Skip to content

TextGenerationJobConfig

Source code in docs_src/capo_sagemaker/types/text_generation_job_config.py 
14
15
16
17
18
19
20
21
22
23
24
25
26
27
class TextGenerationJobConfig(TypedDict, closed=True):
    completion_criteria: NotRequired[
        "capo_sagemaker.types.auto_ml_job_completion_criteria.AutoMLJobCompletionCriteria"
    ]
    """<p>How long a fine-tuning job is allowed to run. For <code>TextGenerationJobConfig</code> problem types, the <code>MaxRuntimePerTrainingJobInSeconds</code> attribute of <code>AutoMLJobCompletionCriteria</code> defaults to 72h (259200s).</p>"""
    base_model_name: NotRequired["capo_sagemaker.types.base_model_name.BaseModelName"]
    """<p>The name of the base model to fine-tune. Autopilot supports fine-tuning a variety of large language models. For information on the list of supported models, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-llms-finetuning-models.html#autopilot-llms-finetuning-supported-llms">Text generation models supporting fine-tuning in Autopilot</a>. If no <code>BaseModelName</code> is provided, the default model used is <b>Falcon7BInstruct</b>. </p>"""
    text_generation_hyper_parameters: NotRequired[
        "capo_sagemaker.types.text_generation_hyper_parameters.TextGenerationHyperParameters"
    ]
    """<p>The hyperparameters used to configure and optimize the learning process of the base model. You can set any combination of the following hyperparameters for all base models. For more information on each supported hyperparameter, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-llms-finetuning-set-hyperparameters.html">Optimize the learning process of your text generation models with hyperparameters</a>.</p> <ul> <li> <p> <code>"epochCount"</code>: The number of times the model goes through the entire training dataset. Its value should be a string containing an integer value within the range of "1" to "10".</p> </li> <li> <p> <code>"batchSize"</code>: The number of data samples used in each iteration of training. Its value should be a string containing an integer value within the range of "1" to "64".</p> </li> <li> <p> <code>"learningRate"</code>: The step size at which a model's parameters are updated during training. Its value should be a string containing a floating-point value within the range of "0" to "1".</p> </li> <li> <p> <code>"learningRateWarmupSteps"</code>: The number of training steps during which the learning rate gradually increases before reaching its target or maximum value. Its value should be a string containing an integer value within the range of "0" to "250".</p> </li> </ul> <p>Here is an example where all four hyperparameters are configured.</p> <p> <code>{ "epochCount":"5", "learningRate":"0.5", "batchSize": "32", "learningRateWarmupSteps": "10" }</code> </p>"""
    model_access_config: NotRequired[
        "capo_sagemaker.types.model_access_config.ModelAccessConfig"
    ]

base_model_name instance-attribute 

base_model_name: NotRequired[BaseModelName]

The name of the base model to fine-tune. Autopilot supports fine-tuning a variety of large language models. For information on the list of supported models, see Text generation models supporting fine-tuning in Autopilot. If no BaseModelName is provided, the default model used is Falcon7BInstruct.

completion_criteria instance-attribute 

completion_criteria: NotRequired[AutoMLJobCompletionCriteria]

How long a fine-tuning job is allowed to run. For TextGenerationJobConfig problem types, the MaxRuntimePerTrainingJobInSeconds attribute of AutoMLJobCompletionCriteria defaults to 72h (259200s).

model_access_config instance-attribute 

model_access_config: NotRequired[ModelAccessConfig]

text_generation_hyper_parameters instance-attribute 

text_generation_hyper_parameters: NotRequired[TextGenerationHyperParameters]

The hyperparameters used to configure and optimize the learning process of the base model. You can set any combination of the following hyperparameters for all base models. For more information on each supported hyperparameter, see Optimize the learning process of your text generation models with hyperparameters.

  • "epochCount": The number of times the model goes through the entire training dataset. Its value should be a string containing an integer value within the range of "1" to "10".

  • "batchSize": The number of data samples used in each iteration of training. Its value should be a string containing an integer value within the range of "1" to "64".

  • "learningRate": The step size at which a model's parameters are updated during training. Its value should be a string containing a floating-point value within the range of "0" to "1".

  • "learningRateWarmupSteps": The number of training steps during which the learning rate gradually increases before reaching its target or maximum value. Its value should be a string containing an integer value within the range of "0" to "250".

Here is an example where all four hyperparameters are configured.

{ "epochCount":"5", "learningRate":"0.5", "batchSize": "32", "learningRateWarmupSteps": "10" }