Class VeoHyperParameters (1.153.1)

VeoHyperParameters(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Attributes

Name Description
epoch_count int
Optional. Number of complete passes the model makes over the entire training dataset during training.
learning_rate_multiplier float
Optional. Multiplier for adjusting the default learning rate.
tuning_task google.cloud.aiplatform_v1beta1.types.VeoHyperParameters.TuningTask
Optional. The tuning task. Either I2V or T2V.
veo_data_mixture_ratio float
Optional. The ratio of Google internal dataset to use in the training mixture, in range of [0, 1). If 0.2, it means 20% of Google internal dataset and 80% of user dataset will be used for training. If not set, the default value is 0.1. This field is a member of oneof_ _veo_data_mixture_ratio.
tuning_speed google.cloud.aiplatform_v1beta1.types.VeoHyperParameters.TuningSpeed
The speed of the tuning job. Only supported for Veo 3.0 models. This field is a member of oneof_ _tuning_speed.
adapter_size google.cloud.aiplatform_v1beta1.types.VeoHyperParameters.AdapterSize
Optional. The adapter size for LoRA tuning.

Classes

AdapterSize

AdapterSize(value)

Adapter size for LoRA tuning.

TuningSpeed

TuningSpeed(value)

The speed of the tuning job. Only supported for Veo 3.0 models.

TuningTask

TuningTask(value)

An enum defining the tuning task used for Veo.

Methods

VeoHyperParameters

VeoHyperParameters(mapping=None, *, ignore_unknown_fields=False, **kwargs)