always multi.

            • MULTI("multi")

      • Optional<ReinforcementHyperparameters> hyperparameters

        The hyperparameters used for the reinforcement fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ComputeMultiplier> computeMultiplier

          Multiplier on amount of compute used for exploring search space during training.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<EvalInterval> evalInterval

          The number of training steps between evaluation runs.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<EvalSamples> evalSamples

          Number of evaluation samples to generate per training step.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ReasoningEffort> reasoningEffort

          Level of reasoning effort.

          • DEFAULT("default")

          • LOW("low")

          • MEDIUM("medium")

          • HIGH("high")

    • Optional<SupervisedMethod> supervised

      Configuration for the supervised fine-tuning method.

      • Optional<SupervisedHyperparameters> hyperparameters

        The hyperparameters used for the fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

  • Optional<Long> 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.

  • Optional<String> 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.

  • Optional<String> validationFile

    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

• class FineTuningJob:

  The fine_tuning.job object represents a fine-tuning job that has been created through the API.

  • String id

    The object identifier, which can be referenced in the API endpoints.

  • long createdAt

    The Unix timestamp (in seconds) for when the fine-tuning job was created.

  • Optional<Error> error

    For fine-tuning jobs that have failed, this will contain more information on the cause of the failure.

    • String code

      A machine-readable error code.

    • String message

      A human-readable error message.

    • Optional<String> param

      The parameter that was invalid, usually training_file or validation_file. This field will be null if the failure was not parameter-specific.

  • Optional<String> fineTunedModel

    The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running.

  • Optional<Long> finishedAt

    The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running.

  • Hyperparameters hyperparameters

    The hyperparameters used for the fine-tuning job. This value will only be returned when running supervised jobs.

    • Optional<BatchSize> batchSize

      Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<LearningRateMultiplier> learningRateMultiplier

      Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<NEpochs> nEpochs

      The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

      • JsonValue;

        • AUTO("auto")

      • long

  • String model

    The base model that is being fine-tuned.

  • JsonValue; object_ "fine_tuning.job"constant

    The object type, which is always "fine_tuning.job".

    • FINE_TUNING_JOB("fine_tuning.job")

  • String organizationId

    The organization that owns the fine-tuning job.

  • List<String> resultFiles

    The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the Files API.

  • long seed

    The seed used for the fine-tuning job.

  • Status status

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

    • VALIDATING_FILES("validating_files")

    • QUEUED("queued")

    • RUNNING("running")

    • SUCCEEDED("succeeded")

    • FAILED("failed")

    • CANCELLED("cancelled")

  • Optional<Long> trainedTokens

    The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running.

  • String trainingFile

    The file ID used for training. You can retrieve the training data with the Files API.

  • Optional<String> validationFile

    The file ID used for validation. You can retrieve the validation results with the Files API.

  • Optional<Long> estimatedFinish

    The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job is not running.

  • Optional<List<FineTuningJobWandbIntegrationObject>> integrations

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

    • JsonValue; type "wandb"constant

      The type of the integration being enabled for the fine-tuning job

      • WANDB("wandb")

    • FineTuningJobWandbIntegration wandb

      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.

      • String project

        The name of the project that the new run will be created under.

      • Optional<String> entity

        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.

      • Optional<String> name

        A display name to set for the run. If not set, we will use the Job ID as the name.

      • Optional<List<String>> tags

        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}".

  • Optional<Metadata> 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.

  • Optional<Method> method

    The method used for fine-tuning.

    • Type type

      The type of method. Is either supervised, dpo, or reinforcement.

      • SUPERVISED("supervised")

      • DPO("dpo")

      • REINFORCEMENT("reinforcement")

    • Optional<DpoMethod> dpo

      Configuration for the DPO fine-tuning method.

      • Optional<DpoHyperparameters> hyperparameters

        The hyperparameters used for the DPO fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<Beta> beta

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

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

    • Optional<ReinforcementMethod> reinforcement

      Configuration for the reinforcement fine-tuning method.

      • Grader grader

        The grader used for the fine-tuning job.

        • class StringCheckGrader:

          A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

          • String input

            The input text. This may include template strings.

          • String name

            The name of the grader.

          • Operation operation

            The string check operation to perform. One of eq, ne, like, or ilike.

            • EQ("eq")

            • NE("ne")

            • LIKE("like")

            • ILIKE("ilike")

          • String reference

            The reference text. This may include template strings.

          • JsonValue; type "string_check"constant

            The object type, which is always string_check.

            • STRING_CHECK("string_check")

        • class TextSimilarityGrader:

          A TextSimilarityGrader object which grades text based on similarity metrics.

          • EvaluationMetric evaluationMetric

            The evaluation metric to use. One of cosine, fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, or rouge_l.

            • COSINE("cosine")

            • FUZZY_MATCH("fuzzy_match")

            • BLEU("bleu")

            • GLEU("gleu")

            • METEOR("meteor")

            • ROUGE_1("rouge_1")

            • ROUGE_2("rouge_2")

            • ROUGE_3("rouge_3")

            • ROUGE_4("rouge_4")

            • ROUGE_5("rouge_5")

            • ROUGE_L("rouge_l")

          • String input

            The text being graded.

          • String name

            The name of the grader.

          • String reference

            The text being graded against.

          • JsonValue; type "text_similarity"constant

            The type of grader.

            • TEXT_SIMILARITY("text_similarity")

        • class PythonGrader:

          A PythonGrader object that runs a python script on the input.

          • String name

            The name of the grader.

          • String source

            The source code of the python script.

          • JsonValue; type "python"constant

            The object type, which is always python.

            • PYTHON("python")

          • Optional<String> imageTag

            The image tag to use for the python script.

        • class ScoreModelGrader:

          A ScoreModelGrader object that uses a model to assign a score to the input.

          • List<Input> input

            The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.

            • Content content

              Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

              • String

              • class ResponseInputText:

                A text input to the model.

                • String text

                  The text input to the model.

                • JsonValue; type "input_text"constant

                  The type of the input item. Always input_text.

                  • INPUT_TEXT("input_text")

                • Optional<PromptCacheBreakpoint> promptCacheBreakpoint

                  Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

                  • JsonValue; mode "explicit"constant

                    The breakpoint mode. Always explicit.

                    • EXPLICIT("explicit")

              • class OutputText:

                A text output from the model.

                • String text

                  The text output from the model.

                • JsonValue; type "output_text"constant

                  The type of the output text. Always output_text.

                  • OUTPUT_TEXT("output_text")

              • class InputImage:

                An image input block used within EvalItem content arrays.

                • String imageUrl

                  The URL of the image input.

                • JsonValue; type "input_image"constant

                  The type of the image input. Always input_image.

                  • INPUT_IMAGE("input_image")

                • Optional<String> detail

                  The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

              • class ResponseInputAudio:

                An audio input to the model.

                • InputAudio inputAudio

                  • String data

                    Base64-encoded audio data.

                  • Format format

                    The format of the audio data. Currently supported formats are mp3 and wav.

                    • MP3("mp3")

                    • WAV("wav")

                • JsonValue; type "input_audio"constant

                  The type of the input item. Always input_audio.

                  • INPUT_AUDIO("input_audio")

              • List<EvalContentItem>

                • String

                • class ResponseInputText:

                  A text input to the model.

                • OutputText

                  • String text

                    The text output from the model.

                  • JsonValue; type "output_text"constant

                    The type of the output text. Always output_text.

                    • OUTPUT_TEXT("output_text")

                • InputImage

                  • String imageUrl

                    The URL of the image input.

                  • JsonValue; type "input_image"constant

                    The type of the image input. Always input_image.

                    • INPUT_IMAGE("input_image")

                  • Optional<String> detail

                    The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                • class ResponseInputAudio:

                  An audio input to the model.

            • Role role

              The role of the message input. One of user, assistant, system, or developer.

              • USER("user")

              • ASSISTANT("assistant")

              • SYSTEM("system")

              • DEVELOPER("developer")

            • Optional<Type> type

              The type of the message input. Always message.

              • MESSAGE("message")

          • String model

            The model to use for the evaluation.

          • String name

            The name of the grader.

          • JsonValue; type "score_model"constant

            The object type, which is always score_model.

            • SCORE_MODEL("score_model")

          • Optional<List<Double>> range

            The range of the score. Defaults to [0, 1].

          • Optional<SamplingParams> samplingParams

            The sampling parameters for the model.

            • Optional<Long> maxCompletionsTokens

              The maximum number of tokens the grader model may generate in its response.

            • Optional<ReasoningEffort> reasoningEffort

              Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

              • NONE("none")

              • MINIMAL("minimal")

              • LOW("low")

              • MEDIUM("medium")

              • HIGH("high")

              • XHIGH("xhigh")

              • MAX("max")

            • Optional<Long> seed

              A seed value to initialize the randomness, during sampling.

            • Optional<Double> temperature

              A higher temperature increases randomness in the outputs.

            • Optional<Double> topP

              An alternative to temperature for nucleus sampling; 1.0 includes all tokens.

        • class MultiGrader:

          A MultiGrader object combines the output of multiple graders to produce a single score.

          • String calculateOutput

            A formula to calculate the output based on grader results.

          • Graders graders

            A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class StringCheckGrader:

              A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class TextSimilarityGrader:

              A TextSimilarityGrader object which grades text based on similarity metrics.

            • class PythonGrader:

              A PythonGrader object that runs a python script on the input.

            • class ScoreModelGrader:

              A ScoreModelGrader object that uses a model to assign a score to the input.

            • class LabelModelGrader:

              A LabelModelGrader object which uses a model to assign labels to each item in the evaluation.

              • List<Input> input

                • Content content

                  Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

                  • String

                  • class ResponseInputText:

                    A text input to the model.

                  • class OutputText:

                    A text output from the model.

                    • String text

                      The text output from the model.

                    • JsonValue; type "output_text"constant

                      The type of the output text. Always output_text.

                      • OUTPUT_TEXT("output_text")

                  • class InputImage:

                    An image input block used within EvalItem content arrays.

                    • String imageUrl

                      The URL of the image input.

                    • JsonValue; type "input_image"constant

                      The type of the image input. Always input_image.

                      • INPUT_IMAGE("input_image")

                    • Optional<String> detail

                      The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                  • class ResponseInputAudio:

                    An audio input to the model.

                  • List<EvalContentItem>

                    • String

                    • class ResponseInputText:

                      A text input to the model.

                    • OutputText

                    • InputImage

                    • class ResponseInputAudio:

                      An audio input to the model.

                • Role role

                  The role of the message input. One of user, assistant, system, or developer.

                  • USER("user")

                  • ASSISTANT("assistant")

                  • SYSTEM("system")

                  • DEVELOPER("developer")

                • Optional<Type> type

                  The type of the message input. Always message.

                  • MESSAGE("message")

              • List<String> labels

                The labels to assign to each item in the evaluation.

              • String model

                The model to use for the evaluation. Must support structured outputs.

              • String name

                The name of the grader.

              • List<String> passingLabels

                The labels that indicate a passing result. Must be a subset of labels.

              • JsonValue; type "label_model"constant

                The object type, which is always label_model.

                • LABEL_MODEL("label_model")

          • String name

            The name of the grader.

          • JsonValue; type "multi"constant

            The object type, which is always multi.

            • MULTI("multi")

      • Optional<ReinforcementHyperparameters> hyperparameters

        The hyperparameters used for the reinforcement fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ComputeMultiplier> computeMultiplier

          Multiplier on amount of compute used for exploring search space during training.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<EvalInterval> evalInterval

          The number of training steps between evaluation runs.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<EvalSamples> evalSamples

          Number of evaluation samples to generate per training step.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ReasoningEffort> reasoningEffort

          Level of reasoning effort.

          • DEFAULT("default")

          • LOW("low")

          • MEDIUM("medium")

          • HIGH("high")

    • Optional<SupervisedMethod> supervised

      Configuration for the supervised fine-tuning method.

      • Optional<SupervisedHyperparameters> hyperparameters

        The hyperparameters used for the fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.finetuning.jobs.FineTuningJob;
import com.openai.models.finetuning.jobs.JobCreateParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        JobCreateParams params = JobCreateParams.builder()
            .model(JobCreateParams.Model.GPT_4O_MINI)
            .trainingFile("file-abc123")
            .build();
        FineTuningJob fineTuningJob = client.fineTuning().jobs().create(params);
    }
}

Response

{
  "id": "id",
  "created_at": 0,
  "error": {
    "code": "code",
    "message": "message",
    "param": "param"
  },
  "fine_tuned_model": "fine_tuned_model",
  "finished_at": 0,
  "hyperparameters": {
    "batch_size": "auto",
    "learning_rate_multiplier": "auto",
    "n_epochs": "auto"
  },
  "model": "model",
  "object": "fine_tuning.job",
  "organization_id": "organization_id",
  "result_files": [
    "file-abc123"
  ],
  "seed": 0,
  "status": "validating_files",
  "trained_tokens": 0,
  "training_file": "training_file",
  "validation_file": "validation_file",
  "estimated_finish": 0,
  "integrations": [
    {
      "type": "wandb",
      "wandb": {
        "project": "my-wandb-project",
        "entity": "entity",
        "name": "name",
        "tags": [
          "custom-tag"
        ]
      }
    }
  ],
  "metadata": {
    "foo": "string"
  },
  "method": {
    "type": "supervised",
    "dpo": {
      "hyperparameters": {
        "batch_size": "auto",
        "beta": "auto",
        "learning_rate_multiplier": "auto",
        "n_epochs": "auto"
      }
    },
    "reinforcement": {
      "grader": {
        "input": "input",
        "name": "name",
        "operation": "eq",
        "reference": "reference",
        "type": "string_check"
      },
      "hyperparameters": {
        "batch_size": "auto",
        "compute_multiplier": "auto",
        "eval_interval": "auto",
        "eval_samples": "auto",
        "learning_rate_multiplier": "auto",
        "n_epochs": "auto",
        "reasoning_effort": "default"
      }
    },
    "supervised": {
      "hyperparameters": {
        "batch_size": "auto",
        "learning_rate_multiplier": "auto",
        "n_epochs": "auto"
      }
    }
  }
}

List fine-tuning jobs

JobListPage fineTuning().jobs().list(JobListParamsparams = JobListParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

get /fine_tuning/jobs

List fine-tuning jobs

Parameters

• JobListParams params

  • Optional<String> after

    Identifier for the last job from the previous pagination request.

  • Optional<Long> limit

    Number of fine-tuning jobs to retrieve.

  • Optional<Metadata> metadata

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

Returns

• class FineTuningJob:

  The fine_tuning.job object represents a fine-tuning job that has been created through the API.

  • String id

    The object identifier, which can be referenced in the API endpoints.

  • long createdAt

    The Unix timestamp (in seconds) for when the fine-tuning job was created.

  • Optional<Error> error

    For fine-tuning jobs that have failed, this will contain more information on the cause of the failure.

    • String code

      A machine-readable error code.

    • String message

      A human-readable error message.

    • Optional<String> param

      The parameter that was invalid, usually training_file or validation_file. This field will be null if the failure was not parameter-specific.

  • Optional<String> fineTunedModel

    The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running.

  • Optional<Long> finishedAt

    The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running.

  • Hyperparameters hyperparameters

    The hyperparameters used for the fine-tuning job. This value will only be returned when running supervised jobs.

    • Optional<BatchSize> batchSize

      Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<LearningRateMultiplier> learningRateMultiplier

      Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<NEpochs> nEpochs

      The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

      • JsonValue;

        • AUTO("auto")

      • long

  • String model

    The base model that is being fine-tuned.

  • JsonValue; object_ "fine_tuning.job"constant

    The object type, which is always "fine_tuning.job".

    • FINE_TUNING_JOB("fine_tuning.job")

  • String organizationId

    The organization that owns the fine-tuning job.

  • List<String> resultFiles

    The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the Files API.

  • long seed

    The seed used for the fine-tuning job.

  • Status status

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

    • VALIDATING_FILES("validating_files")

    • QUEUED("queued")

    • RUNNING("running")

    • SUCCEEDED("succeeded")

    • FAILED("failed")

    • CANCELLED("cancelled")

  • Optional<Long> trainedTokens

    The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running.

  • String trainingFile

    The file ID used for training. You can retrieve the training data with the Files API.

  • Optional<String> validationFile

    The file ID used for validation. You can retrieve the validation results with the Files API.

  • Optional<Long> estimatedFinish

    The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job is not running.

  • Optional<List<FineTuningJobWandbIntegrationObject>> integrations

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

    • JsonValue; type "wandb"constant

      The type of the integration being enabled for the fine-tuning job

      • WANDB("wandb")

    • FineTuningJobWandbIntegration wandb

      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.

      • String project

        The name of the project that the new run will be created under.

      • Optional<String> entity

        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.

      • Optional<String> name

        A display name to set for the run. If not set, we will use the Job ID as the name.

      • Optional<List<String>> tags

        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}".

  • Optional<Metadata> 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.

  • Optional<Method> method

    The method used for fine-tuning.

    • Type type

      The type of method. Is either supervised, dpo, or reinforcement.

      • SUPERVISED("supervised")

      • DPO("dpo")

      • REINFORCEMENT("reinforcement")

    • Optional<DpoMethod> dpo

      Configuration for the DPO fine-tuning method.

      • Optional<DpoHyperparameters> hyperparameters

        The hyperparameters used for the DPO fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<Beta> beta

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

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

    • Optional<ReinforcementMethod> reinforcement

      Configuration for the reinforcement fine-tuning method.

      • Grader grader

        The grader used for the fine-tuning job.

        • class StringCheckGrader:

          A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

          • String input

            The input text. This may include template strings.

          • String name

            The name of the grader.

          • Operation operation

            The string check operation to perform. One of eq, ne, like, or ilike.

            • EQ("eq")

            • NE("ne")

            • LIKE("like")

            • ILIKE("ilike")

          • String reference

            The reference text. This may include template strings.

          • JsonValue; type "string_check"constant

            The object type, which is always string_check.

            • STRING_CHECK("string_check")

        • class TextSimilarityGrader:

          A TextSimilarityGrader object which grades text based on similarity metrics.

          • EvaluationMetric evaluationMetric

            The evaluation metric to use. One of cosine, fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, or rouge_l.

            • COSINE("cosine")

            • FUZZY_MATCH("fuzzy_match")

            • BLEU("bleu")

            • GLEU("gleu")

            • METEOR("meteor")

            • ROUGE_1("rouge_1")

            • ROUGE_2("rouge_2")

            • ROUGE_3("rouge_3")

            • ROUGE_4("rouge_4")

            • ROUGE_5("rouge_5")

            • ROUGE_L("rouge_l")

          • String input

            The text being graded.

          • String name

            The name of the grader.

          • String reference

            The text being graded against.

          • JsonValue; type "text_similarity"constant

            The type of grader.

            • TEXT_SIMILARITY("text_similarity")

        • class PythonGrader:

          A PythonGrader object that runs a python script on the input.

          • String name

            The name of the grader.

          • String source

            The source code of the python script.

          • JsonValue; type "python"constant

            The object type, which is always python.

            • PYTHON("python")

          • Optional<String> imageTag

            The image tag to use for the python script.

        • class ScoreModelGrader:

          A ScoreModelGrader object that uses a model to assign a score to the input.

          • List<Input> input

            The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.

            • Content content

              Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

              • String

              • class ResponseInputText:

                A text input to the model.

                • String text

                  The text input to the model.

                • JsonValue; type "input_text"constant

                  The type of the input item. Always input_text.

                  • INPUT_TEXT("input_text")

                • Optional<PromptCacheBreakpoint> promptCacheBreakpoint

                  Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

                  • JsonValue; mode "explicit"constant

                    The breakpoint mode. Always explicit.

                    • EXPLICIT("explicit")

              • class OutputText:

                A text output from the model.

                • String text

                  The text output from the model.

                • JsonValue; type "output_text"constant

                  The type of the output text. Always output_text.

                  • OUTPUT_TEXT("output_text")

              • class InputImage:

                An image input block used within EvalItem content arrays.

                • String imageUrl

                  The URL of the image input.

                • JsonValue; type "input_image"constant

                  The type of the image input. Always input_image.

                  • INPUT_IMAGE("input_image")

                • Optional<String> detail

                  The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

              • class ResponseInputAudio:

                An audio input to the model.

                • InputAudio inputAudio

                  • String data

                    Base64-encoded audio data.

                  • Format format

                    The format of the audio data. Currently supported formats are mp3 and wav.

                    • MP3("mp3")

                    • WAV("wav")

                • JsonValue; type "input_audio"constant

                  The type of the input item. Always input_audio.

                  • INPUT_AUDIO("input_audio")

              • List<EvalContentItem>

                • String

                • class ResponseInputText:

                  A text input to the model.

                • OutputText

                  • String text

                    The text output from the model.

                  • JsonValue; type "output_text"constant

                    The type of the output text. Always output_text.

                    • OUTPUT_TEXT("output_text")

                • InputImage

                  • String imageUrl

                    The URL of the image input.

                  • JsonValue; type "input_image"constant

                    The type of the image input. Always input_image.

                    • INPUT_IMAGE("input_image")

                  • Optional<String> detail

                    The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                • class ResponseInputAudio:

                  An audio input to the model.

            • Role role

              The role of the message input. One of user, assistant, system, or developer.

              • USER("user")

              • ASSISTANT("assistant")

              • SYSTEM("system")

              • DEVELOPER("developer")

            • Optional<Type> type

              The type of the message input. Always message.

              • MESSAGE("message")

          • String model

            The model to use for the evaluation.

          • String name

            The name of the grader.

          • JsonValue; type "score_model"constant

            The object type, which is always score_model.

            • SCORE_MODEL("score_model")

          • Optional<List<Double>> range

            The range of the score. Defaults to [0, 1].

          • Optional<SamplingParams> samplingParams

            The sampling parameters for the model.

            • Optional<Long> maxCompletionsTokens

              The maximum number of tokens the grader model may generate in its response.

            • Optional<ReasoningEffort> reasoningEffort

              Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

              • NONE("none")

              • MINIMAL("minimal")

              • LOW("low")

              • MEDIUM("medium")

              • HIGH("high")

              • XHIGH("xhigh")

              • MAX("max")

            • Optional<Long> seed

              A seed value to initialize the randomness, during sampling.

            • Optional<Double> temperature

              A higher temperature increases randomness in the outputs.

            • Optional<Double> topP

              An alternative to temperature for nucleus sampling; 1.0 includes all tokens.

        • class MultiGrader:

          A MultiGrader object combines the output of multiple graders to produce a single score.

          • String calculateOutput

            A formula to calculate the output based on grader results.

          • Graders graders

            A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class StringCheckGrader:

              A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class TextSimilarityGrader:

              A TextSimilarityGrader object which grades text based on similarity metrics.

            • class PythonGrader:

              A PythonGrader object that runs a python script on the input.

            • class ScoreModelGrader:

              A ScoreModelGrader object that uses a model to assign a score to the input.

            • class LabelModelGrader:

              A LabelModelGrader object which uses a model to assign labels to each item in the evaluation.

              • List<Input> input

                • Content content

                  Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

                  • String

                  • class ResponseInputText:

                    A text input to the model.

                  • class OutputText:

                    A text output from the model.

                    • String text

                      The text output from the model.

                    • JsonValue; type "output_text"constant

                      The type of the output text. Always output_text.

                      • OUTPUT_TEXT("output_text")

                  • class InputImage:

                    An image input block used within EvalItem content arrays.

                    • String imageUrl

                      The URL of the image input.

                    • JsonValue; type "input_image"constant

                      The type of the image input. Always input_image.

                      • INPUT_IMAGE("input_image")

                    • Optional<String> detail

                      The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                  • class ResponseInputAudio:

                    An audio input to the model.

                  • List<EvalContentItem>

                    • String

                    • class ResponseInputText:

                      A text input to the model.

                    • OutputText

                    • InputImage

                    • class ResponseInputAudio:

                      An audio input to the model.

                • Role role

                  The role of the message input. One of user, assistant, system, or developer.

                  • USER("user")

                  • ASSISTANT("assistant")

                  • SYSTEM("system")

                  • DEVELOPER("developer")

                • Optional<Type> type

                  The type of the message input. Always message.

                  • MESSAGE("message")

              • List<String> labels

                The labels to assign to each item in the evaluation.

              • String model

                The model to use for the evaluation. Must support structured outputs.

              • String name

                The name of the grader.

              • List<String> passingLabels

                The labels that indicate a passing result. Must be a subset of labels.

              • JsonValue; type "label_model"constant

                The object type, which is always label_model.

                • LABEL_MODEL("label_model")

          • String name

            The name of the grader.

          • JsonValue; type "multi"constant

            The object type, which is always multi.

            • MULTI("multi")

      • Optional<ReinforcementHyperparameters> hyperparameters

        The hyperparameters used for the reinforcement fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ComputeMultiplier> computeMultiplier

          Multiplier on amount of compute used for exploring search space during training.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<EvalInterval> evalInterval

          The number of training steps between evaluation runs.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<EvalSamples> evalSamples

          Number of evaluation samples to generate per training step.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ReasoningEffort> reasoningEffort

          Level of reasoning effort.

          • DEFAULT("default")

          • LOW("low")

          • MEDIUM("medium")

          • HIGH("high")

    • Optional<SupervisedMethod> supervised

      Configuration for the supervised fine-tuning method.

      • Optional<SupervisedHyperparameters> hyperparameters

        The hyperparameters used for the fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.finetuning.jobs.JobListPage;
import com.openai.models.finetuning.jobs.JobListParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        JobListPage page = client.fineTuning().jobs().list();
    }
}

Response

{
  "data": [
    {
      "id": "id",
      "created_at": 0,
      "error": {
        "code": "code",
        "message": "message",
        "param": "param"
      },
      "fine_tuned_model": "fine_tuned_model",
      "finished_at": 0,
      "hyperparameters": {
        "batch_size": "auto",
        "learning_rate_multiplier": "auto",
        "n_epochs": "auto"
      },
      "model": "model",
      "object": "fine_tuning.job",
      "organization_id": "organization_id",
      "result_files": [
        "file-abc123"
      ],
      "seed": 0,
      "status": "validating_files",
      "trained_tokens": 0,
      "training_file": "training_file",
      "validation_file": "validation_file",
      "estimated_finish": 0,
      "integrations": [
        {
          "type": "wandb",
          "wandb": {
            "project": "my-wandb-project",
            "entity": "entity",
            "name": "name",
            "tags": [
              "custom-tag"
            ]
          }
        }
      ],
      "metadata": {
        "foo": "string"
      },
      "method": {
        "type": "supervised",
        "dpo": {
          "hyperparameters": {
            "batch_size": "auto",
            "beta": "auto",
            "learning_rate_multiplier": "auto",
            "n_epochs": "auto"
          }
        },
        "reinforcement": {
          "grader": {
            "input": "input",
            "name": "name",
            "operation": "eq",
            "reference": "reference",
            "type": "string_check"
          },
          "hyperparameters": {
            "batch_size": "auto",
            "compute_multiplier": "auto",
            "eval_interval": "auto",
            "eval_samples": "auto",
            "learning_rate_multiplier": "auto",
            "n_epochs": "auto",
            "reasoning_effort": "default"
          }
        },
        "supervised": {
          "hyperparameters": {
            "batch_size": "auto",
            "learning_rate_multiplier": "auto",
            "n_epochs": "auto"
          }
        }
      }
    }
  ],
  "has_more": true,
  "object": "list"
}

Retrieve fine-tuning job

FineTuningJob fineTuning().jobs().retrieve(JobRetrieveParamsparams = JobRetrieveParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

get /fine_tuning/jobs/{fine_tuning_job_id}

Retrieve fine-tuning job

Parameters

• JobRetrieveParams params

  • Optional<String> fineTuningJobId

Returns

• class FineTuningJob:

  The fine_tuning.job object represents a fine-tuning job that has been created through the API.

  • String id

    The object identifier, which can be referenced in the API endpoints.

  • long createdAt

    The Unix timestamp (in seconds) for when the fine-tuning job was created.

  • Optional<Error> error

    For fine-tuning jobs that have failed, this will contain more information on the cause of the failure.

    • String code

      A machine-readable error code.

    • String message

      A human-readable error message.

    • Optional<String> param

      The parameter that was invalid, usually training_file or validation_file. This field will be null if the failure was not parameter-specific.

  • Optional<String> fineTunedModel

    The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running.

  • Optional<Long> finishedAt

    The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running.

  • Hyperparameters hyperparameters

    The hyperparameters used for the fine-tuning job. This value will only be returned when running supervised jobs.

    • Optional<BatchSize> batchSize

      Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<LearningRateMultiplier> learningRateMultiplier

      Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<NEpochs> nEpochs

      The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

      • JsonValue;

        • AUTO("auto")

      • long

  • String model

    The base model that is being fine-tuned.

  • JsonValue; object_ "fine_tuning.job"constant

    The object type, which is always "fine_tuning.job".

    • FINE_TUNING_JOB("fine_tuning.job")

  • String organizationId

    The organization that owns the fine-tuning job.

  • List<String> resultFiles

    The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the Files API.

  • long seed

    The seed used for the fine-tuning job.

  • Status status

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

    • VALIDATING_FILES("validating_files")

    • QUEUED("queued")

    • RUNNING("running")

    • SUCCEEDED("succeeded")

    • FAILED("failed")

    • CANCELLED("cancelled")

  • Optional<Long> trainedTokens

    The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running.

  • String trainingFile

    The file ID used for training. You can retrieve the training data with the Files API.

  • Optional<String> validationFile

    The file ID used for validation. You can retrieve the validation results with the Files API.

  • Optional<Long> estimatedFinish

    The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job is not running.

  • Optional<List<FineTuningJobWandbIntegrationObject>> integrations

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

    • JsonValue; type "wandb"constant

      The type of the integration being enabled for the fine-tuning job

      • WANDB("wandb")

    • FineTuningJobWandbIntegration wandb

      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.

      • String project

        The name of the project that the new run will be created under.

      • Optional<String> entity

        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.

      • Optional<String> name

        A display name to set for the run. If not set, we will use the Job ID as the name.

      • Optional<List<String>> tags

        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}".

  • Optional<Metadata> 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.

  • Optional<Method> method

    The method used for fine-tuning.

    • Type type

      The type of method. Is either supervised, dpo, or reinforcement.

      • SUPERVISED("supervised")

      • DPO("dpo")

      • REINFORCEMENT("reinforcement")

    • Optional<DpoMethod> dpo

      Configuration for the DPO fine-tuning method.

      • Optional<DpoHyperparameters> hyperparameters

        The hyperparameters used for the DPO fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<Beta> beta

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

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

    • Optional<ReinforcementMethod> reinforcement

      Configuration for the reinforcement fine-tuning method.

      • Grader grader

        The grader used for the fine-tuning job.

        • class StringCheckGrader:

          A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

          • String input

            The input text. This may include template strings.

          • String name

            The name of the grader.

          • Operation operation

            The string check operation to perform. One of eq, ne, like, or ilike.

            • EQ("eq")

            • NE("ne")

            • LIKE("like")

            • ILIKE("ilike")

          • String reference

            The reference text. This may include template strings.

          • JsonValue; type "string_check"constant

            The object type, which is always string_check.

            • STRING_CHECK("string_check")

        • class TextSimilarityGrader:

          A TextSimilarityGrader object which grades text based on similarity metrics.

          • EvaluationMetric evaluationMetric

            The evaluation metric to use. One of cosine, fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, or rouge_l.

            • COSINE("cosine")

            • FUZZY_MATCH("fuzzy_match")

            • BLEU("bleu")

            • GLEU("gleu")

            • METEOR("meteor")

            • ROUGE_1("rouge_1")

            • ROUGE_2("rouge_2")

            • ROUGE_3("rouge_3")

            • ROUGE_4("rouge_4")

            • ROUGE_5("rouge_5")

            • ROUGE_L("rouge_l")

          • String input

            The text being graded.

          • String name

            The name of the grader.

          • String reference

            The text being graded against.

          • JsonValue; type "text_similarity"constant

            The type of grader.

            • TEXT_SIMILARITY("text_similarity")

        • class PythonGrader:

          A PythonGrader object that runs a python script on the input.

          • String name

            The name of the grader.

          • String source

            The source code of the python script.

          • JsonValue; type "python"constant

            The object type, which is always python.

            • PYTHON("python")

          • Optional<String> imageTag

            The image tag to use for the python script.

        • class ScoreModelGrader:

          A ScoreModelGrader object that uses a model to assign a score to the input.

          • List<Input> input

            The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.

            • Content content

              Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

              • String

              • class ResponseInputText:

                A text input to the model.

                • String text

                  The text input to the model.

                • JsonValue; type "input_text"constant

                  The type of the input item. Always input_text.

                  • INPUT_TEXT("input_text")

                • Optional<PromptCacheBreakpoint> promptCacheBreakpoint

                  Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

                  • JsonValue; mode "explicit"constant

                    The breakpoint mode. Always explicit.

                    • EXPLICIT("explicit")

              • class OutputText:

                A text output from the model.

                • String text

                  The text output from the model.

                • JsonValue; type "output_text"constant

                  The type of the output text. Always output_text.

                  • OUTPUT_TEXT("output_text")

              • class InputImage:

                An image input block used within EvalItem content arrays.

                • String imageUrl

                  The URL of the image input.

                • JsonValue; type "input_image"constant

                  The type of the image input. Always input_image.

                  • INPUT_IMAGE("input_image")

                • Optional<String> detail

                  The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

              • class ResponseInputAudio:

                An audio input to the model.

                • InputAudio inputAudio

                  • String data

                    Base64-encoded audio data.

                  • Format format

                    The format of the audio data. Currently supported formats are mp3 and wav.

                    • MP3("mp3")

                    • WAV("wav")

                • JsonValue; type "input_audio"constant

                  The type of the input item. Always input_audio.

                  • INPUT_AUDIO("input_audio")

              • List<EvalContentItem>

                • String

                • class ResponseInputText:

                  A text input to the model.

                • OutputText

                  • String text

                    The text output from the model.

                  • JsonValue; type "output_text"constant

                    The type of the output text. Always output_text.

                    • OUTPUT_TEXT("output_text")

                • InputImage

                  • String imageUrl

                    The URL of the image input.

                  • JsonValue; type "input_image"constant

                    The type of the image input. Always input_image.

                    • INPUT_IMAGE("input_image")

                  • Optional<String> detail

                    The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                • class ResponseInputAudio:

                  An audio input to the model.

            • Role role

              The role of the message input. One of user, assistant, system, or developer.

              • USER("user")

              • ASSISTANT("assistant")

              • SYSTEM("system")

              • DEVELOPER("developer")

            • Optional<Type> type

              The type of the message input. Always message.

              • MESSAGE("message")

          • String model

            The model to use for the evaluation.

          • String name

            The name of the grader.

          • JsonValue; type "score_model"constant

            The object type, which is always score_model.

            • SCORE_MODEL("score_model")

          • Optional<List<Double>> range

            The range of the score. Defaults to [0, 1].

          • Optional<SamplingParams> samplingParams

            The sampling parameters for the model.

            • Optional<Long> maxCompletionsTokens

              The maximum number of tokens the grader model may generate in its response.

            • Optional<ReasoningEffort> reasoningEffort

              Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

              • NONE("none")

              • MINIMAL("minimal")

              • LOW("low")

              • MEDIUM("medium")

              • HIGH("high")

              • XHIGH("xhigh")

              • MAX("max")

            • Optional<Long> seed

              A seed value to initialize the randomness, during sampling.

            • Optional<Double> temperature

              A higher temperature increases randomness in the outputs.

            • Optional<Double> topP

              An alternative to temperature for nucleus sampling; 1.0 includes all tokens.

        • class MultiGrader:

          A MultiGrader object combines the output of multiple graders to produce a single score.

          • String calculateOutput

            A formula to calculate the output based on grader results.

          • Graders graders

            A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class StringCheckGrader:

              A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class TextSimilarityGrader:

              A TextSimilarityGrader object which grades text based on similarity metrics.

            • class PythonGrader:

              A PythonGrader object that runs a python script on the input.

            • class ScoreModelGrader:

              A ScoreModelGrader object that uses a model to assign a score to the input.

            • class LabelModelGrader:

              A LabelModelGrader object which uses a model to assign labels to each item in the evaluation.

              • List<Input> input

                • Content content

                  Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

                  • String

                  • class ResponseInputText:

                    A text input to the model.

                  • class OutputText:

                    A text output from the model.

                    • String text

                      The text output from the model.

                    • JsonValue; type "output_text"constant

                      The type of the output text. Always output_text.

                      • OUTPUT_TEXT("output_text")

                  • class InputImage:

                    An image input block used within EvalItem content arrays.

                    • String imageUrl

                      The URL of the image input.

                    • JsonValue; type "input_image"constant

                      The type of the image input. Always input_image.

                      • INPUT_IMAGE("input_image")

                    • Optional<String> detail

                      The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                  • class ResponseInputAudio:

                    An audio input to the model.

                  • List<EvalContentItem>

                    • String

                    • class ResponseInputText:

                      A text input to the model.

                    • OutputText

                    • InputImage

                    • class ResponseInputAudio:

                      An audio input to the model.

                • Role role

                  The role of the message input. One of user, assistant, system, or developer.

                  • USER("user")

                  • ASSISTANT("assistant")

                  • SYSTEM("system")

                  • DEVELOPER("developer")

                • Optional<Type> type

                  The type of the message input. Always message.

                  • MESSAGE("message")

              • List<String> labels

                The labels to assign to each item in the evaluation.

              • String model

                The model to use for the evaluation. Must support structured outputs.

              • String name

                The name of the grader.

              • List<String> passingLabels

                The labels that indicate a passing result. Must be a subset of labels.

              • JsonValue; type "label_model"constant

                The object type, which is always label_model.

                • LABEL_MODEL("label_model")

          • String name

            The name of the grader.

          • JsonValue; type "multi"constant

            The object type, which is always multi.

            • MULTI("multi")

      • Optional<ReinforcementHyperparameters> hyperparameters

        The hyperparameters used for the reinforcement fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ComputeMultiplier> computeMultiplier

          Multiplier on amount of compute used for exploring search space during training.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<EvalInterval> evalInterval

          The number of training steps between evaluation runs.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<EvalSamples> evalSamples

          Number of evaluation samples to generate per training step.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ReasoningEffort> reasoningEffort

          Level of reasoning effort.

          • DEFAULT("default")

          • LOW("low")

          • MEDIUM("medium")

          • HIGH("high")

    • Optional<SupervisedMethod> supervised

      Configuration for the supervised fine-tuning method.

      • Optional<SupervisedHyperparameters> hyperparameters

        The hyperparameters used for the fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.finetuning.jobs.FineTuningJob;
import com.openai.models.finetuning.jobs.JobRetrieveParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        FineTuningJob fineTuningJob = client.fineTuning().jobs().retrieve("ft-AF1WoRqd3aJAHsqc9NY7iL8F");
    }
}

Response

{
  "id": "id",
  "created_at": 0,
  "error": {
    "code": "code",
    "message": "message",
    "param": "param"
  },
  "fine_tuned_model": "fine_tuned_model",
  "finished_at": 0,
  "hyperparameters": {
    "batch_size": "auto",
    "learning_rate_multiplier": "auto",
    "n_epochs": "auto"
  },
  "model": "model",
  "object": "fine_tuning.job",
  "organization_id": "organization_id",
  "result_files": [
    "file-abc123"
  ],
  "seed": 0,
  "status": "validating_files",
  "trained_tokens": 0,
  "training_file": "training_file",
  "validation_file": "validation_file",
  "estimated_finish": 0,
  "integrations": [
    {
      "type": "wandb",
      "wandb": {
        "project": "my-wandb-project",
        "entity": "entity",
        "name": "name",
        "tags": [
          "custom-tag"
        ]
      }
    }
  ],
  "metadata": {
    "foo": "string"
  },
  "method": {
    "type": "supervised",
    "dpo": {
      "hyperparameters": {
        "batch_size": "auto",
        "beta": "auto",
        "learning_rate_multiplier": "auto",
        "n_epochs": "auto"
      }
    },
    "reinforcement": {
      "grader": {
        "input": "input",
        "name": "name",
        "operation": "eq",
        "reference": "reference",
        "type": "string_check"
      },
      "hyperparameters": {
        "batch_size": "auto",
        "compute_multiplier": "auto",
        "eval_interval": "auto",
        "eval_samples": "auto",
        "learning_rate_multiplier": "auto",
        "n_epochs": "auto",
        "reasoning_effort": "default"
      }
    },
    "supervised": {
      "hyperparameters": {
        "batch_size": "auto",
        "learning_rate_multiplier": "auto",
        "n_epochs": "auto"
      }
    }
  }
}

List fine-tuning events

JobListEventsPage fineTuning().jobs().listEvents(JobListEventsParamsparams = JobListEventsParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

get /fine_tuning/jobs/{fine_tuning_job_id}/events

List fine-tuning events

Parameters

• JobListEventsParams params

  • Optional<String> fineTuningJobId

  • Optional<String> after

    Identifier for the last event from the previous pagination request.

  • Optional<Long> limit

    Number of events to retrieve.

Returns

• class FineTuningJobEvent:

  Fine-tuning job event object

  • String id

    The object identifier.

  • long createdAt

    The Unix timestamp (in seconds) for when the fine-tuning job was created.

  • Level level

    The log level of the event.

    • INFO("info")

    • WARN("warn")

    • ERROR("error")

  • String message

    The message of the event.

  • JsonValue; object_ "fine_tuning.job.event"constant

    The object type, which is always "fine_tuning.job.event".

    • FINE_TUNING_JOB_EVENT("fine_tuning.job.event")

  • Optional<JsonValue> data

    The data associated with the event.

  • Optional<Type> type

    The type of event.

    • MESSAGE("message")

    • METRICS("metrics")

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.finetuning.jobs.JobListEventsPage;
import com.openai.models.finetuning.jobs.JobListEventsParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        JobListEventsPage page = client.fineTuning().jobs().listEvents("ft-AF1WoRqd3aJAHsqc9NY7iL8F");
    }
}

Response

{
  "data": [
    {
      "id": "id",
      "created_at": 0,
      "level": "info",
      "message": "message",
      "object": "fine_tuning.job.event",
      "data": {},
      "type": "message"
    }
  ],
  "has_more": true,
  "object": "list"
}

Cancel fine-tuning

FineTuningJob fineTuning().jobs().cancel(JobCancelParamsparams = JobCancelParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

post /fine_tuning/jobs/{fine_tuning_job_id}/cancel

Cancel fine-tuning

Parameters

• JobCancelParams params

  • Optional<String> fineTuningJobId

Returns

• class FineTuningJob:

  The fine_tuning.job object represents a fine-tuning job that has been created through the API.

  • String id

    The object identifier, which can be referenced in the API endpoints.

  • long createdAt

    The Unix timestamp (in seconds) for when the fine-tuning job was created.

  • Optional<Error> error

    For fine-tuning jobs that have failed, this will contain more information on the cause of the failure.

    • String code

      A machine-readable error code.

    • String message

      A human-readable error message.

    • Optional<String> param

      The parameter that was invalid, usually training_file or validation_file. This field will be null if the failure was not parameter-specific.

  • Optional<String> fineTunedModel

    The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running.

  • Optional<Long> finishedAt

    The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running.

  • Hyperparameters hyperparameters

    The hyperparameters used for the fine-tuning job. This value will only be returned when running supervised jobs.

    • Optional<BatchSize> batchSize

      Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<LearningRateMultiplier> learningRateMultiplier

      Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<NEpochs> nEpochs

      The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

      • JsonValue;

        • AUTO("auto")

      • long

  • String model

    The base model that is being fine-tuned.

  • JsonValue; object_ "fine_tuning.job"constant

    The object type, which is always "fine_tuning.job".

    • FINE_TUNING_JOB("fine_tuning.job")

  • String organizationId

    The organization that owns the fine-tuning job.

  • List<String> resultFiles

    The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the Files API.

  • long seed

    The seed used for the fine-tuning job.

  • Status status

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

    • VALIDATING_FILES("validating_files")

    • QUEUED("queued")

    • RUNNING("running")

    • SUCCEEDED("succeeded")

    • FAILED("failed")

    • CANCELLED("cancelled")

  • Optional<Long> trainedTokens

    The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running.

  • String trainingFile

    The file ID used for training. You can retrieve the training data with the Files API.

  • Optional<String> validationFile

    The file ID used for validation. You can retrieve the validation results with the Files API.

  • Optional<Long> estimatedFinish

    The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job is not running.

  • Optional<List<FineTuningJobWandbIntegrationObject>> integrations

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

    • JsonValue; type "wandb"constant

      The type of the integration being enabled for the fine-tuning job

      • WANDB("wandb")

    • FineTuningJobWandbIntegration wandb

      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.

      • String project

        The name of the project that the new run will be created under.

      • Optional<String> entity

        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.

      • Optional<String> name

        A display name to set for the run. If not set, we will use the Job ID as the name.

      • Optional<List<String>> tags

        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}".

  • Optional<Metadata> 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.

  • Optional<Method> method

    The method used for fine-tuning.

    • Type type

      The type of method. Is either supervised, dpo, or reinforcement.

      • SUPERVISED("supervised")

      • DPO("dpo")

      • REINFORCEMENT("reinforcement")

    • Optional<DpoMethod> dpo

      Configuration for the DPO fine-tuning method.

      • Optional<DpoHyperparameters> hyperparameters

        The hyperparameters used for the DPO fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<Beta> beta

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

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

    • Optional<ReinforcementMethod> reinforcement

      Configuration for the reinforcement fine-tuning method.

      • Grader grader

        The grader used for the fine-tuning job.

        • class StringCheckGrader:

          A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

          • String input

            The input text. This may include template strings.

          • String name

            The name of the grader.

          • Operation operation

            The string check operation to perform. One of eq, ne, like, or ilike.

            • EQ("eq")

            • NE("ne")

            • LIKE("like")

            • ILIKE("ilike")

          • String reference

            The reference text. This may include template strings.

          • JsonValue; type "string_check"constant

            The object type, which is always string_check.

            • STRING_CHECK("string_check")

        • class TextSimilarityGrader:

          A TextSimilarityGrader object which grades text based on similarity metrics.

          • EvaluationMetric evaluationMetric

            The evaluation metric to use. One of cosine, fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, or rouge_l.

            • COSINE("cosine")

            • FUZZY_MATCH("fuzzy_match")

            • BLEU("bleu")

            • GLEU("gleu")

            • METEOR("meteor")

            • ROUGE_1("rouge_1")

            • ROUGE_2("rouge_2")

            • ROUGE_3("rouge_3")

            • ROUGE_4("rouge_4")

            • ROUGE_5("rouge_5")

            • ROUGE_L("rouge_l")

          • String input

            The text being graded.

          • String name

            The name of the grader.

          • String reference

            The text being graded against.

          • JsonValue; type "text_similarity"constant

            The type of grader.

            • TEXT_SIMILARITY("text_similarity")

        • class PythonGrader:

          A PythonGrader object that runs a python script on the input.

          • String name

            The name of the grader.

          • String source

            The source code of the python script.

          • JsonValue; type "python"constant

            The object type, which is always python.

            • PYTHON("python")

          • Optional<String> imageTag

            The image tag to use for the python script.

        • class ScoreModelGrader:

          A ScoreModelGrader object that uses a model to assign a score to the input.

          • List<Input> input

            The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.

            • Content content

              Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

              • String

              • class ResponseInputText:

                A text input to the model.

                • String text

                  The text input to the model.

                • JsonValue; type "input_text"constant

                  The type of the input item. Always input_text.

                  • INPUT_TEXT("input_text")

                • Optional<PromptCacheBreakpoint> promptCacheBreakpoint

                  Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

                  • JsonValue; mode "explicit"constant

                    The breakpoint mode. Always explicit.

                    • EXPLICIT("explicit")

              • class OutputText:

                A text output from the model.

                • String text

                  The text output from the model.

                • JsonValue; type "output_text"constant

                  The type of the output text. Always output_text.

                  • OUTPUT_TEXT("output_text")

              • class InputImage:

                An image input block used within EvalItem content arrays.

                • String imageUrl

                  The URL of the image input.

                • JsonValue; type "input_image"constant

                  The type of the image input. Always input_image.

                  • INPUT_IMAGE("input_image")

                • Optional<String> detail

                  The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

              • class ResponseInputAudio:

                An audio input to the model.

                • InputAudio inputAudio

                  • String data

                    Base64-encoded audio data.

                  • Format format

                    The format of the audio data. Currently supported formats are mp3 and wav.

                    • MP3("mp3")

                    • WAV("wav")

                • JsonValue; type "input_audio"constant

                  The type of the input item. Always input_audio.

                  • INPUT_AUDIO("input_audio")

              • List<EvalContentItem>

                • String

                • class ResponseInputText:

                  A text input to the model.

                • OutputText

                  • String text

                    The text output from the model.

                  • JsonValue; type "output_text"constant

                    The type of the output text. Always output_text.

                    • OUTPUT_TEXT("output_text")

                • InputImage

                  • String imageUrl

                    The URL of the image input.

                  • JsonValue; type "input_image"constant

                    The type of the image input. Always input_image.

                    • INPUT_IMAGE("input_image")

                  • Optional<String> detail

                    The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                • class ResponseInputAudio:

                  An audio input to the model.

            • Role role

              The role of the message input. One of user, assistant, system, or developer.

              • USER("user")

              • ASSISTANT("assistant")

              • SYSTEM("system")

              • DEVELOPER("developer")

            • Optional<Type> type

              The type of the message input. Always message.

              • MESSAGE("message")

          • String model

            The model to use for the evaluation.

          • String name

            The name of the grader.

          • JsonValue; type "score_model"constant

            The object type, which is always score_model.

            • SCORE_MODEL("score_model")

          • Optional<List<Double>> range

            The range of the score. Defaults to [0, 1].

          • Optional<SamplingParams> samplingParams

            The sampling parameters for the model.

            • Optional<Long> maxCompletionsTokens

              The maximum number of tokens the grader model may generate in its response.

            • Optional<ReasoningEffort> reasoningEffort

              Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

              • NONE("none")

              • MINIMAL("minimal")

              • LOW("low")

              • MEDIUM("medium")

              • HIGH("high")

              • XHIGH("xhigh")

              • MAX("max")

            • Optional<Long> seed

              A seed value to initialize the randomness, during sampling.

            • Optional<Double> temperature

              A higher temperature increases randomness in the outputs.

            • Optional<Double> topP

              An alternative to temperature for nucleus sampling; 1.0 includes all tokens.

        • class MultiGrader:

          A MultiGrader object combines the output of multiple graders to produce a single score.

          • String calculateOutput

            A formula to calculate the output based on grader results.

          • Graders graders

            A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class StringCheckGrader:

              A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class TextSimilarityGrader:

              A TextSimilarityGrader object which grades text based on similarity metrics.

            • class PythonGrader:

              A PythonGrader object that runs a python script on the input.

            • class ScoreModelGrader:

              A ScoreModelGrader object that uses a model to assign a score to the input.

            • class LabelModelGrader:

              A LabelModelGrader object which uses a model to assign labels to each item in the evaluation.

              • List<Input> input

                • Content content

                  Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

                  • String

                  • class ResponseInputText:

                    A text input to the model.

                  • class OutputText:

                    A text output from the model.

                    • String text

                      The text output from the model.

                    • JsonValue; type "output_text"constant

                      The type of the output text. Always output_text.

                      • OUTPUT_TEXT("output_text")

                  • class InputImage:

                    An image input block used within EvalItem content arrays.

                    • String imageUrl

                      The URL of the image input.

                    • JsonValue; type "input_image"constant

                      The type of the image input. Always input_image.

                      • INPUT_IMAGE("input_image")

                    • Optional<String> detail

                      The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                  • class ResponseInputAudio:

                    An audio input to the model.

                  • List<EvalContentItem>

                    • String

                    • class ResponseInputText:

                      A text input to the model.

                    • OutputText

                    • InputImage

                    • class ResponseInputAudio:

                      An audio input to the model.

                • Role role

                  The role of the message input. One of user, assistant, system, or developer.

                  • USER("user")

                  • ASSISTANT("assistant")

                  • SYSTEM("system")

                  • DEVELOPER("developer")

                • Optional<Type> type

                  The type of the message input. Always message.

                  • MESSAGE("message")

              • List<String> labels

                The labels to assign to each item in the evaluation.

              • String model

                The model to use for the evaluation. Must support structured outputs.

              • String name

                The name of the grader.

              • List<String> passingLabels

                The labels that indicate a passing result. Must be a subset of labels.

              • JsonValue; type "label_model"constant

                The object type, which is always label_model.

                • LABEL_MODEL("label_model")

          • String name

            The name of the grader.

          • JsonValue; type "multi"constant

            The object type, which is always multi.

            • MULTI("multi")

      • Optional<ReinforcementHyperparameters> hyperparameters

        The hyperparameters used for the reinforcement fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ComputeMultiplier> computeMultiplier

          Multiplier on amount of compute used for exploring search space during training.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<EvalInterval> evalInterval

          The number of training steps between evaluation runs.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<EvalSamples> evalSamples

          Number of evaluation samples to generate per training step.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ReasoningEffort> reasoningEffort

          Level of reasoning effort.

          • DEFAULT("default")

          • LOW("low")

          • MEDIUM("medium")

          • HIGH("high")

    • Optional<SupervisedMethod> supervised

      Configuration for the supervised fine-tuning method.

      • Optional<SupervisedHyperparameters> hyperparameters

        The hyperparameters used for the fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.finetuning.jobs.FineTuningJob;
import com.openai.models.finetuning.jobs.JobCancelParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        FineTuningJob fineTuningJob = client.fineTuning().jobs().cancel("ft-AF1WoRqd3aJAHsqc9NY7iL8F");
    }
}

Response

{
  "id": "id",
  "created_at": 0,
  "error": {
    "code": "code",
    "message": "message",
    "param": "param"
  },
  "fine_tuned_model": "fine_tuned_model",
  "finished_at": 0,
  "hyperparameters": {
    "batch_size": "auto",
    "learning_rate_multiplier": "auto",
    "n_epochs": "auto"
  },
  "model": "model",
  "object": "fine_tuning.job",
  "organization_id": "organization_id",
  "result_files": [
    "file-abc123"
  ],
  "seed": 0,
  "status": "validating_files",
  "trained_tokens": 0,
  "training_file": "training_file",
  "validation_file": "validation_file",
  "estimated_finish": 0,
  "integrations": [
    {
      "type": "wandb",
      "wandb": {
        "project": "my-wandb-project",
        "entity": "entity",
        "name": "name",
        "tags": [
          "custom-tag"
        ]
      }
    }
  ],
  "metadata": {
    "foo": "string"
  },
  "method": {
    "type": "supervised",
    "dpo": {
      "hyperparameters": {
        "batch_size": "auto",
        "beta": "auto",
        "learning_rate_multiplier": "auto",
        "n_epochs": "auto"
      }
    },
    "reinforcement": {
      "grader": {
        "input": "input",
        "name": "name",
        "operation": "eq",
        "reference": "reference",
        "type": "string_check"
      },
      "hyperparameters": {
        "batch_size": "auto",
        "compute_multiplier": "auto",
        "eval_interval": "auto",
        "eval_samples": "auto",
        "learning_rate_multiplier": "auto",
        "n_epochs": "auto",
        "reasoning_effort": "default"
      }
    },
    "supervised": {
      "hyperparameters": {
        "batch_size": "auto",
        "learning_rate_multiplier": "auto",
        "n_epochs": "auto"
      }
    }
  }
}

Pause fine-tuning

FineTuningJob fineTuning().jobs().pause(JobPauseParamsparams = JobPauseParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

post /fine_tuning/jobs/{fine_tuning_job_id}/pause

Pause fine-tuning

Parameters

• JobPauseParams params

  • Optional<String> fineTuningJobId

Returns

• class FineTuningJob:

  The fine_tuning.job object represents a fine-tuning job that has been created through the API.

  • String id

    The object identifier, which can be referenced in the API endpoints.

  • long createdAt

    The Unix timestamp (in seconds) for when the fine-tuning job was created.

  • Optional<Error> error

    For fine-tuning jobs that have failed, this will contain more information on the cause of the failure.

    • String code

      A machine-readable error code.

    • String message

      A human-readable error message.

    • Optional<String> param

      The parameter that was invalid, usually training_file or validation_file. This field will be null if the failure was not parameter-specific.

  • Optional<String> fineTunedModel

    The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running.

  • Optional<Long> finishedAt

    The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running.

  • Hyperparameters hyperparameters

    The hyperparameters used for the fine-tuning job. This value will only be returned when running supervised jobs.

    • Optional<BatchSize> batchSize

      Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

      • JsonValue;

        • AUTO("auto")

      • long

    • Optional<LearningRateMultiplier> learningRateMultiplier

      Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

      • JsonValue;

        • AUTO("auto")

      • double

    • Optional<NEpochs> nEpochs

      The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

      • JsonValue;

        • AUTO("auto")

      • long

  • String model

    The base model that is being fine-tuned.

  • JsonValue; object_ "fine_tuning.job"constant

    The object type, which is always "fine_tuning.job".

    • FINE_TUNING_JOB("fine_tuning.job")

  • String organizationId

    The organization that owns the fine-tuning job.

  • List<String> resultFiles

    The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the Files API.

  • long seed

    The seed used for the fine-tuning job.

  • Status status

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

    • VALIDATING_FILES("validating_files")

    • QUEUED("queued")

    • RUNNING("running")

    • SUCCEEDED("succeeded")

    • FAILED("failed")

    • CANCELLED("cancelled")

  • Optional<Long> trainedTokens

    The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running.

  • String trainingFile

    The file ID used for training. You can retrieve the training data with the Files API.

  • Optional<String> validationFile

    The file ID used for validation. You can retrieve the validation results with the Files API.

  • Optional<Long> estimatedFinish

    The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job is not running.

  • Optional<List<FineTuningJobWandbIntegrationObject>> integrations

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

    • JsonValue; type "wandb"constant

      The type of the integration being enabled for the fine-tuning job

      • WANDB("wandb")

    • FineTuningJobWandbIntegration wandb

      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.

      • String project

        The name of the project that the new run will be created under.

      • Optional<String> entity

        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.

      • Optional<String> name

        A display name to set for the run. If not set, we will use the Job ID as the name.

      • Optional<List<String>> tags

        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}".

  • Optional<Metadata> 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.

  • Optional<Method> method

    The method used for fine-tuning.

    • Type type

      The type of method. Is either supervised, dpo, or reinforcement.

      • SUPERVISED("supervised")

      • DPO("dpo")

      • REINFORCEMENT("reinforcement")

    • Optional<DpoMethod> dpo

      Configuration for the DPO fine-tuning method.

      • Optional<DpoHyperparameters> hyperparameters

        The hyperparameters used for the DPO fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<Beta> beta

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

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

    • Optional<ReinforcementMethod> reinforcement

      Configuration for the reinforcement fine-tuning method.

      • Grader grader

        The grader used for the fine-tuning job.

        • class StringCheckGrader:

          A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

          • String input

            The input text. This may include template strings.

          • String name

            The name of the grader.

          • Operation operation

            The string check operation to perform. One of eq, ne, like, or ilike.

            • EQ("eq")

            • NE("ne")

            • LIKE("like")

            • ILIKE("ilike")

          • String reference

            The reference text. This may include template strings.

          • JsonValue; type "string_check"constant

            The object type, which is always string_check.

            • STRING_CHECK("string_check")

        • class TextSimilarityGrader:

          A TextSimilarityGrader object which grades text based on similarity metrics.

          • EvaluationMetric evaluationMetric

            The evaluation metric to use. One of cosine, fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, or rouge_l.

            • COSINE("cosine")

            • FUZZY_MATCH("fuzzy_match")

            • BLEU("bleu")

            • GLEU("gleu")

            • METEOR("meteor")

            • ROUGE_1("rouge_1")

            • ROUGE_2("rouge_2")

            • ROUGE_3("rouge_3")

            • ROUGE_4("rouge_4")

            • ROUGE_5("rouge_5")

            • ROUGE_L("rouge_l")

          • String input

            The text being graded.

          • String name

            The name of the grader.

          • String reference

            The text being graded against.

          • JsonValue; type "text_similarity"constant

            The type of grader.

            • TEXT_SIMILARITY("text_similarity")

        • class PythonGrader:

          A PythonGrader object that runs a python script on the input.

          • String name

            The name of the grader.

          • String source

            The source code of the python script.

          • JsonValue; type "python"constant

            The object type, which is always python.

            • PYTHON("python")

          • Optional<String> imageTag

            The image tag to use for the python script.

        • class ScoreModelGrader:

          A ScoreModelGrader object that uses a model to assign a score to the input.

          • List<Input> input

            The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.

            • Content content

              Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

              • String

              • class ResponseInputText:

                A text input to the model.

                • String text

                  The text input to the model.

                • JsonValue; type "input_text"constant

                  The type of the input item. Always input_text.

                  • INPUT_TEXT("input_text")

                • Optional<PromptCacheBreakpoint> promptCacheBreakpoint

                  Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

                  • JsonValue; mode "explicit"constant

                    The breakpoint mode. Always explicit.

                    • EXPLICIT("explicit")

              • class OutputText:

                A text output from the model.

                • String text

                  The text output from the model.

                • JsonValue; type "output_text"constant

                  The type of the output text. Always output_text.

                  • OUTPUT_TEXT("output_text")

              • class InputImage:

                An image input block used within EvalItem content arrays.

                • String imageUrl

                  The URL of the image input.

                • JsonValue; type "input_image"constant

                  The type of the image input. Always input_image.

                  • INPUT_IMAGE("input_image")

                • Optional<String> detail

                  The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

              • class ResponseInputAudio:

                An audio input to the model.

                • InputAudio inputAudio

                  • String data

                    Base64-encoded audio data.

                  • Format format

                    The format of the audio data. Currently supported formats are mp3 and wav.

                    • MP3("mp3")

                    • WAV("wav")

                • JsonValue; type "input_audio"constant

                  The type of the input item. Always input_audio.

                  • INPUT_AUDIO("input_audio")

              • List<EvalContentItem>

                • String

                • class ResponseInputText:

                  A text input to the model.

                • OutputText

                  • String text

                    The text output from the model.

                  • JsonValue; type "output_text"constant

                    The type of the output text. Always output_text.

                    • OUTPUT_TEXT("output_text")

                • InputImage

                  • String imageUrl

                    The URL of the image input.

                  • JsonValue; type "input_image"constant

                    The type of the image input. Always input_image.

                    • INPUT_IMAGE("input_image")

                  • Optional<String> detail

                    The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                • class ResponseInputAudio:

                  An audio input to the model.

            • Role role

              The role of the message input. One of user, assistant, system, or developer.

              • USER("user")

              • ASSISTANT("assistant")

              • SYSTEM("system")

              • DEVELOPER("developer")

            • Optional<Type> type

              The type of the message input. Always message.

              • MESSAGE("message")

          • String model

            The model to use for the evaluation.

          • String name

            The name of the grader.

          • JsonValue; type "score_model"constant

            The object type, which is always score_model.

            • SCORE_MODEL("score_model")

          • Optional<List<Double>> range

            The range of the score. Defaults to [0, 1].

          • Optional<SamplingParams> samplingParams

            The sampling parameters for the model.

            • Optional<Long> maxCompletionsTokens

              The maximum number of tokens the grader model may generate in its response.

            • Optional<ReasoningEffort> reasoningEffort

              Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

              • NONE("none")

              • MINIMAL("minimal")

              • LOW("low")

              • MEDIUM("medium")

              • HIGH("high")

              • XHIGH("xhigh")

              • MAX("max")

            • Optional<Long> seed

              A seed value to initialize the randomness, during sampling.

            • Optional<Double> temperature

              A higher temperature increases randomness in the outputs.

            • Optional<Double> topP

              An alternative to temperature for nucleus sampling; 1.0 includes all tokens.

        • class MultiGrader:

          A MultiGrader object combines the output of multiple graders to produce a single score.

          • String calculateOutput

            A formula to calculate the output based on grader results.

          • Graders graders

            A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class StringCheckGrader:

              A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

            • class TextSimilarityGrader:

              A TextSimilarityGrader object which grades text based on similarity metrics.

            • class PythonGrader:

              A PythonGrader object that runs a python script on the input.

            • class ScoreModelGrader:

              A ScoreModelGrader object that uses a model to assign a score to the input.

            • class LabelModelGrader:

              A LabelModelGrader object which uses a model to assign labels to each item in the evaluation.

              • List<Input> input

                • Content content

                  Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

                  • String

                  • class ResponseInputText:

                    A text input to the model.

                  • class OutputText:

                    A text output from the model.

                    • String text

                      The text output from the model.

                    • JsonValue; type "output_text"constant

                      The type of the output text. Always output_text.

                      • OUTPUT_TEXT("output_text")

                  • class InputImage:

                    An image input block used within EvalItem content arrays.

                    • String imageUrl

                      The URL of the image input.

                    • JsonValue; type "input_image"constant

                      The type of the image input. Always input_image.

                      • INPUT_IMAGE("input_image")

                    • Optional<String> detail

                      The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.

                  • class ResponseInputAudio:

                    An audio input to the model.

                  • List<EvalContentItem>

                    • String

                    • class ResponseInputText:

                      A text input to the model.

                    • OutputText

                    • InputImage

                    • class ResponseInputAudio:

                      An audio input to the model.

                • Role role

                  The role of the message input. One of user, assistant, system, or developer.

                  • USER("user")

                  • ASSISTANT("assistant")

                  • SYSTEM("system")

                  • DEVELOPER("developer")

                • Optional<Type> type

                  The type of the message input. Always message.

                  • MESSAGE("message")

              • List<String> labels

                The labels to assign to each item in the evaluation.

              • String model

                The model to use for the evaluation. Must support structured outputs.

              • String name

                The name of the grader.

              • List<String> passingLabels

                The labels that indicate a passing result. Must be a subset of labels.

              • JsonValue; type "label_model"constant

                The object type, which is always label_model.

                • LABEL_MODEL("label_model")

          • String name

            The name of the grader.

          • JsonValue; type "multi"constant

            The object type, which is always multi.

            • MULTI("multi")

      • Optional<ReinforcementHyperparameters> hyperparameters

        The hyperparameters used for the reinforcement fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ComputeMultiplier> computeMultiplier

          Multiplier on amount of compute used for exploring search space during training.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<EvalInterval> evalInterval

          The number of training steps between evaluation runs.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<EvalSamples> evalSamples

          Number of evaluation samples to generate per training step.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<ReasoningEffort> reasoningEffort

          Level of reasoning effort.

          • DEFAULT("default")

          • LOW("low")

          • MEDIUM("medium")

          • HIGH("high")

    • Optional<SupervisedMethod> supervised

      Configuration for the supervised fine-tuning method.

      • Optional<SupervisedHyperparameters> hyperparameters

        The hyperparameters used for the fine-tuning job.

        • Optional<BatchSize> batchSize

          Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.

          • JsonValue;

            • AUTO("auto")

          • long

        • Optional<LearningRateMultiplier> learningRateMultiplier

          Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.

          • JsonValue;

            • AUTO("auto")

          • double

        • Optional<NEpochs> nEpochs

          The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

          • JsonValue;

            • AUTO("auto")

          • long