REST Resource: tunedModels

{
  "name": string,
  "displayName": string,
  "description": string,
  "state": enum (State),
  "createTime": string,
  "updateTime": string,
  "tuningTask": {
    object (TuningTask)
  },

  // Union field source_model can be only one of the following:
  "tunedModelSource": {
    object (TunedModelSource)
  },
  "baseModel": string
  // End of list of possible types for union field source_model.
  "temperature": number,
  "topP": number,
  "topK": integer
}

string

Output only. The tuned model name. A unique name will be generated on create. Example: tunedModels/az2mb0bpw6i If displayName is set on create, the id portion of the name will be set by concatenating the words of the displayName with hyphens and adding a random portion for uniqueness. Example: displayName = "Sentence Translator" name = "tunedModels/sentence-translator-u3b7m"

string

Optional. The name to display for this model in user interfaces. The display name must be up to 40 characters including spaces.

string

Optional. A short description of this model.

enum (State)

Output only. The state of the tuned model.

string (Timestamp format)

Output only. The timestamp when this model was created.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

string (Timestamp format)

Output only. The timestamp when this model was updated.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

object (TuningTask)

Required. The tuning task that creates the tuned model.

object (TunedModelSource)

Optional. TunedModel to use as the starting point for training the new model.

string

Immutable. The name of the Model to tune. Example: models/text-bison-001

number

Optional. Controls the randomness of the output.

Values can range over [0.0,1.0], inclusive. A value closer to 1.0 will produce responses that are more varied, while a value closer to 0.0 will typically result in less surprising responses from the model.

This value specifies default to be the one used by the base model while creating the model.

number

Optional. For Nucleus sampling.

Nucleus sampling considers the smallest set of tokens whose probability sum is at least topP.

This value specifies default to be the one used by the base model while creating the model.

integer

Optional. For Top-k sampling.

Top-k sampling considers the set of topK most probable tokens. This value specifies default to be used by the backend while making the call to the model.

This value specifies default to be the one used by the base model while creating the model.

{
  "tunedModel": string,
  "baseModel": string
}

string

Immutable. The name of the TunedModel to use as the starting point for training the new model. Example: tunedModels/my-tuned-model

string

Output only. The name of the base Model this TunedModel was tuned from. Example: models/text-bison-001

{
  "startTime": string,
  "completeTime": string,
  "snapshots": [
    {
      object (TuningSnapshot)
    }
  ],
  "trainingData": {
    object (Dataset)
  },
  "hyperparameters": {
    object (Hyperparameters)
  }
}

string (Timestamp format)

Output only. The timestamp when tuning this model started.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

string (Timestamp format)

Output only. The timestamp when tuning this model completed.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

object (TuningSnapshot)

Output only. Metrics collected during tuning.

object (Dataset)

Required. Input only. Immutable. The model training data.

object (Hyperparameters)

Immutable. Hyperparameters controlling the tuning process. If not provided, default values will be used.

{
  "step": integer,
  "epoch": integer,
  "meanLoss": number,
  "computeTime": string
}

integer

Output only. The tuning step.

integer

Output only. The epoch this step was part of.

number

Output only. The mean loss of the training examples for this step.

string (Timestamp format)

Output only. The timestamp when this metric was computed.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

{

  // Union field dataset can be only one of the following:
  "examples": {
    object (TuningExamples)
  }
  // End of list of possible types for union field dataset.
}

object (TuningExamples)

Optional. Inline examples.

{
  "examples": [
    {
      object (TuningExample)
    }
  ]
}

object (TuningExample)

Required. The examples. Example input can be for text or discuss, but all examples in a set must be of the same type.

{
  "output": string,

  // Union field model_input can be only one of the following:
  "textInput": string
  // End of list of possible types for union field model_input.
}

string

Required. The expected model output.

string

Optional. Text model input.

{

  // Union field learning_rate_option can be only one of the following:
  "learningRate": number,
  "learningRateMultiplier": number
  // End of list of possible types for union field learning_rate_option.
  "epochCount": integer,
  "batchSize": integer
}

number

Optional. Immutable. The learning rate hyperparameter for tuning. If not set, a default of 0.001 or 0.0002 will be calculated based on the number of training examples.

number

Optional. Immutable. The learning rate multiplier is used to calculate a final learningRate based on the default (recommended) value. Actual learning rate := learningRateMultiplier * default learning rate Default learning rate is dependent on base model and dataset size. If not set, a default of 1.0 will be used.

integer

Immutable. The number of training epochs. An epoch is one pass through the training data. If not set, a default of 5 will be used.

integer

Immutable. The batch size hyperparameter for tuning. If not set, a default of 4 or 16 will be used based on the number of training examples.