ChatModelMetrics

class oci.generative_ai.models.ChatModelMetrics(**kwargs)

Bases: oci.generative_ai.models.model_metrics.ModelMetrics

The chat model metrics of the fine-tuning process.

Attributes

MODEL_METRICS_TYPE_CHAT_MODEL_METRICS str(object=’’) -> str
MODEL_METRICS_TYPE_TEXT_GENERATION_MODEL_METRICS str(object=’’) -> str
final_accuracy Gets the final_accuracy of this ChatModelMetrics.
final_loss Gets the final_loss of this ChatModelMetrics.
model_metrics_type [Required] Gets the model_metrics_type of this ModelMetrics.

Methods

__init__(**kwargs) Initializes a new ChatModelMetrics object with values from keyword arguments.
get_subtype(object_dictionary) Given the hash representation of a subtype of this class, use the info in the hash to return the class of the subtype.
MODEL_METRICS_TYPE_CHAT_MODEL_METRICS = 'CHAT_MODEL_METRICS'
MODEL_METRICS_TYPE_TEXT_GENERATION_MODEL_METRICS = 'TEXT_GENERATION_MODEL_METRICS'
__init__(**kwargs)

Initializes a new ChatModelMetrics object with values from keyword arguments. The default value of the model_metrics_type attribute of this class is CHAT_MODEL_METRICS and it should not be changed. The following keyword arguments are supported (corresponding to the getters/setters of this class):

Parameters:
  • model_metrics_type (str) – The value to assign to the model_metrics_type property of this ChatModelMetrics. Allowed values for this property are: “TEXT_GENERATION_MODEL_METRICS”, “CHAT_MODEL_METRICS”
  • final_accuracy (float) – The value to assign to the final_accuracy property of this ChatModelMetrics.
  • final_loss (float) – The value to assign to the final_loss property of this ChatModelMetrics.
final_accuracy

Gets the final_accuracy of this ChatModelMetrics. Fine-tuned model accuracy.

Returns:The final_accuracy of this ChatModelMetrics.
Return type:float
final_loss

Gets the final_loss of this ChatModelMetrics. Fine-tuned model loss.

Returns:The final_loss of this ChatModelMetrics.
Return type:float
static get_subtype(object_dictionary)

Given the hash representation of a subtype of this class, use the info in the hash to return the class of the subtype.

model_metrics_type

[Required] Gets the model_metrics_type of this ModelMetrics. The type of the model metrics. Each type of model can expect a different set of model metrics.

Allowed values for this property are: “TEXT_GENERATION_MODEL_METRICS”, “CHAT_MODEL_METRICS”, ‘UNKNOWN_ENUM_VALUE’. Any unrecognized values returned by a service will be mapped to ‘UNKNOWN_ENUM_VALUE’.

Returns:The model_metrics_type of this ModelMetrics.
Return type:str