使用 Amazon SageMaker JumpStart 通过微调和 HPO 从文本文档中识别关键见解

text1 = "astonishing ... ( frames ) profound ethical and philosophical questions in the form of dazzling pop entertainment" 
text2 = "simply stupid , irrelevant and deeply , truly , bottomlessly cynical "

Inference:
Input text: 'astonishing ... ( frames ) profound ethical and philosophical questions in the form of dazzling pop entertainment'
Model prediction: [0.000452966779, 0.999547064]
Labels: [0, 1]
Predicted Label: 1 # value 0 means negative sentiment and value 1 means positive sentiment

Inference:
Input text: 'simply stupid , irrelevant and deeply , truly , bottomlessly cynical '
Model prediction: [0.998723, 0.00127695734]
Labels: [0, 1]
Predicted Label: 0

from sagemaker import image_uris, model_uris, script_uris, hyperparameters

model_id, model_version = model_id, "*" # all the other options of model_id are the same as the one in Section 2.
training_instance_type = config.TRAINING_INSTANCE_TYPE

# Retrieve the docker image
train_image_uri = image_uris.retrieve(
    region=None,
    framework=None,
    model_id=model_id,
    model_version=model_version,
    image_scope="training",
    instance_type=training_instance_type,
)
# Retrieve the training script
train_source_uri = script_uris.retrieve(
    model_id=model_id, model_version=model_version, script_scope="training"
)
# Retrieve the pre-trained model tarball to further fine-tune
train_model_uri = model_uris.retrieve(
    model_id=model_id, model_version=model_version, model_scope="training"
)

from sagemaker import hyperparameters

# Retrieve the default hyper-parameters for fine-tuning the model
hyperparameters = hyperparameters.retrieve_default(model_id=model_id, model_version=model_version)

# [Optional] Override default hyperparameters with custom values
hyperparameters["batch-size"] = "64"
hyperparameters["adam-learning-rate"] = "1e-6"

# Define objective metric per framework, based on which the best model will be selected.
metric_definitions_per_model = {
    "tensorflow": {
        "metrics": [{"Name": "val_accuracy", "Regex": "val_accuracy: ([0-9.]+)"}],
        "type": "Maximize",
    }
}

# You can select from the hyperparameters supported by the model, and configure ranges of values to be searched for training the optimal model.(https://docs.aws.amazon.com/sagemaker/latest/dg/automatic-model-tuning-define-ranges.html)
hyperparameter_ranges = {
    "adam-learning-rate": ContinuousParameter(0.00001, 0.01, scaling_type="Logarithmic")
}

# Increase the total number of training jobs run by AMT, for increased accuracy (and training time).
max_jobs = 6
# Change parallel training jobs run by AMT to reduce total training time, constrained by your account limits.
# if max_jobs=max_parallel_jobs then Bayesian search turns to Random.
max_parallel_jobs = 3

hp_tuner = HyperparameterTuner(
    tc_estimator,
    metric_definitions["metrics"][0]["Name"],
    hyperparameter_ranges,
    metric_definitions["metrics"],
    max_jobs=max_jobs,
    max_parallel_jobs=max_parallel_jobs,
    objective_type=metric_definitions["type"],
    base_tuning_job_name=tuning_job_name,
)

# Launch a SageMaker Tuning job to search for the best hyperparameters
hp_tuner.fit({"training": training_data_path_updated})

data = {'text': 'Amazon SageMaker is a fully managed service that provides every developer and data scientist with the ability to build, train, and deploy machine learning (ML) models quickly.'}
response = predictor.predict(data=data)

print(response['entities'])
print(response['noun_chunks'])

[{'text': 'Amazon SageMaker', 'start_char': 0, 'end_char': 16, 'label': 'ORG'}]
[{'text': 'Amazon SageMaker', 'start_char': 0, 'end_char': 16}, {'text': 'a fully managed service', 'start_char': 20, 'end_char': 43}, {'text': 'that', 'start_char': 44, 'end_char': 48}, {'text': 'every developer and data scientist', 'start_char': 58, 'end_char': 92}, {'text': 'the ability', 'start_char': 98, 'end_char': 109}, {'text': 'ML', 'start_char': 156, 'end_char': 158}]

model = PyTorchModel(
    model_data=f"{config.SOURCE_S3_PATH}/artifacts/models/empty.tar.gz",
    entry_point="entry_point.py",
    source_dir="../containers/question_answering",
    role=config.IAM_ROLE,
    framework_version="1.5.0",
    py_version="py3",
    code_location="s3://" + config.S3_BUCKET + "/code",
    env={
        "MODEL_ASSETS_S3_BUCKET": config.SOURCE_S3_BUCKET,
        "MODEL_ASSETS_S3_PREFIX": f"{config.SOURCE_S3_PREFIX}/artifacts/models/question_answering/",
        "MMS_DEFAULT_RESPONSE_TIMEOUT": "3000",
    },
)

在成功部署端点并配置预测器后，我们可以在示例输入上试用问答模型。 该模型已经在 斯坦福问答数据集 (SQuAD) 数据集。 引入该数据集是为了进一步推进问答建模领域。 这是一个由文章、问题和答案组成的阅读理解数据集。

data = {'question': 'what is my name?', 'context': "my name is thom"}
response = predictor.predict(data=data)

print(response['answers'])
[{'score': 0.9793591499328613, 'start': 11, 'end': 15, 'answer': 'thom'}, 
{'score': 0.02019440196454525, 'start': 0, 'end': 15, 'answer': 'my name is thom'}, 
{'score': 4.349117443780415e-05, 'start': 3, 'end': 15, 'answer': 'name is thom'}]

hyperparameters = {
    "pretrained-model": "bert-base-uncased",
    "learning-rate": 0.0002,
    "max-epoch": 2,
    "weight-decay": 0,
    "batch-size": 16,
    "accumulate-grad-batches": 2,
    "gradient-clip-val": 1.0
}

re_estimator = PyTorch(
    framework_version='1.5.0',
    py_version='py3',
    entry_point='entry_point.py',
    source_dir='../containers/relationship_extraction',
    hyperparameters=hyperparameters,
    role=aws_role,
    instance_count=1,
    instance_type=train_instance_type,
    output_path=f"s3://{bucket}/{prefix}/output",
    code_location=f"s3://{bucket}/{prefix}/output",
    base_job_name=training_job_name,
    tags=[{'Key': config.TAG_KEY, 'Value': config.SOLUTION_PREFIX}],
    sagemaker_session=sess,
    volume_size=30,
    env={
        'MMS_DEFAULT_RESPONSE_TIMEOUT': '500'
    },
    debugger_hook_config=False
)

re_estimator.fit(
    {
        "train": f"s3://{bucket}/{prefix}/train/",
        "validation": f"s3://{bucket}/{prefix}/validation/",
    }
)

hyperparameters = {
    "max-epoch": 2,
    "weight-decay": 0,
    "batch-size": 16,
    "accumulate-grad-batches": 2,
    "gradient-clip-val": 1.0
}

estimator = PyTorch(
    framework_version='1.5.0',
    py_version='py3',
    entry_point='entry_point.py',
    source_dir='../containers/relationship_extraction',
    hyperparameters=hyperparameters,
    role=aws_role,
    instance_count=1,
    instance_type=train_instance_type,
    output_path=f"s3://{bucket}/{prefix}/output",
    code_location=f"s3://{bucket}/{prefix}/output",
    base_job_name=tuning_job_name,
    tags=[{'Key': config.TAG_KEY, 'Value': config.SOLUTION_PREFIX}],
    sagemaker_session=sess,
    volume_size=30,
    env={
        'MMS_DEFAULT_RESPONSE_TIMEOUT': '500'
    },
    debugger_hook_config=False
    
    re_tuner = HyperparameterTuner(
    estimator,
    metric_definitions["metrics"][0]["Name"],
    hyperparameter_ranges,
    metric_definitions["metrics"],
    max_jobs=max_jobs,
    max_parallel_jobs=max_parallel_jobs,
    objective_type=metric_definitions["type"],
    base_tuning_job_name=tuning_job_name,
)

re_tuner.fit({
    "train": f"s3://{bucket}/{prefix}/train/",
    "validation": f"s3://{bucket}/{prefix}/validation/",
})

ARTICLE = """ Documents are a primary tool for communication,
collaboration, record keeping, and transactions across industries,
including financial, medical, legal, and real estate. The format of data
can pose an extra challenge in data extraction, especially if the content
is typed, handwritten, or embedded in a form or table. Furthermore,
extracting data from your documents is manual, error-prone, time-consuming,
expensive, and does not scale. Amazon Textract is a machine learning (ML)
service that extracts printed text and other data from documents as well as
tables and forms. We’re pleased to announce two new features for Amazon
Textract: support for handwriting in English documents, and expanding
language support for extracting printed text from documents typed in
Spanish, Portuguese, French, German, and Italian. Many documents, such as
medical intake forms or employment applications, contain both handwritten
and printed text. The ability to extract text and handwriting has been a
need our customers have asked us for. Amazon Textract can now extract
printed text and handwriting from documents written in English with high
confidence scores, whether it’s free-form text or text embedded in tables
and forms. Documents can also contain a mix of typed text or handwritten
text. The following image shows an example input document containing a mix
of typed and handwritten text, and its converted output document.."""

data = {'text': ARTICLE}
response = predictor.predict(data=data)
print(response['summary'])

"""Amazon Textract is a machine learning (ML) service that extracts printed text 
and other data from documents as well as tables and forms . 
customers can now extract and process documents in more languages .
support for handwriting in english documents and expanding language support for extracting 
printed text ."""

results = rouge.compute(predictions=[response['summary']], references=[ARTICLE])

rouge1: AggregateScore(low=Score(precision=1.0, recall=0.1070615034168565, fmeasure=0.1934156378600823), 
mid=Score(precision=1.0, recall=0.1070615034168565, fmeasure=0.1934156378600823), high=Score(precision=1.0, recall=0.1070615034168565, fmeasure=0.1934156378600823))

rouge2: AggregateScore(low=Score(precision=0.9565217391304348, recall=0.1004566210045662, fmeasure=0.18181818181818182), 
mid=Score(precision=0.9565217391304348, recall=0.1004566210045662, fmeasure=0.18181818181818182), high=Score(precision=0.9565217391304348, recall=0.1004566210045662, 
fmeasure=0.18181818181818182))

rougeL: AggregateScore(low=Score(precision=0.8085106382978723, recall=0.08656036446469248, fmeasure=0.15637860082304528), 
mid=Score(precision=0.8085106382978723, recall=0.08656036446469248, fmeasure=0.15637860082304528), high=Score(precision=0.8085106382978723, recall=0.08656036446469248, 
fmeasure=0.15637860082304528))

rougeLsum: AggregateScore(low=Score(precision=0.9787234042553191, recall=0.10478359908883828, fmeasure=0.18930041152263374), 
mid=Score(precision=0.9787234042553191, recall=0.10478359908883828, fmeasure=0.18930041152263374), high=Score(precision=0.9787234042553191, recall=0.10478359908883828, 
fmeasure=0.18930041152263374))