Amazon Bedrock 模型微调实践（二）：数据准备篇

!pip install --upgrade pip%pip install --no-build-isolation --force-reinstall \    "boto3>=1.28.57" \    "awscli>=1.29.57" \    "botocore>=1.31.57"!pip install -qU --force-reinstall langchain typing_extensions pypdf urllib3==2.1.0!pip install -qU ipywidgets>=7,<8!pip install jsonlines!pip install datasets==2.15.0!pip install pandas==2.1.3!pip install matplotlib==3.8.2

import warningswarnings.filterwarnings('ignore')import jsonimport osimport sysimport boto3 import timeimport pprintfrom datasets import load_datasetimport randomimport jsonlines

session = boto3.session.Session()region = session.region_namests_client = boto3.client('sts')account_id = sts_client.get_caller_identity()["Account"]s3_suffix = f"{region}-{account_id}"bucket_name = f"bedrock-haiku-customization-{s3_suffix}"s3_client = boto3.client('s3')bedrock = boto3.client(service_name="bedrock")bedrock_runtime = boto3.client(service_name="bedrock-runtime")iam = boto3.client('iam', region_name=region)
import uuidsuffix = str(uuid.uuid4())role_name = "BedrockRole-" + suffixs3_bedrock_finetuning_access_policy="BedrockPolicy-" + suffixcustomization_role = f"arn:aws:iam::{account_id}:role/{role_name}"

print("region:", region)print("role_name:", role_name)print("bucket_name:", bucket_name)print("s3_bedrock_finetuning_access_policy:", s3_bedrock_finetuning_access_policy)print("customization_role:", customization_role)

# Create S3 bucket for knowledge base data sources3bucket = s3_client.create_bucket(    Bucket=bucket_name,    ## Uncomment the following if you run into errors    CreateBucketConfiguration={         'LocationConstraint':region,    },)

ROLE_DOC = f"""{{    "Version": "2012-10-17",    "Statement": [        {{            "Effect": "Allow",            "Principal": {{                "Service": "bedrock.amazonaws.com"            }},            "Action": "sts:AssumeRole",            "Condition": {{                "StringEquals": {{                    "aws:SourceAccount": "{account_id}"                }},                "ArnEquals": {{                    "aws:SourceArn": "arn:aws:bedrock:{region}:{account_id}:model-customization-job/*"                }}            }}        }}    ]}}"""

ACCESS_POLICY_DOC = f"""{{    "Version": "2012-10-17",    "Statement": [        {{            "Effect": "Allow",            "Action": [                "s3:AbortMultipartUpload",                "s3:DeleteObject",                "s3:PutObject",                "s3:GetObject",                "s3:GetBucketAcl",                "s3:GetBucketNotification",                "s3:ListBucket",                "s3:PutBucketNotification"            ],            "Resource": [                "arn:aws:s3:::{bucket_name}",                "arn:aws:s3:::{bucket_name}/*"            ]        }}    ]}}"""

response = iam.create_role(    RoleName=role_name,    AssumeRolePolicyDocument=ROLE_DOC,    Description="Role for Bedrock to access S3 for haiku finetuning",)pprint.pp(response)
role_arn = response["Role"]["Arn"]pprint.pp(role_arn)
response = iam.create_policy(    PolicyName=s3_bedrock_finetuning_access_policy,    PolicyDocument=ACCESS_POLICY_DOC,)pprint.pp(response)
policy_arn = response["Policy"]["Arn"]pprint.pp(policy_arn)

iam.attach_role_policy(    RoleName=role_name,    PolicyArn=policy_arn,)

#Load cnn dataset from huggingfacedataset = load_dataset("cnn_dailymail",'3.0.0')
print(dataset)

DatasetDict({    train: Dataset({        features: ['article', 'highlights', 'id'],        num_rows: 287113    })    validation: Dataset({        features: ['article', 'highlights', 'id'],        num_rows: 13368    })    test: Dataset({        features: ['article', 'highlights', 'id'],        num_rows: 11490    })})

{"system": string, "messages": [{"role": "user", "content": string}, {"role": "assistant", "content": string}]}{"system": string, "messages": [{"role": "user", "content": string}, {"role": "assistant", "content": string}]}{"system": string, "messages": [{"role": "user", "content": string}, {"role": "assistant", "content": string}]}

system_string = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request."
instruction = """instruction:
Summarize the news article provided below.
input:"""

datapoints_train=[]for dp in dataset['train']:    temp_dict={}    temp_dict["system"] = system_string    temp_dict["messages"] = [        {"role": "user", "content": instruction+dp['article']},        {"role": "assistant", "content": dp['highlights']}    ]    datapoints_train.append(temp_dict)

print(datapoints_train[4])
{'system': 'Below is an intruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.', 'messages': [{'role': 'user', 'content': 'instruction:\n\nSummarize the news article provided below.\n\ninput:\n(CNN)  -- The National Football League has indefinitely suspended Atlanta Falcons quarterback Michael Vick without pay, officials with the league said Friday. NFL star Michael Vick is set to appear in court Monday. A judge will have the final say on a plea deal. Earlier, Vick admitted to participating in a dogfighting ring as part of a plea agreement with federal prosecutors in Virginia. "Your admitted conduct was not only illegal, but also cruel and reprehensible. Your team, the NFL, and NFL fans have all been hurt by your actions," NFL Commissioner Roger Goodell said in a letter to Vick. Goodell said he would review the status of the suspension after the legal proceedings are over. In papers filed Friday with a federal court in Virginia, Vick also admitted that he and two co-conspirators killed dogs that did not fight well. Falcons owner Arthur Blank said Vick\'s admissions describe actions that are "incomprehensible and unacceptable." The suspension makes "a strong statement that conduct which tarnishes the good reputation of the NFL will not be tolerated," he said in a statement.  Watch what led to Vick\'s suspension » . Goodell said the Falcons could "assert any claims or remedies" to recover $22 million of Vick\'s signing bonus from the 10-year, $130 million contract he signed in 2004, according to The Associated Press. Vick said he would plead guilty to one count of "Conspiracy to Travel in Interstate Commerce in Aid of Unlawful Activities and to Sponsor a Dog in an Animal Fighting Venture" in a plea agreement filed at U.S. District Court in Richmond, Virginia. The charge is punishable by up to five years in prison, a $250,000 fine, "full restitution, a special assessment and 3 years of supervised release," the plea deal said. Federal prosecutors agreed to ask for the low end of the sentencing guidelines. "The defendant will plead guilty because the defendant is in fact guilty of the charged offense," the plea agreement said. In an additional summary of facts, signed by Vick and filed with the agreement, Vick admitted buying pit bulls and the property used for training and fighting the dogs, but the statement said he did not bet on the fights or receive any of the money won. "Most of the \'Bad Newz Kennels\' operations and gambling monies were provided by Vick," the official summary of facts said. Gambling wins were generally split among co-conspirators Tony Taylor, Quanis Phillips and sometimes Purnell Peace, it continued. "Vick did not gamble by placing side bets on any of the fights. Vick did not receive any of the proceeds from the purses that were won by \'Bad Newz Kennels.\' " Vick also agreed that "collective efforts" by him and two others caused the deaths of at least six dogs. Around April, Vick, Peace and Phillips tested some dogs in fighting sessions at Vick\'s property in Virginia, the statement said. "Peace, Phillips and Vick agreed to the killing of approximately 6-8 dogs that did not perform well in \'testing\' sessions at 1915 Moonlight Road and all of those dogs were killed by various methods, including hanging and drowning. "Vick agrees and stipulates that these dogs all died as a result of the collective efforts of Peace, Phillips and Vick," the summary said. Peace, 35, of Virginia Beach, Virginia; Phillips, 28, of Atlanta, Georgia; and Taylor, 34, of Hampton, Virginia, already have accepted agreements to plead guilty in exchange for reduced sentences. Vick, 27, is scheduled to appear Monday in court, where he is expected to plead guilty before a judge.  See a timeline of the case against Vick » . The judge in the case will have the final say over the plea agreement. The federal case against Vick focused on the interstate conspiracy, but Vick\'s admission that he was involved in the killing of dogs could lead to local charges, according to CNN legal analyst Jeffrey Toobin. "It sometimes happens -- not often -- that the state will follow a federal prosecution by charging its own crimes for exactly the same behavior," Toobin said Friday. "The risk for Vick is, if he makes admissions in his federal guilty plea, the state of Virginia could say, \'Hey, look, you admitted violating Virginia state law as well. We\'re going to introduce that against you and charge you in our court.\' " In the plea deal, Vick agreed to cooperate with investigators and provide all information he may have on any criminal activity and to testify if necessary. Vick also agreed to turn over any documents he has and to submit to polygraph tests. Vick agreed to "make restitution for the full amount of the costs associated" with the dogs that are being held by the government. "Such costs may include, but are not limited to, all costs associated with the care of the dogs involved in that case, including if necessary, the long-term care and/or the humane euthanasia of some or all of those animals." Prosecutors, with the support of animal rights activists, have asked for permission to euthanize the dogs. But the dogs could serve as important evidence in the cases against Vick and his admitted co-conspirators. Judge Henry E. Hudson issued an order Thursday telling the U.S. Marshals Service to "arrest and seize the defendant property, and use discretion and whatever means appropriate to protect and maintain said defendant property." Both the judge\'s order and Vick\'s filing refer to "approximately" 53 pit bull dogs. After Vick\'s indictment last month, Goodell ordered the quarterback not to report to the Falcons training camp, and the league is reviewing the case. Blank told the NFL Network on Monday he could not speculate on Vick\'s future as a Falcon, at least not until he had seen "a statement of facts" in the case.  E-mail to a friend . CNN\'s Mike Phelan contributed to this report.'}, {'role': 'assistant', 'content': "NEW: NFL chief, Atlanta Falcons owner critical of Michael Vick's conduct .\nNFL suspends Falcons quarterback indefinitely without pay .\nVick admits funding dogfighting operation but says he did not gamble .\nVick due in federal court Monday; future in NFL remains uncertain ."}]}

datapoints_valid=[]for dp in dataset['validation']:    temp_dict={}    temp_dict["system"] = system_string    temp_dict["messages"] = [        {"role": "user", "content": instruction+dp['article']},        {"role": "assistant", "content": dp['highlights']}    ]    datapoints_valid.append(temp_dict)

datapoints_test=[]for dp in dataset['test']:    temp_dict={}    temp_dict["system"] = system_string    temp_dict["messages"] = [        {"role": "user", "content": instruction+dp['article']},        {"role": "assistant", "content": dp['highlights']}    ]    datapoints_test.append(temp_dict)

def dp_transform(data_points,num_dps,max_dp_length):    """    This function filters and selects a subset of data points from the provided list based on the specified maximum length     and desired number of data points.    """     lines=[]    for dp in data_points:        if len(dp['system']+dp['messages'][0]['content']+dp['messages'][1]['content'])<=max_dp_length:            lines.append(dp)    random.shuffle(lines)    lines=lines[:num_dps]    return lines

def jsonl_converter(dataset,file_name):    """    This function writes the provided dataset to a JSONL (JSON Lines) file.    """    print(file_name)    with jsonlines.open(file_name, 'w') as writer:        for line in dataset:            writer.write(line)

train=dp_transform(datapoints_train,1000,20000)validation=dp_transform(datapoints_valid,100,20000)test=dp_transform(datapoints_test,10,20000)

dataset_folder="haiku-fine-tuning-datasets"train_file_name="train-cnn-1K.jsonl"validation_file_name="validation-cnn-100.jsonl"test_file_name="test-cnn-10.jsonl"!mkdir haiku-fine-tuning-datasetsabs_path=os.path.abspath(dataset_folder)
jsonl_converter(train,f'{abs_path}/{train_file_name}')jsonl_converter(validation,f'{abs_path}/{validation_file_name}')jsonl_converter(test,f'{abs_path}/{test_file_name}')

s3_client.upload_file(f'{abs_path}/{train_file_name}', bucket_name, f'haiku-fine-tuning-datasets/train/{train_file_name}')s3_client.upload_file(f'{abs_path}/{validation_file_name}', bucket_name, f'haiku-fine-tuning-datasets/validation/{validation_file_name}')s3_client.upload_file(f'{abs_path}/{test_file_name}', bucket_name, f'haiku-fine-tuning-datasets/test/{test_file_name}')
s3_train_uri=f's3://{bucket_name}/haiku-fine-tuning-datasets/train/{train_file_name}'s3_validation_uri=f's3://{bucket_name}/haiku-fine-tuning-datasets/validation/{validation_file_name}'s3_test_uri=f's3://{bucket_name}/haiku-fine-tuning-datasets/test/{test_file_name}'