Я пытаюсь создать модель XGBoost на бесплатном уровне AWS Sagemaker. Я получаю сообщение об ошибке:
"ResourceLimitExceeded: при вызове операции CreateEndpoint произошла ошибка (ResourceLimitExceeded): ограничение службы уровня учетной записи« ml.m5.xlarge для использования конечной точки »равно 0 экземплярам, с текущим использованием 0 Экземпляров и дельтой запроса 1 Экземпляров. ".
Какой правильный train_instance_type я должен использовать?
Вот мой код:
# import libraries
import boto3, re, sys, math, json, os, sagemaker, urllib.request
from sagemaker import get_execution_role
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from IPython.display import Image
from IPython.display import display
from time import gmtime, strftime
from sagemaker.predictor import csv_serializer
# Define IAM role
role = get_execution_role()
prefix = 'sagemaker/DEMO-xgboost-dm'
containers = {'us-west-2': '433757028032.dkr.ecr.us-west-2.amazonaws.com/xgboost:latest',
'us-east-1': '811284229777.dkr.ecr.us-east-1.amazonaws.com/xgboost:latest',
'us-east-2': '825641698319.dkr.ecr.us-east-2.amazonaws.com/xgboost:latest',
'eu-west-1': '685385470294.dkr.ecr.eu-west-1.amazonaws.com/xgboost:latest'} # each region has its XGBoost container
my_region = boto3.session.Session().region_name # set the region of the instance
# Create an instance of the XGBoost model (an estimator), and define the model’s hyperparameters.
# Note: train_instance_type='ml.m5.large' has 0 free credits! Use one of https://aws.amazon.com/sagemaker/pricing/
sess = sagemaker.Session()
xgb = sagemaker.estimator.Estimator(containers[my_region],role, train_instance_count=1, train_instance_type='ml.m5.xlarge',output_path='s3://{}/{}/output'.format('my_s3_bucket', prefix),sagemaker_session=sess)
xgb.set_hyperparameters(max_depth=1,eta=0.2,gamma=4,min_child_weight=6,subsample=0.8,silent=0,objective='binary:logistic',num_round=100)
# Train the model using gradient optimization on a ml.m4.xlarge instance
# After a few minutes, you should start to see the training logs being generated.
xgb.fit({'train': s3_input_train})
На этом шаге вот что я вижу:
2019-10-22 06:32:51 Starting - Starting the training job...
2019-10-22 06:33:00 Starting - Launching requested ML instances......
2019-10-22 06:33:54 Starting - Preparing the instances for training...
2019-10-22 06:34:41 Downloading - Downloading input data...
2019-10-22 06:35:22 Training - Training image download completed. Training in progress..Arguments: train
[2019-10-22:06:35:22:INFO] Running standalone xgboost training.
[2019-10-22:06:35:22:INFO] Path /opt/ml/input/data/validation does not exist!
[2019-10-22:06:35:22:INFO] File size need to be processed in the node: 3.38mb. Available memory size in the node: 8089.9mb
[2019-10-22:06:35:22:INFO] Determined delimiter of CSV input is ','
[06:35:22] S3DistributionType set as FullyReplicated
[06:35:22] 28831x59 matrix with 1701029 entries loaded from /opt/ml/input/data/train?format=csv&label_column=0&delimiter=,
[06:35:22] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1
[0]#011train-error:0.102182
[06:35:22] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1
[1]#011train-error:0.102182
[06:35:22] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1
[2]#011train-error:0.102182
[06:35:22] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1
[3]#011train-error:0.102182
[06:35:22] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1
[4]#011train-error:0.102182
[06:35:22] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1
[5]#011train-error:0.102182
[06:35:22] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1
[6]#011train-error:0.102182
[06:35:22] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1
[7]#011train-error:0.10839
[06:35:22] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1
[8]#011train-error:0.102737
[06:35:22] src/tree/updater_prune.cc:74: tree pruning end, 1 roots, 2 extra nodes, 0 pruned nodes, max_depth=1
[9]#011train-error:0.107697
А потом, когда я разверну это:
# Deploy the model on a server and create an endpoint that you can access
xgb_predictor = xgb.deploy(initial_instance_count=1,instance_type='ml.m5.xlarge')
---------------------------------------------------------------------------
ResourceLimitExceeded Traceback (most recent call last)
<ipython-input-38-6d149f3edc98> in <module>()
1 # Deploy the model on a server and create an endpoint that you can access
----> 2 xgb_predictor = xgb.deploy(initial_instance_count=1,instance_type='ml.m5.xlarge')
~/anaconda3/envs/python3/lib/python3.6/site-packages/sagemaker/estimator.py in deploy(self, initial_instance_count, instance_type, accelerator_type, endpoint_name, use_compiled_model, update_endpoint, wait, model_name, kms_key, **kwargs)
559 tags=self.tags,
560 wait=wait,
--> 561 kms_key=kms_key,
562 )
563
~/anaconda3/envs/python3/lib/python3.6/site-packages/sagemaker/model.py in deploy(self, initial_instance_count, instance_type, accelerator_type, endpoint_name, update_endpoint, tags, kms_key, wait)
464 else:
465 self.sagemaker_session.endpoint_from_production_variants(
--> 466 self.endpoint_name, [production_variant], tags, kms_key, wait
467 )
468
~/anaconda3/envs/python3/lib/python3.6/site-packages/sagemaker/session.py in endpoint_from_production_variants(self, name, production_variants, tags, kms_key, wait)
1361
1362 self.sagemaker_client.create_endpoint_config(**config_options)
-> 1363 return self.create_endpoint(endpoint_name=name, config_name=name, tags=tags, wait=wait)
1364
1365 def expand_role(self, role):
~/anaconda3/envs/python3/lib/python3.6/site-packages/sagemaker/session.py in create_endpoint(self, endpoint_name, config_name, tags, wait)
975
976 self.sagemaker_client.create_endpoint(
--> 977 EndpointName=endpoint_name, EndpointConfigName=config_name, Tags=tags
978 )
979 if wait:
~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/client.py in _api_call(self, *args, **kwargs)
355 "%s() only accepts keyword arguments." % py_operation_name)
356 # The "self" in this scope is referring to the BaseClient.
--> 357 return self._make_api_call(operation_name, kwargs)
358
359 _api_call.__name__ = str(py_operation_name)
~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/client.py in _make_api_call(self, operation_name, api_params)
659 error_code = parsed_response.get("Error", {}).get("Code")
660 error_class = self.exceptions.from_code(error_code)
--> 661 raise error_class(parsed_response, operation_name)
662 else:
663 return parsed_response
ResourceLimitExceeded: An error occurred (ResourceLimitExceeded) when calling the CreateEndpoint operation: The account-level service limit 'ml.m5.xlarge for endpoint usage' is 0 Instances, with current utilization of 0 Instances and a request delta of 1 Instances. Please contact AWS support to request an increase for this limit.
Редактировать: Попытка ml.m4.xlarge экземпляр:
Когда я использую ml.m4.xlarge, я получаю то же сообщение «ResourceLimitExceeded: при вызове операции CreateEndpoint произошла ошибка (ResourceLimitExceeded):предельный уровень обслуживания «ml.m4.xlarge для использования конечной точки» равен 0 экземплярам, текущее использование - 0 экземпляров, а дельта запроса - 1 экземпляру. Обратитесь в службу поддержки AWS, чтобы запросить увеличение этого лимита. "