머신러닝 알고리즘 - LightGbm
Page content
개요
- 주택가격을 예측하는 데 필요한 Kaggle 데이터를 불러와서 빅쿼리에 저장하는 실습 진행
- 데이터를 불러와서
LightGBM를 활용하여 머신러닝을 만든다.
I. 사전 준비작업
Kaggle API설치 및 연동해서GCP에 데이터를 적재하는 것까지 진행한다.
(1) Kaggle API 설치
- 구글 코랩에서
API를 불러오려면 다음 소스코드를 실행한다.
!pip install kaggle
Requirement already satisfied: kaggle in /usr/local/lib/python3.6/dist-packages (1.5.6)
Requirement already satisfied: six>=1.10 in /usr/local/lib/python3.6/dist-packages (from kaggle) (1.12.0)
Requirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from kaggle) (2.23.0)
Requirement already satisfied: certifi in /usr/local/lib/python3.6/dist-packages (from kaggle) (2020.6.20)
Requirement already satisfied: tqdm in /usr/local/lib/python3.6/dist-packages (from kaggle) (4.41.1)
Requirement already satisfied: python-dateutil in /usr/local/lib/python3.6/dist-packages (from kaggle) (2.8.1)
Requirement already satisfied: python-slugify in /usr/local/lib/python3.6/dist-packages (from kaggle) (4.0.1)
Requirement already satisfied: urllib3<1.25,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from kaggle) (1.24.3)
Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->kaggle) (3.0.4)
Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->kaggle) (2.10)
Requirement already satisfied: text-unidecode>=1.3 in /usr/local/lib/python3.6/dist-packages (from python-slugify->kaggle) (1.3)
(2) Kaggle Token 다운로드
- Kaggle에서 API Token을 다운로드 받는다.
- [Kaggle]-[My Account]-[API]-[Create New API Token]을 누르면
kaggle.json파일이 다운로드 된다. - 이 파일을 바탕화면에 옮긴 뒤, 아래 코드를 실행 시킨다.
from google.colab import files
uploaded = files.upload()
for fn in uploaded.keys():
print('uploaded file "{name}" with length {length} bytes'.format(
name=fn, length=len(uploaded[fn])))
# kaggle.json을 아래 폴더로 옮긴 뒤, file을 사용할 수 있도록 권한을 부여한다.
!mkdir -p ~/.kaggle/ && mv kaggle.json ~/.kaggle/ && chmod 600 ~/.kaggle/kaggle.json
- 실제
kaggle.json파일이 업로드 되었다는 뜻이다.
ls -1ha ~/.kaggle/kaggle.json
/root/.kaggle/kaggle.json
(3) Kaggle 데이터 불러오기
Kaggle대회 리스트를 불러온다.
!kaggle competitions list
Warning: Looks like you're using an outdated API Version, please consider updating (server 1.5.6 / client 1.5.4)
ref deadline category reward teamCount userHasEntered
--------------------------------------------- ------------------- --------------- --------- --------- --------------
tpu-getting-started 2030-06-03 23:59:00 Getting Started Kudos 186 False
digit-recognizer 2030-01-01 00:00:00 Getting Started Knowledge 2963 False
titanic 2030-01-01 00:00:00 Getting Started Knowledge 22419 True
house-prices-advanced-regression-techniques 2030-01-01 00:00:00 Getting Started Knowledge 5051 True
connectx 2030-01-01 00:00:00 Getting Started Knowledge 710 False
nlp-getting-started 2030-01-01 00:00:00 Getting Started Kudos 1498 True
competitive-data-science-predict-future-sales 2020-12-31 23:59:00 Playground Kudos 7808 False
osic-pulmonary-fibrosis-progression 2020-10-06 23:59:00 Featured $55,000 248 False
halite 2020-09-15 23:59:00 Featured Swag 691 False
birdsong-recognition 2020-09-15 23:59:00 Research $25,000 396 False
landmark-retrieval-2020 2020-08-17 23:59:00 Research $25,000 165 False
siim-isic-melanoma-classification 2020-08-17 23:59:00 Featured $30,000 2180 False
global-wheat-detection 2020-08-04 23:59:00 Research $15,000 1788 False
open-images-object-detection-rvc-2020 2020-07-31 16:00:00 Playground Knowledge 58 False
open-images-instance-segmentation-rvc-2020 2020-07-31 16:00:00 Playground Knowledge 12 False
hashcode-photo-slideshow 2020-07-27 23:59:00 Playground Knowledge 59 False
prostate-cancer-grade-assessment 2020-07-22 23:59:00 Featured $25,000 920 False
alaska2-image-steganalysis 2020-07-20 23:59:00 Research $25,000 1046 False
m5-forecasting-accuracy 2020-06-30 23:59:00 Featured $50,000 5558 True
m5-forecasting-uncertainty 2020-06-30 23:59:00 Featured $50,000 909 False
- 여기에서 참여하기 원하는 대회의 데이터셋을 불러오면 된다.
- 이번
basic강의에서는house-prices-advanced-regression-techniques데이터를 활용한 데이터 가공과 시각화를 연습할 것이기 때문에 아래와 같이 코드를 실행하여 데이터를 불러온다.
!kaggle competitions download -c house-prices-advanced-regression-techniques
Warning: Looks like you're using an outdated API Version, please consider updating (server 1.5.6 / client 1.5.4)
Downloading train.csv to /content
0% 0.00/450k [00:00<?, ?B/s]
100% 450k/450k [00:00<00:00, 68.5MB/s]
Downloading data_description.txt to /content
0% 0.00/13.1k [00:00<?, ?B/s]
100% 13.1k/13.1k [00:00<00:00, 12.9MB/s]
Downloading test.csv to /content
0% 0.00/441k [00:00<?, ?B/s]
100% 441k/441k [00:00<00:00, 61.7MB/s]
Downloading sample_submission.csv to /content
0% 0.00/31.2k [00:00<?, ?B/s]
100% 31.2k/31.2k [00:00<00:00, 31.8MB/s]
- 실제 데이터가 잘 다운로드 받게 되었는지 확인한다.
!ls
data_description.txt sample_data sample_submission.csv test.csv train.csv
(4) BigQuery에 데이터 적재
sample_submission.csv,test.csv,train.csv데이터를 불러와서 빅쿼리에 적재를 한다.- 로컬에서 빅쿼리로 데이터를 Load하는 방법에는 여러가지가 있다.
Local에서 직접 올리기 (단, 10MB 이하)Google Stroage활용Pandas활용
Google Stroage를 활용하려면 클라우드 수업으로 진행되기 때문에,Pandas패키지를 활용한다.to_gbq라는 함수를 사용하는데, 이를 위해서는 보통pandas-gbq package패키지를 별도로 설치를 해야한다.- 다행히도, 구글
Colab에서는 위 패키지는 별도로 설치할 필요가 없다.
import pandas as pd
from pandas.io import gbq
# import sample_submission file
sample_submission = pd.read_csv('sample_submission.csv')
# Connect to Google Cloud API and Upload DataFrame
sample_submission.to_gbq(destination_table='house_price.sample_submission',
project_id='your_project_id',
if_exists='replace')
# import train file
train = pd.read_csv('train.csv')
column명을 확인해본다.
print(train.columns)
Index(['Id', 'MSSubClass', 'MSZoning', 'LotFrontage', 'LotArea', 'Street',
'Alley', 'LotShape', 'LandContour', 'Utilities', 'LotConfig',
'LandSlope', 'Neighborhood', 'Condition1', 'Condition2', 'BldgType',
'HouseStyle', 'OverallQual', 'OverallCond', 'YearBuilt', 'YearRemodAdd',
'RoofStyle', 'RoofMatl', 'Exterior1st', 'Exterior2nd', 'MasVnrType',
'MasVnrArea', 'ExterQual', 'ExterCond', 'Foundation', 'BsmtQual',
'BsmtCond', 'BsmtExposure', 'BsmtFinType1', 'BsmtFinSF1',
'BsmtFinType2', 'BsmtFinSF2', 'BsmtUnfSF', 'TotalBsmtSF', 'Heating',
'HeatingQC', 'CentralAir', 'Electrical', '1stFlrSF', '2ndFlrSF',
'LowQualFinSF', 'GrLivArea', 'BsmtFullBath', 'BsmtHalfBath', 'FullBath',
'HalfBath', 'BedroomAbvGr', 'KitchenAbvGr', 'KitchenQual',
'TotRmsAbvGrd', 'Functional', 'Fireplaces', 'FireplaceQu', 'GarageType',
'GarageYrBlt', 'GarageFinish', 'GarageCars', 'GarageArea', 'GarageQual',
'GarageCond', 'PavedDrive', 'WoodDeckSF', 'OpenPorchSF',
'EnclosedPorch', '3SsnPorch', 'ScreenPorch', 'PoolArea', 'PoolQC',
'Fence', 'MiscFeature', 'MiscVal', 'MoSold', 'YrSold', 'SaleType',
'SaleCondition', 'SalePrice'],
dtype='object')
- 빅쿼리에 데이터를
Loading할 때는 첫번째 글짜가 숫자가 오면 안되기 때문에, column 명을 수정한다.- 이 때, 각 숫자 앞에
my만 추가한다.
- 이 때, 각 숫자 앞에
colnames_dict = {"1stFlrSF": "my1stFlrSF", "2ndFlrSF": "my2ndFlrSF", "3SsnPorch": "my3SsnPorch"}
# Connect to Google Cloud API and Upload DataFrame
train = train.rename(columns=colnames_dict)
train.to_gbq(destination_table='house_price.train',
project_id='your_project_id',
if_exists='replace')
1it [00:06, 6.25s/it]
# Connect to Google Cloud API and Upload DataFrame
test = pd.read_csv('test.csv')
test = test.rename(columns=colnames_dict)
test.to_gbq(destination_table='house_price.test',
project_id='your_project_id',
if_exists='replace')
1it [00:03, 3.25s/it]
- 실제 데이터가 들어갔는지 빅쿼리에서 확인한다.
II. 데이터 피처공학
- 사이킷런 패키지는 기본적으로 결측치를 허용하지 않기 때문에, 반드시 확인 후, 처리해야 한다.
- 이번에는
BigQuery를 통해 데이터를 불러온다. - 주요 데이터 추출을 위한 피처공학에 대해 배워본다.
(1) 주요 패키지 불러오기
- 이제 주요 패키지를 불러온다.
import math
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
from scipy.stats import norm
import lightgbm as lgb
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_log_error
from sklearn import preprocessing
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import cross_val_score, cross_val_predict
(2) 데이터 불러오기
from google.colab import auth
auth.authenticate_user()
print('Authenticated')
Authenticated
- 먼저 훈련 데이터를 불러온다.
from google.cloud import bigquery
from tabulate import tabulate
import pandas as pd
project_id = 'your_project_id'
client = bigquery.Client(project=project_id)
df_train = client.query('''
SELECT
*
FROM `your_project_id.house_price.train`
''').to_dataframe()
df_train.shape
(1460, 81)
- 그 다음은 테스트 데이터를 불러온다.
df_test = client.query('''
SELECT
*
FROM `your_project_id.house_price.test`
''').to_dataframe()
df_test.shape
(1459, 80)
- 아래 코드는 출력 시, 전체
Column에 대해 확인할 수 있음
pd.options.display.max_columns = None
# df_train.describe()
(3) 결측 데이터 확인
# data set의 Percent 구하는 함수를 짜보자.
def check_fill_na(data):
new_df = data.copy()
new_df_na = (new_df.isnull().sum() / len(new_df)) * 100
new_df_na.sort_values(ascending=False).reset_index(drop=True)
new_df_na = new_df_na.drop(new_df_na[new_df_na == 0].index).sort_values(ascending=False)
return new_df_na
check_fill_na(df_train)
PoolQC 99.520548
MiscFeature 96.301370
Alley 93.767123
Fence 80.753425
FireplaceQu 47.260274
LotFrontage 17.739726
GarageYrBlt 5.547945
GarageType 5.547945
GarageFinish 5.547945
GarageQual 5.547945
GarageCond 5.547945
BsmtFinType2 2.602740
BsmtExposure 2.602740
BsmtFinType1 2.534247
BsmtCond 2.534247
BsmtQual 2.534247
MasVnrArea 0.547945
MasVnrType 0.547945
Electrical 0.068493
dtype: float64
(4) 주요 함수 정의
- 수치형과 범주형 데이터 결측치의 보간에 관한 함수를 정의한다.
def fill_missing(df, cols, val):
""" val 입력값을 넣는다. """
for col in cols:
df[col] = df[col].fillna(val)
def fill_missing_with_mode(df, cols):
""" 최대 빈도수를 넣는다. """
for col in cols:
df[col] = df[col].fillna(df[col].mode()[0])
def addlogs(res, cols):
""" 로그 변환 """
m = res.shape[1]
for c in cols:
res = res.assign(newcol=pd.Series(np.log(1.01+res[c])).values)
res.columns.values[m] = c + '_log'
m += 1
return res
- 1층, 2층, 3층의 면적을 합친
전체 total을 구해본다.
(5) 전체 면적 데이터 추가
- 가정의 전체 면적을 더해서 추가 변수를 만든다.
df_train['TotalSF'] = df_train['TotalBsmtSF'] + df_train['my1stFlrSF'] + df_train['my2ndFlrSF']
- 전체 수치형 데이터에
log transformation을 해준다.
loglist = ['LotFrontage','LotArea','MasVnrArea','BsmtFinSF1','BsmtFinSF2','BsmtUnfSF',
'TotalBsmtSF','my1stFlrSF','my2ndFlrSF','LowQualFinSF','GrLivArea',
'BsmtFullBath','BsmtHalfBath','FullBath','HalfBath','BedroomAbvGr','KitchenAbvGr',
'TotRmsAbvGrd','Fireplaces','GarageCars','GarageArea','WoodDeckSF','OpenPorchSF',
'EnclosedPorch','my3SsnPorch','ScreenPorch','PoolArea','MiscVal','YearRemodAdd','TotalSF']
df_train = addlogs(df_train, loglist)
(6) 타겟변수 로그변환
- 데이터가 작기 때문에, 모형의 안정성을 위해 로그변환을 해준다.
df_train["SalePrice"] = np.log1p(df_train["SalePrice"])
(7) 결측치 데이터 보간
- 결측치 데이터를 보간한다.
# 우선, 결측치가 있는 것 중, 범주형 데이터는 "None"으로 확인
fill_missing(df_train, ["PoolQC", "MiscFeature", "Alley", "Fence", "FireplaceQu",
"GarageType", "GarageFinish", "GarageQual", "GarageCond",
'BsmtQual', 'BsmtCond', 'BsmtExposure', 'BsmtFinType1', 'BsmtFinType2',
"MasVnrType", "MSSubClass"], "None")
# 수치형 데이터는 0으로 보간
fill_missing(df_train, ["GarageYrBlt", "GarageArea", "GarageCars",
'BsmtFinSF1', 'BsmtFinSF2', 'BsmtUnfSF','TotalBsmtSF', 'BsmtFullBath', 'BsmtHalfBath',
"MasVnrArea"], 0)
# 그 중, 일부는 빈도수로 채워 넣는다.
fill_missing_with_mode(df_train, ["MSZoning", "KitchenQual", "Exterior1st", "Exterior2nd", "SaleType"])
fill_missing(df_train, ["Functional"],"Typ")
(8) 변수 삭제
- 1개의 값만 존재하는 데이터는 삭제한다.
df_train.drop(['Utilities'], axis=1, inplace=True)
(9) 이상치 제거
- 적은 데이터에서 상위 또는 하위 이상치가 발생하는 것은 좋지 않다. 따라서, 해당 관측치는 제거한다.
df_train.drop(df_train[(df_train['OverallQual']<5) & (df_train['SalePrice']>200000)].index, inplace=True)
df_train.drop(df_train[(df_train['GrLivArea']>4000) & (df_train['SalePrice']<300000)].index, inplace=True)
df_train.reset_index(drop=True, inplace=True)
(10) 재범주화
- 몇몇 수치형 데이터는 사실 범주형 데이터에 가깝다.
- 따라서, 이를 문자형으로 바꾼다.
df_train['MSSubClass'] = df_train['MSSubClass'].apply(str)
df_train['YrSold'] = df_train['YrSold'].astype(str)
df_train['MoSold'] = df_train['MoSold'].astype(str)
(11) 범주형 데이터 다루기
- 이제 범주형 데이터를 원핫 인코딩으로 변환한다.
- 원핫 인코딩으로 변환하는 이유는, 알고리즘은 수치형으로 되어 있기 때문에 그렇다.
def fix_missing_cols(in_train, in_test):
missing_cols = set(in_train.columns) - set(in_test.columns)
# 테스트 데이터와 훈련 데이터의 컬럼을 동일하게 하는 코드는 작성한다.
for c in missing_cols:
in_test[c] = 0
# 순서를 동일하게 만든다.
in_test = in_test[in_train.columns]
return in_test
def dummy_encode(in_df_train, in_df_test):
df_train = in_df_train
df_test = in_df_test
categorical_feats = [
f for f in df_train.columns if df_train[f].dtype == 'object'
]
print(categorical_feats)
for f_ in categorical_feats:
prefix = f_
df_train = pd.concat([df_train, pd.get_dummies(df_train[f_], prefix=prefix)], axis=1).drop(f_, axis=1)
df_test = pd.concat([df_test, pd.get_dummies(df_test[f_], prefix=prefix)], axis=1).drop(f_, axis=1)
df_test = fix_missing_cols(df_train, df_test)
return df_train, df_test
- 훈련 데이터와 테스트 데이터의 크기가 다르면 예측 시, 에러가 발생한다.
df_train, df_test = dummy_encode(df_train, df_test)
print("Shape train: %s, test: %s" % (df_train.shape, df_test.shape))
['MSSubClass', 'MSZoning', 'Street', 'Alley', 'LotShape', 'LandContour', 'LotConfig', 'LandSlope', 'Neighborhood', 'Condition1', 'Condition2', 'BldgType', 'HouseStyle', 'RoofStyle', 'RoofMatl', 'Exterior1st', 'Exterior2nd', 'MasVnrType', 'ExterQual', 'ExterCond', 'Foundation', 'BsmtQual', 'BsmtCond', 'BsmtExposure', 'BsmtFinType1', 'BsmtFinType2', 'Heating', 'HeatingQC', 'CentralAir', 'Electrical', 'KitchenQual', 'Functional', 'FireplaceQu', 'GarageType', 'GarageFinish', 'GarageQual', 'GarageCond', 'PavedDrive', 'PoolQC', 'Fence', 'MiscFeature', 'MoSold', 'YrSold', 'SaleType', 'SaleCondition']
Shape train: (1456, 361), test: (1459, 361)
III. 머신러닝 모형 개발
- 이제
LightGBM을 활용하여 머신러닝 모형을 개발한다.
(1) 종속변수 처리
- 종속변수를
y객체로 저장한다.
y = df_train["SalePrice"]
y.sample(3)
741 11.686887
1032 12.959541
1169 11.896833
Name: SalePrice, dtype: float64
- 훈련 및 테스트 데이터의 변수를 삭제한다.
df_train.drop(["SalePrice"], axis=1, inplace=True)
df_test.drop(["SalePrice"], axis=1, inplace=True)
print("Shape train: %s, test: %s" % (df_train.shape, df_test.shape))
Shape train: (1456, 360), test: (1459, 360)
(2) 데이터셋 분리
- 데이터셋을 분리한다.
X_train, X_test, y_train, y_test = train_test_split( df_train, y, test_size=0.2, random_state=42)
(3) LightGBM 파라미터 정의
LightGBM파라미터 정의는 다음 메뉴얼을 읽고 적용한다.- LightGBM 파라미터 메뉴얼
hyper_params = {
'task': 'train',
'boosting_type': 'gbdt',
'objective': 'regression',
'metric': ['l2', 'auc'],
'learning_rate': 0.005,
'feature_fraction': 0.9,
'bagging_fraction': 0.7,
'bagging_freq': 10,
'verbose': 0,
"max_depth": 8,
"num_leaves": 128,
"max_bin": 512,
"num_iterations": 100000,
"n_estimators": 1000
}
(4) 모델 정의
- 이제 모델을 정의한다.
gbm = lgb.LGBMRegressor(**hyper_params)
(5) 모델 학습
- 이제 모델을 학습한다.
gbm.fit(X_train, y_train,
eval_set=[(X_test, y_test)],
eval_metric='l1',
early_stopping_rounds=1000)
/usr/local/lib/python3.6/dist-packages/lightgbm/engine.py:118: UserWarning: Found `num_iterations` in params. Will use it instead of argument
warnings.warn("Found `{}` in params. Will use it instead of argument".format(alias))
[1] valid_0's l2: 0.186477 valid_0's auc: 1 valid_0's l1: 0.333038
Training until validation scores don't improve for 1000 rounds.
[2] valid_0's l2: 0.185073 valid_0's auc: 1 valid_0's l1: 0.331606
[3] valid_0's l2: 0.183684 valid_0's auc: 1 valid_0's l1: 0.330192
[4] valid_0's l2: 0.18231 valid_0's auc: 1 valid_0's l1: 0.328797
[5] valid_0's l2: 0.18095 valid_0's auc: 1 valid_0's l1: 0.327404
[6] valid_0's l2: 0.179603 valid_0's auc: 1 valid_0's l1: 0.326023
[7] valid_0's l2: 0.17828 valid_0's auc: 1 valid_0's l1: 0.324652
[8] valid_0's l2: 0.176947 valid_0's auc: 1 valid_0's l1: 0.323279
[9] valid_0's l2: 0.175652 valid_0's auc: 1 valid_0's l1: 0.321952
[10] valid_0's l2: 0.174352 valid_0's auc: 1 valid_0's l1: 0.320633
[11] valid_0's l2: 0.172985 valid_0's auc: 1 valid_0's l1: 0.319239
[12] valid_0's l2: 0.171633 valid_0's auc: 1 valid_0's l1: 0.317859
[13] valid_0's l2: 0.170309 valid_0's auc: 1 valid_0's l1: 0.316502
[14] valid_0's l2: 0.16898 valid_0's auc: 1 valid_0's l1: 0.315116
[15] valid_0's l2: 0.167683 valid_0's auc: 1 valid_0's l1: 0.313772
[16] valid_0's l2: 0.166394 valid_0's auc: 1 valid_0's l1: 0.31242
[17] valid_0's l2: 0.165107 valid_0's auc: 1 valid_0's l1: 0.311063
[18] valid_0's l2: 0.163844 valid_0's auc: 1 valid_0's l1: 0.309722
[19] valid_0's l2: 0.162577 valid_0's auc: 1 valid_0's l1: 0.308362
[20] valid_0's l2: 0.16135 valid_0's auc: 1 valid_0's l1: 0.307035
[21] valid_0's l2: 0.160154 valid_0's auc: 1 valid_0's l1: 0.30574
[22] valid_0's l2: 0.158952 valid_0's auc: 1 valid_0's l1: 0.304455
[23] valid_0's l2: 0.157766 valid_0's auc: 1 valid_0's l1: 0.303184
[24] valid_0's l2: 0.156588 valid_0's auc: 1 valid_0's l1: 0.301915
[25] valid_0's l2: 0.155422 valid_0's auc: 1 valid_0's l1: 0.300652
[26] valid_0's l2: 0.154271 valid_0's auc: 1 valid_0's l1: 0.299401
[27] valid_0's l2: 0.153128 valid_0's auc: 1 valid_0's l1: 0.29816
[28] valid_0's l2: 0.152007 valid_0's auc: 1 valid_0's l1: 0.296939
[29] valid_0's l2: 0.150886 valid_0's auc: 1 valid_0's l1: 0.29571
[30] valid_0's l2: 0.149777 valid_0's auc: 1 valid_0's l1: 0.294487
[31] valid_0's l2: 0.14867 valid_0's auc: 1 valid_0's l1: 0.293253
[32] valid_0's l2: 0.147577 valid_0's auc: 1 valid_0's l1: 0.292036
[33] valid_0's l2: 0.146476 valid_0's auc: 1 valid_0's l1: 0.290788
[34] valid_0's l2: 0.145403 valid_0's auc: 1 valid_0's l1: 0.289586
[35] valid_0's l2: 0.144338 valid_0's auc: 1 valid_0's l1: 0.288388
[36] valid_0's l2: 0.143281 valid_0's auc: 1 valid_0's l1: 0.287178
[37] valid_0's l2: 0.14225 valid_0's auc: 1 valid_0's l1: 0.286005
[38] valid_0's l2: 0.141221 valid_0's auc: 1 valid_0's l1: 0.284832
[39] valid_0's l2: 0.140209 valid_0's auc: 1 valid_0's l1: 0.283683
[40] valid_0's l2: 0.139199 valid_0's auc: 1 valid_0's l1: 0.282515
[41] valid_0's l2: 0.138212 valid_0's auc: 1 valid_0's l1: 0.28136
[42] valid_0's l2: 0.13724 valid_0's auc: 1 valid_0's l1: 0.280197
[43] valid_0's l2: 0.136299 valid_0's auc: 1 valid_0's l1: 0.279079
[44] valid_0's l2: 0.135336 valid_0's auc: 1 valid_0's l1: 0.277933
[45] valid_0's l2: 0.134398 valid_0's auc: 1 valid_0's l1: 0.276826
[46] valid_0's l2: 0.133457 valid_0's auc: 1 valid_0's l1: 0.275697
[47] valid_0's l2: 0.132536 valid_0's auc: 1 valid_0's l1: 0.274587
[48] valid_0's l2: 0.131645 valid_0's auc: 1 valid_0's l1: 0.273479
[49] valid_0's l2: 0.130738 valid_0's auc: 1 valid_0's l1: 0.272353
[50] valid_0's l2: 0.129837 valid_0's auc: 1 valid_0's l1: 0.271238
[51] valid_0's l2: 0.128927 valid_0's auc: 1 valid_0's l1: 0.270164
[52] valid_0's l2: 0.128026 valid_0's auc: 1 valid_0's l1: 0.269095
[53] valid_0's l2: 0.127123 valid_0's auc: 1 valid_0's l1: 0.267999
[54] valid_0's l2: 0.126228 valid_0's auc: 1 valid_0's l1: 0.266909
[55] valid_0's l2: 0.125343 valid_0's auc: 1 valid_0's l1: 0.265823
[56] valid_0's l2: 0.124466 valid_0's auc: 1 valid_0's l1: 0.264745
[57] valid_0's l2: 0.123598 valid_0's auc: 1 valid_0's l1: 0.263674
[58] valid_0's l2: 0.122749 valid_0's auc: 1 valid_0's l1: 0.262641
[59] valid_0's l2: 0.121909 valid_0's auc: 1 valid_0's l1: 0.261613
[60] valid_0's l2: 0.121066 valid_0's auc: 1 valid_0's l1: 0.260558
[61] valid_0's l2: 0.120198 valid_0's auc: 1 valid_0's l1: 0.259479
[62] valid_0's l2: 0.119359 valid_0's auc: 1 valid_0's l1: 0.258394
[63] valid_0's l2: 0.118533 valid_0's auc: 1 valid_0's l1: 0.25732
[64] valid_0's l2: 0.117703 valid_0's auc: 1 valid_0's l1: 0.25624
[65] valid_0's l2: 0.116867 valid_0's auc: 1 valid_0's l1: 0.255183
[66] valid_0's l2: 0.11604 valid_0's auc: 1 valid_0's l1: 0.254131
[67] valid_0's l2: 0.115221 valid_0's auc: 1 valid_0's l1: 0.253082
[68] valid_0's l2: 0.114427 valid_0's auc: 1 valid_0's l1: 0.252033
[69] valid_0's l2: 0.113636 valid_0's auc: 1 valid_0's l1: 0.251022
[70] valid_0's l2: 0.112841 valid_0's auc: 1 valid_0's l1: 0.249995
[71] valid_0's l2: 0.112099 valid_0's auc: 1 valid_0's l1: 0.249042
[72] valid_0's l2: 0.111356 valid_0's auc: 1 valid_0's l1: 0.248066
[73] valid_0's l2: 0.110633 valid_0's auc: 1 valid_0's l1: 0.247137
[74] valid_0's l2: 0.109927 valid_0's auc: 1 valid_0's l1: 0.246213
[75] valid_0's l2: 0.109217 valid_0's auc: 1 valid_0's l1: 0.245305
[76] valid_0's l2: 0.108526 valid_0's auc: 1 valid_0's l1: 0.244404
[77] valid_0's l2: 0.107828 valid_0's auc: 1 valid_0's l1: 0.243503
[78] valid_0's l2: 0.107142 valid_0's auc: 1 valid_0's l1: 0.24262
[79] valid_0's l2: 0.106454 valid_0's auc: 1 valid_0's l1: 0.24171
[80] valid_0's l2: 0.105774 valid_0's auc: 1 valid_0's l1: 0.240835
[81] valid_0's l2: 0.105113 valid_0's auc: 1 valid_0's l1: 0.239931
[82] valid_0's l2: 0.10445 valid_0's auc: 1 valid_0's l1: 0.239013
[83] valid_0's l2: 0.103802 valid_0's auc: 1 valid_0's l1: 0.238121
[84] valid_0's l2: 0.103149 valid_0's auc: 1 valid_0's l1: 0.237229
[85] valid_0's l2: 0.102513 valid_0's auc: 1 valid_0's l1: 0.236346
[86] valid_0's l2: 0.101873 valid_0's auc: 1 valid_0's l1: 0.235464
[87] valid_0's l2: 0.101239 valid_0's auc: 1 valid_0's l1: 0.234595
[88] valid_0's l2: 0.100623 valid_0's auc: 1 valid_0's l1: 0.233723
[89] valid_0's l2: 0.10003 valid_0's auc: 1 valid_0's l1: 0.232923
[90] valid_0's l2: 0.0994325 valid_0's auc: 1 valid_0's l1: 0.232081
[91] valid_0's l2: 0.0988341 valid_0's auc: 1 valid_0's l1: 0.231256
[92] valid_0's l2: 0.0982427 valid_0's auc: 1 valid_0's l1: 0.23043
[93] valid_0's l2: 0.0976575 valid_0's auc: 1 valid_0's l1: 0.229611
[94] valid_0's l2: 0.0970764 valid_0's auc: 1 valid_0's l1: 0.228802
[95] valid_0's l2: 0.0964998 valid_0's auc: 1 valid_0's l1: 0.227986
[96] valid_0's l2: 0.0959351 valid_0's auc: 1 valid_0's l1: 0.227177
[97] valid_0's l2: 0.0953646 valid_0's auc: 1 valid_0's l1: 0.226367
[98] valid_0's l2: 0.0948064 valid_0's auc: 1 valid_0's l1: 0.225571
[99] valid_0's l2: 0.0942486 valid_0's auc: 1 valid_0's l1: 0.224767
[100] valid_0's l2: 0.0937024 valid_0's auc: 1 valid_0's l1: 0.223984
[101] valid_0's l2: 0.0931472 valid_0's auc: 1 valid_0's l1: 0.223225
[102] valid_0's l2: 0.0925974 valid_0's auc: 1 valid_0's l1: 0.222479
[103] valid_0's l2: 0.0920528 valid_0's auc: 1 valid_0's l1: 0.221736
[104] valid_0's l2: 0.0915138 valid_0's auc: 1 valid_0's l1: 0.221
[105] valid_0's l2: 0.0909796 valid_0's auc: 1 valid_0's l1: 0.220276
[106] valid_0's l2: 0.090451 valid_0's auc: 1 valid_0's l1: 0.219556
[107] valid_0's l2: 0.0899295 valid_0's auc: 1 valid_0's l1: 0.218826
[108] valid_0's l2: 0.0894069 valid_0's auc: 1 valid_0's l1: 0.218104
[109] valid_0's l2: 0.088892 valid_0's auc: 1 valid_0's l1: 0.217398
[110] valid_0's l2: 0.0883824 valid_0's auc: 1 valid_0's l1: 0.216633
[111] valid_0's l2: 0.0878517 valid_0's auc: 1 valid_0's l1: 0.215829
[112] valid_0's l2: 0.0873278 valid_0's auc: 1 valid_0's l1: 0.215036
[113] valid_0's l2: 0.0868143 valid_0's auc: 1 valid_0's l1: 0.214272
[114] valid_0's l2: 0.0863019 valid_0's auc: 1 valid_0's l1: 0.21351
[115] valid_0's l2: 0.0857982 valid_0's auc: 1 valid_0's l1: 0.212764
[116] valid_0's l2: 0.0853065 valid_0's auc: 1 valid_0's l1: 0.212028
[117] valid_0's l2: 0.0848346 valid_0's auc: 1 valid_0's l1: 0.211302
[118] valid_0's l2: 0.0843538 valid_0's auc: 1 valid_0's l1: 0.210594
[119] valid_0's l2: 0.0838739 valid_0's auc: 1 valid_0's l1: 0.209875
[120] valid_0's l2: 0.0833984 valid_0's auc: 1 valid_0's l1: 0.209173
[121] valid_0's l2: 0.0829321 valid_0's auc: 1 valid_0's l1: 0.208462
[122] valid_0's l2: 0.0824703 valid_0's auc: 1 valid_0's l1: 0.207756
[123] valid_0's l2: 0.0820144 valid_0's auc: 1 valid_0's l1: 0.207066
[124] valid_0's l2: 0.081551 valid_0's auc: 1 valid_0's l1: 0.206367
[125] valid_0's l2: 0.0811024 valid_0's auc: 1 valid_0's l1: 0.205677
[126] valid_0's l2: 0.0806537 valid_0's auc: 1 valid_0's l1: 0.204991
[127] valid_0's l2: 0.0802125 valid_0's auc: 1 valid_0's l1: 0.2043
[128] valid_0's l2: 0.0797764 valid_0's auc: 1 valid_0's l1: 0.203624
[129] valid_0's l2: 0.0793265 valid_0's auc: 1 valid_0's l1: 0.202944
[130] valid_0's l2: 0.0788984 valid_0's auc: 1 valid_0's l1: 0.202282
[131] valid_0's l2: 0.0784813 valid_0's auc: 1 valid_0's l1: 0.201642
[132] valid_0's l2: 0.0780612 valid_0's auc: 1 valid_0's l1: 0.200997
[133] valid_0's l2: 0.0776434 valid_0's auc: 1 valid_0's l1: 0.20035
[134] valid_0's l2: 0.0772287 valid_0's auc: 1 valid_0's l1: 0.199709
[135] valid_0's l2: 0.076818 valid_0's auc: 1 valid_0's l1: 0.199071
[136] valid_0's l2: 0.0764078 valid_0's auc: 1 valid_0's l1: 0.198426
[137] valid_0's l2: 0.0760052 valid_0's auc: 1 valid_0's l1: 0.197792
[138] valid_0's l2: 0.0756034 valid_0's auc: 1 valid_0's l1: 0.197156
[139] valid_0's l2: 0.0752056 valid_0's auc: 1 valid_0's l1: 0.196522
[140] valid_0's l2: 0.0748172 valid_0's auc: 1 valid_0's l1: 0.195911
[141] valid_0's l2: 0.0744102 valid_0's auc: 1 valid_0's l1: 0.195286
[142] valid_0's l2: 0.0740071 valid_0's auc: 1 valid_0's l1: 0.194664
[143] valid_0's l2: 0.0735927 valid_0's auc: 1 valid_0's l1: 0.194012
[144] valid_0's l2: 0.0731805 valid_0's auc: 1 valid_0's l1: 0.193362
[145] valid_0's l2: 0.072793 valid_0's auc: 1 valid_0's l1: 0.192765
[146] valid_0's l2: 0.0723862 valid_0's auc: 1 valid_0's l1: 0.192119
[147] valid_0's l2: 0.0719923 valid_0's auc: 1 valid_0's l1: 0.191507
[148] valid_0's l2: 0.0715889 valid_0's auc: 1 valid_0's l1: 0.190867
[149] valid_0's l2: 0.0712158 valid_0's auc: 1 valid_0's l1: 0.190288
[150] valid_0's l2: 0.0708594 valid_0's auc: 1 valid_0's l1: 0.189705
[151] valid_0's l2: 0.070493 valid_0's auc: 1 valid_0's l1: 0.189144
[152] valid_0's l2: 0.0701238 valid_0's auc: 1 valid_0's l1: 0.188579
[153] valid_0's l2: 0.0697602 valid_0's auc: 1 valid_0's l1: 0.188021
[154] valid_0's l2: 0.0693983 valid_0's auc: 1 valid_0's l1: 0.187461
[155] valid_0's l2: 0.0690326 valid_0's auc: 1 valid_0's l1: 0.186898
[156] valid_0's l2: 0.0686763 valid_0's auc: 1 valid_0's l1: 0.186344
[157] valid_0's l2: 0.0683329 valid_0's auc: 1 valid_0's l1: 0.185798
[158] valid_0's l2: 0.0679865 valid_0's auc: 1 valid_0's l1: 0.185262
[159] valid_0's l2: 0.0676413 valid_0's auc: 1 valid_0's l1: 0.184716
[160] valid_0's l2: 0.0672995 valid_0's auc: 1 valid_0's l1: 0.184178
[161] valid_0's l2: 0.066948 valid_0's auc: 1 valid_0's l1: 0.183626
[162] valid_0's l2: 0.0666073 valid_0's auc: 1 valid_0's l1: 0.18307
[163] valid_0's l2: 0.0662621 valid_0's auc: 1 valid_0's l1: 0.182523
[164] valid_0's l2: 0.0659206 valid_0's auc: 1 valid_0's l1: 0.181984
[165] valid_0's l2: 0.0655801 valid_0's auc: 1 valid_0's l1: 0.181447
[166] valid_0's l2: 0.0652426 valid_0's auc: 1 valid_0's l1: 0.180916
[167] valid_0's l2: 0.0649108 valid_0's auc: 1 valid_0's l1: 0.18039
[168] valid_0's l2: 0.0645769 valid_0's auc: 1 valid_0's l1: 0.179857
[169] valid_0's l2: 0.0642507 valid_0's auc: 1 valid_0's l1: 0.179335
[170] valid_0's l2: 0.0639258 valid_0's auc: 1 valid_0's l1: 0.178825
[171] valid_0's l2: 0.0636088 valid_0's auc: 1 valid_0's l1: 0.178301
[172] valid_0's l2: 0.0632884 valid_0's auc: 1 valid_0's l1: 0.177774
[173] valid_0's l2: 0.0629678 valid_0's auc: 1 valid_0's l1: 0.177252
[174] valid_0's l2: 0.0626559 valid_0's auc: 1 valid_0's l1: 0.176743
[175] valid_0's l2: 0.0623445 valid_0's auc: 1 valid_0's l1: 0.176224
[176] valid_0's l2: 0.0620368 valid_0's auc: 1 valid_0's l1: 0.175713
[177] valid_0's l2: 0.0617362 valid_0's auc: 1 valid_0's l1: 0.175246
[178] valid_0's l2: 0.0614374 valid_0's auc: 1 valid_0's l1: 0.174753
[179] valid_0's l2: 0.0611418 valid_0's auc: 1 valid_0's l1: 0.174268
[180] valid_0's l2: 0.0608452 valid_0's auc: 1 valid_0's l1: 0.173767
[181] valid_0's l2: 0.0605311 valid_0's auc: 1 valid_0's l1: 0.173259
[182] valid_0's l2: 0.0602465 valid_0's auc: 1 valid_0's l1: 0.172779
[183] valid_0's l2: 0.0599334 valid_0's auc: 1 valid_0's l1: 0.172268
[184] valid_0's l2: 0.0596255 valid_0's auc: 1 valid_0's l1: 0.171752
[185] valid_0's l2: 0.0593249 valid_0's auc: 1 valid_0's l1: 0.171256
[186] valid_0's l2: 0.0590197 valid_0's auc: 1 valid_0's l1: 0.170737
[187] valid_0's l2: 0.0587211 valid_0's auc: 1 valid_0's l1: 0.170229
[188] valid_0's l2: 0.0584267 valid_0's auc: 1 valid_0's l1: 0.169738
[189] valid_0's l2: 0.0581327 valid_0's auc: 1 valid_0's l1: 0.169229
[190] valid_0's l2: 0.0578475 valid_0's auc: 1 valid_0's l1: 0.168741
[191] valid_0's l2: 0.0575943 valid_0's auc: 1 valid_0's l1: 0.16832
[192] valid_0's l2: 0.057342 valid_0's auc: 1 valid_0's l1: 0.167893
[193] valid_0's l2: 0.0570979 valid_0's auc: 1 valid_0's l1: 0.167463
[194] valid_0's l2: 0.0568503 valid_0's auc: 1 valid_0's l1: 0.167043
[195] valid_0's l2: 0.0566055 valid_0's auc: 1 valid_0's l1: 0.166605
[196] valid_0's l2: 0.0563625 valid_0's auc: 1 valid_0's l1: 0.166189
[197] valid_0's l2: 0.0561224 valid_0's auc: 1 valid_0's l1: 0.165779
[198] valid_0's l2: 0.0558846 valid_0's auc: 1 valid_0's l1: 0.165372
[199] valid_0's l2: 0.055649 valid_0's auc: 1 valid_0's l1: 0.164966
[200] valid_0's l2: 0.0554041 valid_0's auc: 1 valid_0's l1: 0.164528
[201] valid_0's l2: 0.0551436 valid_0's auc: 1 valid_0's l1: 0.164053
[202] valid_0's l2: 0.0548906 valid_0's auc: 1 valid_0's l1: 0.163601
[203] valid_0's l2: 0.0546344 valid_0's auc: 1 valid_0's l1: 0.163138
[204] valid_0's l2: 0.0543889 valid_0's auc: 1 valid_0's l1: 0.162662
[205] valid_0's l2: 0.0541447 valid_0's auc: 1 valid_0's l1: 0.162211
[206] valid_0's l2: 0.0539034 valid_0's auc: 1 valid_0's l1: 0.161763
[207] valid_0's l2: 0.0536569 valid_0's auc: 1 valid_0's l1: 0.161301
[208] valid_0's l2: 0.0534192 valid_0's auc: 1 valid_0's l1: 0.160861
[209] valid_0's l2: 0.0531823 valid_0's auc: 1 valid_0's l1: 0.160427
[210] valid_0's l2: 0.0529445 valid_0's auc: 1 valid_0's l1: 0.159991
[211] valid_0's l2: 0.0527023 valid_0's auc: 1 valid_0's l1: 0.159558
[212] valid_0's l2: 0.0524749 valid_0's auc: 1 valid_0's l1: 0.15915
[213] valid_0's l2: 0.0522381 valid_0's auc: 1 valid_0's l1: 0.158726
[214] valid_0's l2: 0.052006 valid_0's auc: 1 valid_0's l1: 0.15833
[215] valid_0's l2: 0.0517811 valid_0's auc: 1 valid_0's l1: 0.157918
[216] valid_0's l2: 0.0515663 valid_0's auc: 1 valid_0's l1: 0.157489
[217] valid_0's l2: 0.051345 valid_0's auc: 1 valid_0's l1: 0.157082
[218] valid_0's l2: 0.051122 valid_0's auc: 1 valid_0's l1: 0.156698
[219] valid_0's l2: 0.0509057 valid_0's auc: 1 valid_0's l1: 0.156298
[220] valid_0's l2: 0.0506877 valid_0's auc: 1 valid_0's l1: 0.155889
[221] valid_0's l2: 0.0504668 valid_0's auc: 1 valid_0's l1: 0.155489
[222] valid_0's l2: 0.0502482 valid_0's auc: 1 valid_0's l1: 0.155093
[223] valid_0's l2: 0.0500318 valid_0's auc: 1 valid_0's l1: 0.154697
[224] valid_0's l2: 0.0498198 valid_0's auc: 1 valid_0's l1: 0.154318
[225] valid_0's l2: 0.0496099 valid_0's auc: 1 valid_0's l1: 0.153933
[226] valid_0's l2: 0.0493988 valid_0's auc: 1 valid_0's l1: 0.153537
[227] valid_0's l2: 0.0491889 valid_0's auc: 1 valid_0's l1: 0.15317
[228] valid_0's l2: 0.048986 valid_0's auc: 1 valid_0's l1: 0.152792
[229] valid_0's l2: 0.0487852 valid_0's auc: 1 valid_0's l1: 0.152413
[230] valid_0's l2: 0.0485813 valid_0's auc: 1 valid_0's l1: 0.15203
[231] valid_0's l2: 0.0483812 valid_0's auc: 1 valid_0's l1: 0.151631
[232] valid_0's l2: 0.0481991 valid_0's auc: 1 valid_0's l1: 0.151286
[233] valid_0's l2: 0.0480033 valid_0's auc: 1 valid_0's l1: 0.150891
[234] valid_0's l2: 0.0478077 valid_0's auc: 1 valid_0's l1: 0.150495
[235] valid_0's l2: 0.0476157 valid_0's auc: 1 valid_0's l1: 0.150104
[236] valid_0's l2: 0.047424 valid_0's auc: 1 valid_0's l1: 0.149712
[237] valid_0's l2: 0.0472362 valid_0's auc: 1 valid_0's l1: 0.149326
[238] valid_0's l2: 0.0470503 valid_0's auc: 1 valid_0's l1: 0.148942
[239] valid_0's l2: 0.0468671 valid_0's auc: 1 valid_0's l1: 0.148568
[240] valid_0's l2: 0.046683 valid_0's auc: 1 valid_0's l1: 0.14819
[241] valid_0's l2: 0.0465001 valid_0's auc: 1 valid_0's l1: 0.147844
[242] valid_0's l2: 0.0463296 valid_0's auc: 1 valid_0's l1: 0.147511
[243] valid_0's l2: 0.0461576 valid_0's auc: 1 valid_0's l1: 0.147177
[244] valid_0's l2: 0.0459868 valid_0's auc: 1 valid_0's l1: 0.146845
[245] valid_0's l2: 0.0458166 valid_0's auc: 1 valid_0's l1: 0.14651
[246] valid_0's l2: 0.0456529 valid_0's auc: 1 valid_0's l1: 0.146188
[247] valid_0's l2: 0.0454948 valid_0's auc: 1 valid_0's l1: 0.145862
[248] valid_0's l2: 0.045335 valid_0's auc: 1 valid_0's l1: 0.145548
[249] valid_0's l2: 0.0451577 valid_0's auc: 1 valid_0's l1: 0.145199
[250] valid_0's l2: 0.0450023 valid_0's auc: 1 valid_0's l1: 0.144888
[251] valid_0's l2: 0.0448452 valid_0's auc: 1 valid_0's l1: 0.144573
[252] valid_0's l2: 0.044689 valid_0's auc: 1 valid_0's l1: 0.144258
[253] valid_0's l2: 0.0445356 valid_0's auc: 1 valid_0's l1: 0.143953
[254] valid_0's l2: 0.044386 valid_0's auc: 1 valid_0's l1: 0.143649
[255] valid_0's l2: 0.0442349 valid_0's auc: 1 valid_0's l1: 0.143349
[256] valid_0's l2: 0.0440847 valid_0's auc: 1 valid_0's l1: 0.143044
[257] valid_0's l2: 0.0439355 valid_0's auc: 1 valid_0's l1: 0.142746
[258] valid_0's l2: 0.0437919 valid_0's auc: 1 valid_0's l1: 0.142444
[259] valid_0's l2: 0.0436486 valid_0's auc: 1 valid_0's l1: 0.142152
[260] valid_0's l2: 0.0435075 valid_0's auc: 1 valid_0's l1: 0.141866
[261] valid_0's l2: 0.043366 valid_0's auc: 1 valid_0's l1: 0.141571
[262] valid_0's l2: 0.0432263 valid_0's auc: 1 valid_0's l1: 0.141294
[263] valid_0's l2: 0.0430953 valid_0's auc: 1 valid_0's l1: 0.141025
[264] valid_0's l2: 0.0429652 valid_0's auc: 1 valid_0's l1: 0.140755
[265] valid_0's l2: 0.0428411 valid_0's auc: 1 valid_0's l1: 0.140503
[266] valid_0's l2: 0.0427099 valid_0's auc: 1 valid_0's l1: 0.140231
[267] valid_0's l2: 0.0425881 valid_0's auc: 1 valid_0's l1: 0.139983
[268] valid_0's l2: 0.0424586 valid_0's auc: 1 valid_0's l1: 0.139723
[269] valid_0's l2: 0.0423306 valid_0's auc: 1 valid_0's l1: 0.139466
[270] valid_0's l2: 0.0422047 valid_0's auc: 1 valid_0's l1: 0.139213
[271] valid_0's l2: 0.0420666 valid_0's auc: 1 valid_0's l1: 0.13892
[272] valid_0's l2: 0.0419335 valid_0's auc: 1 valid_0's l1: 0.138637
[273] valid_0's l2: 0.0417981 valid_0's auc: 1 valid_0's l1: 0.138348
[274] valid_0's l2: 0.0416665 valid_0's auc: 1 valid_0's l1: 0.138072
[275] valid_0's l2: 0.0415361 valid_0's auc: 1 valid_0's l1: 0.137796
[276] valid_0's l2: 0.0414017 valid_0's auc: 1 valid_0's l1: 0.137511
[277] valid_0's l2: 0.0412752 valid_0's auc: 1 valid_0's l1: 0.137275
[278] valid_0's l2: 0.0411482 valid_0's auc: 1 valid_0's l1: 0.13701
[279] valid_0's l2: 0.0410198 valid_0's auc: 1 valid_0's l1: 0.136739
[280] valid_0's l2: 0.0408946 valid_0's auc: 1 valid_0's l1: 0.136476
[281] valid_0's l2: 0.0407681 valid_0's auc: 1 valid_0's l1: 0.136219
[282] valid_0's l2: 0.0406391 valid_0's auc: 1 valid_0's l1: 0.13596
[283] valid_0's l2: 0.0405189 valid_0's auc: 1 valid_0's l1: 0.135719
[284] valid_0's l2: 0.0403979 valid_0's auc: 1 valid_0's l1: 0.135471
[285] valid_0's l2: 0.0402758 valid_0's auc: 1 valid_0's l1: 0.135227
[286] valid_0's l2: 0.0401568 valid_0's auc: 1 valid_0's l1: 0.134988
[287] valid_0's l2: 0.0400414 valid_0's auc: 1 valid_0's l1: 0.134755
[288] valid_0's l2: 0.0399173 valid_0's auc: 1 valid_0's l1: 0.134522
[289] valid_0's l2: 0.0397983 valid_0's auc: 1 valid_0's l1: 0.1343
[290] valid_0's l2: 0.0396833 valid_0's auc: 1 valid_0's l1: 0.134081
[291] valid_0's l2: 0.0395465 valid_0's auc: 1 valid_0's l1: 0.133805
[292] valid_0's l2: 0.0394119 valid_0's auc: 1 valid_0's l1: 0.133533
[293] valid_0's l2: 0.039279 valid_0's auc: 1 valid_0's l1: 0.133265
[294] valid_0's l2: 0.0391465 valid_0's auc: 1 valid_0's l1: 0.132995
[295] valid_0's l2: 0.0390154 valid_0's auc: 1 valid_0's l1: 0.132727
[296] valid_0's l2: 0.0388867 valid_0's auc: 1 valid_0's l1: 0.132464
[297] valid_0's l2: 0.0387715 valid_0's auc: 1 valid_0's l1: 0.132228
[298] valid_0's l2: 0.0386451 valid_0's auc: 1 valid_0's l1: 0.131969
[299] valid_0's l2: 0.038541 valid_0's auc: 1 valid_0's l1: 0.13177
[300] valid_0's l2: 0.0384281 valid_0's auc: 1 valid_0's l1: 0.131538
[301] valid_0's l2: 0.0383025 valid_0's auc: 1 valid_0's l1: 0.131284
[302] valid_0's l2: 0.0381804 valid_0's auc: 1 valid_0's l1: 0.131033
[303] valid_0's l2: 0.0380598 valid_0's auc: 1 valid_0's l1: 0.130786
[304] valid_0's l2: 0.0379384 valid_0's auc: 1 valid_0's l1: 0.130533
[305] valid_0's l2: 0.0378162 valid_0's auc: 1 valid_0's l1: 0.13028
[306] valid_0's l2: 0.0376992 valid_0's auc: 1 valid_0's l1: 0.130039
[307] valid_0's l2: 0.0375799 valid_0's auc: 1 valid_0's l1: 0.129805
[308] valid_0's l2: 0.0374629 valid_0's auc: 1 valid_0's l1: 0.129566
[309] valid_0's l2: 0.037361 valid_0's auc: 1 valid_0's l1: 0.129365
[310] valid_0's l2: 0.037245 valid_0's auc: 1 valid_0's l1: 0.129135
[311] valid_0's l2: 0.0371502 valid_0's auc: 1 valid_0's l1: 0.128919
[312] valid_0's l2: 0.0370575 valid_0's auc: 1 valid_0's l1: 0.128706
[313] valid_0's l2: 0.0369641 valid_0's auc: 1 valid_0's l1: 0.128499
[314] valid_0's l2: 0.0368739 valid_0's auc: 1 valid_0's l1: 0.128288
[315] valid_0's l2: 0.0367811 valid_0's auc: 1 valid_0's l1: 0.128083
[316] valid_0's l2: 0.0366909 valid_0's auc: 1 valid_0's l1: 0.127882
[317] valid_0's l2: 0.0366029 valid_0's auc: 1 valid_0's l1: 0.127688
[318] valid_0's l2: 0.0365145 valid_0's auc: 1 valid_0's l1: 0.12749
[319] valid_0's l2: 0.0364251 valid_0's auc: 1 valid_0's l1: 0.12729
[320] valid_0's l2: 0.0363346 valid_0's auc: 1 valid_0's l1: 0.127085
[321] valid_0's l2: 0.0362488 valid_0's auc: 1 valid_0's l1: 0.12691
[322] valid_0's l2: 0.0361585 valid_0's auc: 1 valid_0's l1: 0.126726
[323] valid_0's l2: 0.0360754 valid_0's auc: 1 valid_0's l1: 0.126547
[324] valid_0's l2: 0.0359877 valid_0's auc: 1 valid_0's l1: 0.126359
[325] valid_0's l2: 0.0358996 valid_0's auc: 1 valid_0's l1: 0.126185
[326] valid_0's l2: 0.0358118 valid_0's auc: 1 valid_0's l1: 0.126007
[327] valid_0's l2: 0.0357264 valid_0's auc: 1 valid_0's l1: 0.125828
[328] valid_0's l2: 0.0356479 valid_0's auc: 1 valid_0's l1: 0.125666
[329] valid_0's l2: 0.0355716 valid_0's auc: 1 valid_0's l1: 0.125508
[330] valid_0's l2: 0.0354895 valid_0's auc: 1 valid_0's l1: 0.125331
[331] valid_0's l2: 0.0353982 valid_0's auc: 1 valid_0's l1: 0.125127
[332] valid_0's l2: 0.0353077 valid_0's auc: 1 valid_0's l1: 0.124925
[333] valid_0's l2: 0.0352172 valid_0's auc: 1 valid_0's l1: 0.124712
[334] valid_0's l2: 0.0351283 valid_0's auc: 1 valid_0's l1: 0.124511
[335] valid_0's l2: 0.0350401 valid_0's auc: 1 valid_0's l1: 0.124311
[336] valid_0's l2: 0.0349524 valid_0's auc: 1 valid_0's l1: 0.124111
[337] valid_0's l2: 0.0348666 valid_0's auc: 1 valid_0's l1: 0.123909
[338] valid_0's l2: 0.0347844 valid_0's auc: 1 valid_0's l1: 0.123733
[339] valid_0's l2: 0.0346992 valid_0's auc: 1 valid_0's l1: 0.123537
[340] valid_0's l2: 0.0346186 valid_0's auc: 1 valid_0's l1: 0.123367
[341] valid_0's l2: 0.0345239 valid_0's auc: 1 valid_0's l1: 0.123163
[342] valid_0's l2: 0.0344298 valid_0's auc: 1 valid_0's l1: 0.122961
[343] valid_0's l2: 0.0343371 valid_0's auc: 1 valid_0's l1: 0.122759
[344] valid_0's l2: 0.0342451 valid_0's auc: 1 valid_0's l1: 0.122567
[345] valid_0's l2: 0.0341563 valid_0's auc: 1 valid_0's l1: 0.122379
[346] valid_0's l2: 0.0340731 valid_0's auc: 1 valid_0's l1: 0.122217
[347] valid_0's l2: 0.0339864 valid_0's auc: 1 valid_0's l1: 0.122036
[348] valid_0's l2: 0.0339059 valid_0's auc: 1 valid_0's l1: 0.121881
[349] valid_0's l2: 0.0338175 valid_0's auc: 1 valid_0's l1: 0.121692
[350] valid_0's l2: 0.0337391 valid_0's auc: 1 valid_0's l1: 0.121539
[351] valid_0's l2: 0.0336639 valid_0's auc: 1 valid_0's l1: 0.121386
[352] valid_0's l2: 0.0335899 valid_0's auc: 1 valid_0's l1: 0.121236
[353] valid_0's l2: 0.0335224 valid_0's auc: 1 valid_0's l1: 0.121096
[354] valid_0's l2: 0.0334567 valid_0's auc: 1 valid_0's l1: 0.120952
[355] valid_0's l2: 0.033391 valid_0's auc: 1 valid_0's l1: 0.120815
[356] valid_0's l2: 0.033321 valid_0's auc: 1 valid_0's l1: 0.120674
[357] valid_0's l2: 0.033259 valid_0's auc: 1 valid_0's l1: 0.12055
[358] valid_0's l2: 0.0331915 valid_0's auc: 1 valid_0's l1: 0.120415
[359] valid_0's l2: 0.0331222 valid_0's auc: 1 valid_0's l1: 0.120271
[360] valid_0's l2: 0.0330541 valid_0's auc: 1 valid_0's l1: 0.120129
[361] valid_0's l2: 0.0329809 valid_0's auc: 1 valid_0's l1: 0.119979
[362] valid_0's l2: 0.0329058 valid_0's auc: 1 valid_0's l1: 0.119836
[363] valid_0's l2: 0.0328352 valid_0's auc: 1 valid_0's l1: 0.119691
[364] valid_0's l2: 0.0327654 valid_0's auc: 1 valid_0's l1: 0.119552
[365] valid_0's l2: 0.0326968 valid_0's auc: 1 valid_0's l1: 0.119406
[366] valid_0's l2: 0.0326268 valid_0's auc: 1 valid_0's l1: 0.119261
[367] valid_0's l2: 0.0325554 valid_0's auc: 1 valid_0's l1: 0.119117
[368] valid_0's l2: 0.0324874 valid_0's auc: 1 valid_0's l1: 0.118972
[369] valid_0's l2: 0.0324192 valid_0's auc: 1 valid_0's l1: 0.118831
[370] valid_0's l2: 0.0323503 valid_0's auc: 1 valid_0's l1: 0.118694
[371] valid_0's l2: 0.0322917 valid_0's auc: 1 valid_0's l1: 0.118578
[372] valid_0's l2: 0.0322364 valid_0's auc: 1 valid_0's l1: 0.118466
[373] valid_0's l2: 0.0321812 valid_0's auc: 1 valid_0's l1: 0.118361
[374] valid_0's l2: 0.0321266 valid_0's auc: 1 valid_0's l1: 0.118255
[375] valid_0's l2: 0.0320734 valid_0's auc: 1 valid_0's l1: 0.118147
[376] valid_0's l2: 0.03202 valid_0's auc: 1 valid_0's l1: 0.118043
[377] valid_0's l2: 0.0319445 valid_0's auc: 1 valid_0's l1: 0.117875
[378] valid_0's l2: 0.0318652 valid_0's auc: 1 valid_0's l1: 0.117696
[379] valid_0's l2: 0.0317931 valid_0's auc: 1 valid_0's l1: 0.117528
[380] valid_0's l2: 0.0317419 valid_0's auc: 1 valid_0's l1: 0.11742
[381] valid_0's l2: 0.0316841 valid_0's auc: 1 valid_0's l1: 0.117305
[382] valid_0's l2: 0.0316268 valid_0's auc: 1 valid_0's l1: 0.117189
[383] valid_0's l2: 0.0315697 valid_0's auc: 1 valid_0's l1: 0.117058
[384] valid_0's l2: 0.0315134 valid_0's auc: 1 valid_0's l1: 0.116943
[385] valid_0's l2: 0.0314555 valid_0's auc: 1 valid_0's l1: 0.11681
[386] valid_0's l2: 0.0313893 valid_0's auc: 1 valid_0's l1: 0.11665
[387] valid_0's l2: 0.0313257 valid_0's auc: 1 valid_0's l1: 0.116519
[388] valid_0's l2: 0.0312661 valid_0's auc: 1 valid_0's l1: 0.116393
[389] valid_0's l2: 0.0312123 valid_0's auc: 1 valid_0's l1: 0.116295
[390] valid_0's l2: 0.0311575 valid_0's auc: 1 valid_0's l1: 0.116182
[391] valid_0's l2: 0.0310947 valid_0's auc: 1 valid_0's l1: 0.116038
[392] valid_0's l2: 0.0310335 valid_0's auc: 1 valid_0's l1: 0.115899
[393] valid_0's l2: 0.0309703 valid_0's auc: 1 valid_0's l1: 0.11576
[394] valid_0's l2: 0.0309077 valid_0's auc: 1 valid_0's l1: 0.115621
[395] valid_0's l2: 0.0308536 valid_0's auc: 1 valid_0's l1: 0.115483
[396] valid_0's l2: 0.0307937 valid_0's auc: 1 valid_0's l1: 0.115344
[397] valid_0's l2: 0.0307315 valid_0's auc: 1 valid_0's l1: 0.115204
[398] valid_0's l2: 0.0306709 valid_0's auc: 1 valid_0's l1: 0.115071
[399] valid_0's l2: 0.0306094 valid_0's auc: 1 valid_0's l1: 0.114931
[400] valid_0's l2: 0.0305486 valid_0's auc: 1 valid_0's l1: 0.114795
[401] valid_0's l2: 0.0304879 valid_0's auc: 1 valid_0's l1: 0.114679
[402] valid_0's l2: 0.0304395 valid_0's auc: 1 valid_0's l1: 0.114569
[403] valid_0's l2: 0.030391 valid_0's auc: 1 valid_0's l1: 0.114463
[404] valid_0's l2: 0.0303317 valid_0's auc: 1 valid_0's l1: 0.114351
[405] valid_0's l2: 0.0302723 valid_0's auc: 1 valid_0's l1: 0.11425
[406] valid_0's l2: 0.0302237 valid_0's auc: 1 valid_0's l1: 0.114141
[407] valid_0's l2: 0.0301744 valid_0's auc: 1 valid_0's l1: 0.11403
[408] valid_0's l2: 0.0301256 valid_0's auc: 1 valid_0's l1: 0.113928
[409] valid_0's l2: 0.0300773 valid_0's auc: 1 valid_0's l1: 0.113818
[410] valid_0's l2: 0.0300273 valid_0's auc: 1 valid_0's l1: 0.113714
[411] valid_0's l2: 0.029979 valid_0's auc: 1 valid_0's l1: 0.113607
[412] valid_0's l2: 0.0299299 valid_0's auc: 1 valid_0's l1: 0.113498
[413] valid_0's l2: 0.0298811 valid_0's auc: 1 valid_0's l1: 0.11339
[414] valid_0's l2: 0.0298328 valid_0's auc: 1 valid_0's l1: 0.113282
[415] valid_0's l2: 0.029786 valid_0's auc: 1 valid_0's l1: 0.113178
[416] valid_0's l2: 0.0297376 valid_0's auc: 1 valid_0's l1: 0.113062
[417] valid_0's l2: 0.0296906 valid_0's auc: 1 valid_0's l1: 0.112956
[418] valid_0's l2: 0.0296435 valid_0's auc: 1 valid_0's l1: 0.112851
[419] valid_0's l2: 0.0295948 valid_0's auc: 1 valid_0's l1: 0.11274
[420] valid_0's l2: 0.0295482 valid_0's auc: 1 valid_0's l1: 0.112637
[421] valid_0's l2: 0.0295032 valid_0's auc: 1 valid_0's l1: 0.11256
[422] valid_0's l2: 0.0294562 valid_0's auc: 1 valid_0's l1: 0.112473
[423] valid_0's l2: 0.0294136 valid_0's auc: 1 valid_0's l1: 0.112396
[424] valid_0's l2: 0.0293727 valid_0's auc: 1 valid_0's l1: 0.112289
[425] valid_0's l2: 0.0293291 valid_0's auc: 1 valid_0's l1: 0.112182
[426] valid_0's l2: 0.0292863 valid_0's auc: 1 valid_0's l1: 0.112109
[427] valid_0's l2: 0.0292411 valid_0's auc: 1 valid_0's l1: 0.112019
[428] valid_0's l2: 0.0291943 valid_0's auc: 1 valid_0's l1: 0.111934
[429] valid_0's l2: 0.0291602 valid_0's auc: 1 valid_0's l1: 0.111858
[430] valid_0's l2: 0.0291242 valid_0's auc: 1 valid_0's l1: 0.111795
[431] valid_0's l2: 0.0290723 valid_0's auc: 1 valid_0's l1: 0.111672
[432] valid_0's l2: 0.0290289 valid_0's auc: 1 valid_0's l1: 0.111574
[433] valid_0's l2: 0.0289821 valid_0's auc: 1 valid_0's l1: 0.111451
[434] valid_0's l2: 0.028938 valid_0's auc: 1 valid_0's l1: 0.111349
[435] valid_0's l2: 0.0288905 valid_0's auc: 1 valid_0's l1: 0.111238
[436] valid_0's l2: 0.028845 valid_0's auc: 1 valid_0's l1: 0.111127
[437] valid_0's l2: 0.0287988 valid_0's auc: 1 valid_0's l1: 0.111016
[438] valid_0's l2: 0.0287512 valid_0's auc: 1 valid_0's l1: 0.1109
[439] valid_0's l2: 0.028711 valid_0's auc: 1 valid_0's l1: 0.110811
[440] valid_0's l2: 0.0286698 valid_0's auc: 1 valid_0's l1: 0.110716
[441] valid_0's l2: 0.0286214 valid_0's auc: 1 valid_0's l1: 0.110608
[442] valid_0's l2: 0.0285784 valid_0's auc: 1 valid_0's l1: 0.110513
[443] valid_0's l2: 0.0285358 valid_0's auc: 1 valid_0's l1: 0.110418
[444] valid_0's l2: 0.0284936 valid_0's auc: 1 valid_0's l1: 0.110324
[445] valid_0's l2: 0.0284532 valid_0's auc: 1 valid_0's l1: 0.110235
[446] valid_0's l2: 0.0284142 valid_0's auc: 1 valid_0's l1: 0.11015
[447] valid_0's l2: 0.0283756 valid_0's auc: 1 valid_0's l1: 0.110069
[448] valid_0's l2: 0.0283352 valid_0's auc: 1 valid_0's l1: 0.109982
[449] valid_0's l2: 0.0282955 valid_0's auc: 1 valid_0's l1: 0.1099
[450] valid_0's l2: 0.028259 valid_0's auc: 1 valid_0's l1: 0.109817
[451] valid_0's l2: 0.0282255 valid_0's auc: 1 valid_0's l1: 0.109736
[452] valid_0's l2: 0.0281897 valid_0's auc: 1 valid_0's l1: 0.109655
[453] valid_0's l2: 0.0281536 valid_0's auc: 1 valid_0's l1: 0.109583
[454] valid_0's l2: 0.0281179 valid_0's auc: 1 valid_0's l1: 0.109511
[455] valid_0's l2: 0.0280843 valid_0's auc: 1 valid_0's l1: 0.109438
[456] valid_0's l2: 0.02805 valid_0's auc: 1 valid_0's l1: 0.109359
[457] valid_0's l2: 0.0280163 valid_0's auc: 1 valid_0's l1: 0.10928
[458] valid_0's l2: 0.0279852 valid_0's auc: 1 valid_0's l1: 0.109211
[459] valid_0's l2: 0.027952 valid_0's auc: 1 valid_0's l1: 0.109136
[460] valid_0's l2: 0.0279212 valid_0's auc: 1 valid_0's l1: 0.109067
[461] valid_0's l2: 0.0278836 valid_0's auc: 1 valid_0's l1: 0.108997
[462] valid_0's l2: 0.027847 valid_0's auc: 1 valid_0's l1: 0.108922
[463] valid_0's l2: 0.0278072 valid_0's auc: 1 valid_0's l1: 0.108832
[464] valid_0's l2: 0.0277773 valid_0's auc: 1 valid_0's l1: 0.108777
[465] valid_0's l2: 0.0277336 valid_0's auc: 1 valid_0's l1: 0.108683
[466] valid_0's l2: 0.0276914 valid_0's auc: 1 valid_0's l1: 0.108595
[467] valid_0's l2: 0.027646 valid_0's auc: 1 valid_0's l1: 0.108494
[468] valid_0's l2: 0.0276104 valid_0's auc: 1 valid_0's l1: 0.108426
[469] valid_0's l2: 0.0275615 valid_0's auc: 1 valid_0's l1: 0.108298
[470] valid_0's l2: 0.027521 valid_0's auc: 1 valid_0's l1: 0.108198
[471] valid_0's l2: 0.0274906 valid_0's auc: 1 valid_0's l1: 0.108141
[472] valid_0's l2: 0.0274606 valid_0's auc: 1 valid_0's l1: 0.108087
[473] valid_0's l2: 0.0274282 valid_0's auc: 1 valid_0's l1: 0.108022
[474] valid_0's l2: 0.0273949 valid_0's auc: 1 valid_0's l1: 0.107939
[475] valid_0's l2: 0.0273599 valid_0's auc: 1 valid_0's l1: 0.107855
[476] valid_0's l2: 0.027328 valid_0's auc: 1 valid_0's l1: 0.107795
[477] valid_0's l2: 0.0272935 valid_0's auc: 1 valid_0's l1: 0.107712
[478] valid_0's l2: 0.0272658 valid_0's auc: 1 valid_0's l1: 0.107665
[479] valid_0's l2: 0.0272319 valid_0's auc: 1 valid_0's l1: 0.107583
[480] valid_0's l2: 0.0272038 valid_0's auc: 1 valid_0's l1: 0.107527
[481] valid_0's l2: 0.0271715 valid_0's auc: 1 valid_0's l1: 0.107445
[482] valid_0's l2: 0.0271403 valid_0's auc: 1 valid_0's l1: 0.107365
[483] valid_0's l2: 0.0271072 valid_0's auc: 1 valid_0's l1: 0.107284
[484] valid_0's l2: 0.0270767 valid_0's auc: 1 valid_0's l1: 0.107205
[485] valid_0's l2: 0.0270445 valid_0's auc: 1 valid_0's l1: 0.107137
[486] valid_0's l2: 0.0270146 valid_0's auc: 1 valid_0's l1: 0.107078
[487] valid_0's l2: 0.0269845 valid_0's auc: 1 valid_0's l1: 0.106999
[488] valid_0's l2: 0.0269559 valid_0's auc: 1 valid_0's l1: 0.10693
[489] valid_0's l2: 0.0269267 valid_0's auc: 1 valid_0's l1: 0.106849
[490] valid_0's l2: 0.0268974 valid_0's auc: 1 valid_0's l1: 0.106776
[491] valid_0's l2: 0.02687 valid_0's auc: 1 valid_0's l1: 0.106732
[492] valid_0's l2: 0.0268425 valid_0's auc: 1 valid_0's l1: 0.106699
[493] valid_0's l2: 0.0268153 valid_0's auc: 1 valid_0's l1: 0.106677
[494] valid_0's l2: 0.0267889 valid_0's auc: 1 valid_0's l1: 0.106659
[495] valid_0's l2: 0.0267625 valid_0's auc: 1 valid_0's l1: 0.106635
[496] valid_0's l2: 0.0267339 valid_0's auc: 1 valid_0's l1: 0.106587
[497] valid_0's l2: 0.0267083 valid_0's auc: 1 valid_0's l1: 0.106569
[498] valid_0's l2: 0.0266799 valid_0's auc: 1 valid_0's l1: 0.10653
[499] valid_0's l2: 0.0266529 valid_0's auc: 1 valid_0's l1: 0.106485
[500] valid_0's l2: 0.0266273 valid_0's auc: 1 valid_0's l1: 0.106452
[501] valid_0's l2: 0.0266011 valid_0's auc: 1 valid_0's l1: 0.106396
[502] valid_0's l2: 0.0265763 valid_0's auc: 1 valid_0's l1: 0.10634
[503] valid_0's l2: 0.0265525 valid_0's auc: 1 valid_0's l1: 0.106294
[504] valid_0's l2: 0.0265295 valid_0's auc: 1 valid_0's l1: 0.106247
[505] valid_0's l2: 0.0265079 valid_0's auc: 1 valid_0's l1: 0.106197
[506] valid_0's l2: 0.0264831 valid_0's auc: 1 valid_0's l1: 0.106148
[507] valid_0's l2: 0.0264594 valid_0's auc: 1 valid_0's l1: 0.106097
[508] valid_0's l2: 0.0264322 valid_0's auc: 1 valid_0's l1: 0.106045
[509] valid_0's l2: 0.026414 valid_0's auc: 1 valid_0's l1: 0.106009
[510] valid_0's l2: 0.0263932 valid_0's auc: 1 valid_0's l1: 0.105964
[511] valid_0's l2: 0.0263644 valid_0's auc: 1 valid_0's l1: 0.105905
[512] valid_0's l2: 0.0263368 valid_0's auc: 1 valid_0's l1: 0.105855
[513] valid_0's l2: 0.0263058 valid_0's auc: 1 valid_0's l1: 0.105779
[514] valid_0's l2: 0.026272 valid_0's auc: 1 valid_0's l1: 0.105696
[515] valid_0's l2: 0.0262413 valid_0's auc: 1 valid_0's l1: 0.105618
[516] valid_0's l2: 0.0262149 valid_0's auc: 1 valid_0's l1: 0.105571
[517] valid_0's l2: 0.0261888 valid_0's auc: 1 valid_0's l1: 0.105524
[518] valid_0's l2: 0.0261551 valid_0's auc: 1 valid_0's l1: 0.105443
[519] valid_0's l2: 0.0261295 valid_0's auc: 1 valid_0's l1: 0.105398
[520] valid_0's l2: 0.0260957 valid_0's auc: 1 valid_0's l1: 0.105311
[521] valid_0's l2: 0.0260728 valid_0's auc: 1 valid_0's l1: 0.10526
[522] valid_0's l2: 0.0260533 valid_0's auc: 1 valid_0's l1: 0.105223
[523] valid_0's l2: 0.0260353 valid_0's auc: 1 valid_0's l1: 0.105191
[524] valid_0's l2: 0.026017 valid_0's auc: 1 valid_0's l1: 0.105157
[525] valid_0's l2: 0.026001 valid_0's auc: 1 valid_0's l1: 0.105133
[526] valid_0's l2: 0.0259843 valid_0's auc: 1 valid_0's l1: 0.105107
[527] valid_0's l2: 0.0259585 valid_0's auc: 1 valid_0's l1: 0.105041
[528] valid_0's l2: 0.025941 valid_0's auc: 1 valid_0's l1: 0.105009
[529] valid_0's l2: 0.0259265 valid_0's auc: 1 valid_0's l1: 0.104972
[530] valid_0's l2: 0.0259117 valid_0's auc: 1 valid_0's l1: 0.104948
[531] valid_0's l2: 0.025893 valid_0's auc: 1 valid_0's l1: 0.104905
[532] valid_0's l2: 0.0258713 valid_0's auc: 1 valid_0's l1: 0.104857
[533] valid_0's l2: 0.0258463 valid_0's auc: 1 valid_0's l1: 0.104795
[534] valid_0's l2: 0.0258265 valid_0's auc: 1 valid_0's l1: 0.104751
[535] valid_0's l2: 0.0258034 valid_0's auc: 1 valid_0's l1: 0.104707
[536] valid_0's l2: 0.0257804 valid_0's auc: 1 valid_0's l1: 0.104647
[537] valid_0's l2: 0.0257557 valid_0's auc: 1 valid_0's l1: 0.104588
[538] valid_0's l2: 0.0257322 valid_0's auc: 1 valid_0's l1: 0.104541
[539] valid_0's l2: 0.0257065 valid_0's auc: 1 valid_0's l1: 0.104486
[540] valid_0's l2: 0.0256827 valid_0's auc: 1 valid_0's l1: 0.104434
[541] valid_0's l2: 0.0256639 valid_0's auc: 1 valid_0's l1: 0.104415
[542] valid_0's l2: 0.0256406 valid_0's auc: 1 valid_0's l1: 0.104375
[543] valid_0's l2: 0.0256225 valid_0's auc: 1 valid_0's l1: 0.104358
[544] valid_0's l2: 0.0256055 valid_0's auc: 1 valid_0's l1: 0.104341
[545] valid_0's l2: 0.0255879 valid_0's auc: 1 valid_0's l1: 0.104324
[546] valid_0's l2: 0.0255688 valid_0's auc: 1 valid_0's l1: 0.104304
[547] valid_0's l2: 0.0255565 valid_0's auc: 1 valid_0's l1: 0.1043
[548] valid_0's l2: 0.0255436 valid_0's auc: 1 valid_0's l1: 0.10429
[549] valid_0's l2: 0.0255245 valid_0's auc: 1 valid_0's l1: 0.104261
[550] valid_0's l2: 0.025511 valid_0's auc: 1 valid_0's l1: 0.104245
[551] valid_0's l2: 0.0254893 valid_0's auc: 1 valid_0's l1: 0.104199
[552] valid_0's l2: 0.0254698 valid_0's auc: 1 valid_0's l1: 0.104162
[553] valid_0's l2: 0.0254503 valid_0's auc: 1 valid_0's l1: 0.104125
[554] valid_0's l2: 0.0254309 valid_0's auc: 1 valid_0's l1: 0.104088
[555] valid_0's l2: 0.0254117 valid_0's auc: 1 valid_0's l1: 0.104052
[556] valid_0's l2: 0.0253928 valid_0's auc: 1 valid_0's l1: 0.104015
[557] valid_0's l2: 0.0253746 valid_0's auc: 1 valid_0's l1: 0.103981
[558] valid_0's l2: 0.0253517 valid_0's auc: 1 valid_0's l1: 0.10393
[559] valid_0's l2: 0.0253334 valid_0's auc: 1 valid_0's l1: 0.103894
[560] valid_0's l2: 0.0253122 valid_0's auc: 1 valid_0's l1: 0.103847
[561] valid_0's l2: 0.02529 valid_0's auc: 1 valid_0's l1: 0.103813
[562] valid_0's l2: 0.0252668 valid_0's auc: 1 valid_0's l1: 0.103779
[563] valid_0's l2: 0.0252414 valid_0's auc: 1 valid_0's l1: 0.103718
[564] valid_0's l2: 0.025218 valid_0's auc: 1 valid_0's l1: 0.103682
[565] valid_0's l2: 0.0251955 valid_0's auc: 1 valid_0's l1: 0.103649
[566] valid_0's l2: 0.0251741 valid_0's auc: 1 valid_0's l1: 0.103616
[567] valid_0's l2: 0.0251519 valid_0's auc: 1 valid_0's l1: 0.103582
[568] valid_0's l2: 0.025128 valid_0's auc: 1 valid_0's l1: 0.103546
[569] valid_0's l2: 0.0251075 valid_0's auc: 1 valid_0's l1: 0.103513
[570] valid_0's l2: 0.025089 valid_0's auc: 1 valid_0's l1: 0.103475
[571] valid_0's l2: 0.0250701 valid_0's auc: 1 valid_0's l1: 0.103428
[572] valid_0's l2: 0.0250498 valid_0's auc: 1 valid_0's l1: 0.103369
[573] valid_0's l2: 0.0250301 valid_0's auc: 1 valid_0's l1: 0.10331
[574] valid_0's l2: 0.0250102 valid_0's auc: 1 valid_0's l1: 0.103252
[575] valid_0's l2: 0.0249905 valid_0's auc: 1 valid_0's l1: 0.103195
[576] valid_0's l2: 0.0249694 valid_0's auc: 1 valid_0's l1: 0.103129
[577] valid_0's l2: 0.0249518 valid_0's auc: 1 valid_0's l1: 0.103078
[578] valid_0's l2: 0.0249341 valid_0's auc: 1 valid_0's l1: 0.103033
[579] valid_0's l2: 0.0249156 valid_0's auc: 1 valid_0's l1: 0.102976
[580] valid_0's l2: 0.0248978 valid_0's auc: 1 valid_0's l1: 0.102924
[581] valid_0's l2: 0.024878 valid_0's auc: 1 valid_0's l1: 0.102875
[582] valid_0's l2: 0.0248647 valid_0's auc: 1 valid_0's l1: 0.102848
[583] valid_0's l2: 0.0248452 valid_0's auc: 1 valid_0's l1: 0.102799
[584] valid_0's l2: 0.024826 valid_0's auc: 1 valid_0's l1: 0.10275
[585] valid_0's l2: 0.0248069 valid_0's auc: 1 valid_0's l1: 0.102701
[586] valid_0's l2: 0.0247868 valid_0's auc: 1 valid_0's l1: 0.102646
[587] valid_0's l2: 0.024774 valid_0's auc: 1 valid_0's l1: 0.10262
[588] valid_0's l2: 0.0247609 valid_0's auc: 1 valid_0's l1: 0.10261
[589] valid_0's l2: 0.0247409 valid_0's auc: 1 valid_0's l1: 0.102558
[590] valid_0's l2: 0.0247213 valid_0's auc: 1 valid_0's l1: 0.102501
[591] valid_0's l2: 0.0246987 valid_0's auc: 1 valid_0's l1: 0.102454
[592] valid_0's l2: 0.0246767 valid_0's auc: 1 valid_0's l1: 0.102408
[593] valid_0's l2: 0.0246563 valid_0's auc: 1 valid_0's l1: 0.102362
[594] valid_0's l2: 0.0246364 valid_0's auc: 1 valid_0's l1: 0.102311
[595] valid_0's l2: 0.0246173 valid_0's auc: 1 valid_0's l1: 0.102275
[596] valid_0's l2: 0.024598 valid_0's auc: 1 valid_0's l1: 0.102229
[597] valid_0's l2: 0.0245781 valid_0's auc: 1 valid_0's l1: 0.10219
[598] valid_0's l2: 0.0245636 valid_0's auc: 1 valid_0's l1: 0.102143
[599] valid_0's l2: 0.0245461 valid_0's auc: 1 valid_0's l1: 0.102102
[600] valid_0's l2: 0.0245316 valid_0's auc: 1 valid_0's l1: 0.102056
[601] valid_0's l2: 0.0245169 valid_0's auc: 1 valid_0's l1: 0.102014
[602] valid_0's l2: 0.0244994 valid_0's auc: 1 valid_0's l1: 0.101969
[603] valid_0's l2: 0.0244852 valid_0's auc: 1 valid_0's l1: 0.101935
[604] valid_0's l2: 0.0244692 valid_0's auc: 1 valid_0's l1: 0.101901
[605] valid_0's l2: 0.0244569 valid_0's auc: 1 valid_0's l1: 0.101878
[606] valid_0's l2: 0.024439 valid_0's auc: 1 valid_0's l1: 0.101833
[607] valid_0's l2: 0.0244259 valid_0's auc: 1 valid_0's l1: 0.101809
[608] valid_0's l2: 0.0244136 valid_0's auc: 1 valid_0's l1: 0.101789
[609] valid_0's l2: 0.0243976 valid_0's auc: 1 valid_0's l1: 0.101752
[610] valid_0's l2: 0.0243826 valid_0's auc: 1 valid_0's l1: 0.101715
[611] valid_0's l2: 0.0243716 valid_0's auc: 1 valid_0's l1: 0.101687
[612] valid_0's l2: 0.0243573 valid_0's auc: 1 valid_0's l1: 0.101647
[613] valid_0's l2: 0.0243463 valid_0's auc: 1 valid_0's l1: 0.101618
[614] valid_0's l2: 0.0243239 valid_0's auc: 1 valid_0's l1: 0.101571
[615] valid_0's l2: 0.0243099 valid_0's auc: 1 valid_0's l1: 0.101533
[616] valid_0's l2: 0.0242923 valid_0's auc: 1 valid_0's l1: 0.101498
[617] valid_0's l2: 0.0242776 valid_0's auc: 1 valid_0's l1: 0.101463
[618] valid_0's l2: 0.0242665 valid_0's auc: 1 valid_0's l1: 0.101442
[619] valid_0's l2: 0.0242518 valid_0's auc: 1 valid_0's l1: 0.101406
[620] valid_0's l2: 0.0242418 valid_0's auc: 1 valid_0's l1: 0.101385
[621] valid_0's l2: 0.0242221 valid_0's auc: 1 valid_0's l1: 0.101339
[622] valid_0's l2: 0.0241996 valid_0's auc: 1 valid_0's l1: 0.101291
[623] valid_0's l2: 0.0241807 valid_0's auc: 1 valid_0's l1: 0.101252
[624] valid_0's l2: 0.0241614 valid_0's auc: 1 valid_0's l1: 0.101207
[625] valid_0's l2: 0.0241406 valid_0's auc: 1 valid_0's l1: 0.101157
[626] valid_0's l2: 0.0241216 valid_0's auc: 1 valid_0's l1: 0.101112
[627] valid_0's l2: 0.0241034 valid_0's auc: 1 valid_0's l1: 0.101071
[628] valid_0's l2: 0.0240846 valid_0's auc: 1 valid_0's l1: 0.101026
[629] valid_0's l2: 0.0240707 valid_0's auc: 1 valid_0's l1: 0.100999
[630] valid_0's l2: 0.024052 valid_0's auc: 1 valid_0's l1: 0.100953
[631] valid_0's l2: 0.0240397 valid_0's auc: 1 valid_0's l1: 0.100923
[632] valid_0's l2: 0.0240302 valid_0's auc: 1 valid_0's l1: 0.100898
[633] valid_0's l2: 0.0240209 valid_0's auc: 1 valid_0's l1: 0.100873
[634] valid_0's l2: 0.0240136 valid_0's auc: 1 valid_0's l1: 0.100852
[635] valid_0's l2: 0.0239977 valid_0's auc: 1 valid_0's l1: 0.100809
[636] valid_0's l2: 0.0239826 valid_0's auc: 1 valid_0's l1: 0.100778
[637] valid_0's l2: 0.0239732 valid_0's auc: 1 valid_0's l1: 0.100753
[638] valid_0's l2: 0.0239645 valid_0's auc: 1 valid_0's l1: 0.100735
[639] valid_0's l2: 0.0239553 valid_0's auc: 1 valid_0's l1: 0.100711
[640] valid_0's l2: 0.0239438 valid_0's auc: 1 valid_0's l1: 0.100686
[641] valid_0's l2: 0.023932 valid_0's auc: 1 valid_0's l1: 0.100666
[642] valid_0's l2: 0.023918 valid_0's auc: 1 valid_0's l1: 0.100638
[643] valid_0's l2: 0.0239068 valid_0's auc: 1 valid_0's l1: 0.100616
[644] valid_0's l2: 0.0238947 valid_0's auc: 1 valid_0's l1: 0.100594
[645] valid_0's l2: 0.023884 valid_0's auc: 1 valid_0's l1: 0.10057
[646] valid_0's l2: 0.023873 valid_0's auc: 1 valid_0's l1: 0.100552
[647] valid_0's l2: 0.0238611 valid_0's auc: 1 valid_0's l1: 0.100527
[648] valid_0's l2: 0.0238508 valid_0's auc: 1 valid_0's l1: 0.100504
[649] valid_0's l2: 0.0238439 valid_0's auc: 1 valid_0's l1: 0.100498
[650] valid_0's l2: 0.0238336 valid_0's auc: 1 valid_0's l1: 0.10048
[651] valid_0's l2: 0.0238043 valid_0's auc: 1 valid_0's l1: 0.100419
[652] valid_0's l2: 0.0237767 valid_0's auc: 1 valid_0's l1: 0.100367
[653] valid_0's l2: 0.0237552 valid_0's auc: 1 valid_0's l1: 0.100322
[654] valid_0's l2: 0.0237331 valid_0's auc: 1 valid_0's l1: 0.10028
[655] valid_0's l2: 0.023706 valid_0's auc: 1 valid_0's l1: 0.100228
[656] valid_0's l2: 0.0236793 valid_0's auc: 1 valid_0's l1: 0.100177
[657] valid_0's l2: 0.0236528 valid_0's auc: 1 valid_0's l1: 0.100129
[658] valid_0's l2: 0.0236322 valid_0's auc: 1 valid_0's l1: 0.100088
[659] valid_0's l2: 0.0236125 valid_0's auc: 1 valid_0's l1: 0.100049
[660] valid_0's l2: 0.0235904 valid_0's auc: 1 valid_0's l1: 0.100011
[661] valid_0's l2: 0.0235781 valid_0's auc: 1 valid_0's l1: 0.0999903
[662] valid_0's l2: 0.0235659 valid_0's auc: 1 valid_0's l1: 0.09997
[663] valid_0's l2: 0.0235538 valid_0's auc: 1 valid_0's l1: 0.0999497
[664] valid_0's l2: 0.0235422 valid_0's auc: 1 valid_0's l1: 0.0999348
[665] valid_0's l2: 0.023528 valid_0's auc: 1 valid_0's l1: 0.099911
[666] valid_0's l2: 0.0235159 valid_0's auc: 1 valid_0's l1: 0.0998906
[667] valid_0's l2: 0.0235071 valid_0's auc: 1 valid_0's l1: 0.0998804
[668] valid_0's l2: 0.0234978 valid_0's auc: 1 valid_0's l1: 0.0998678
[669] valid_0's l2: 0.0234816 valid_0's auc: 1 valid_0's l1: 0.0998423
[670] valid_0's l2: 0.0234747 valid_0's auc: 1 valid_0's l1: 0.099828
[671] valid_0's l2: 0.0234564 valid_0's auc: 1 valid_0's l1: 0.099792
[672] valid_0's l2: 0.0234445 valid_0's auc: 1 valid_0's l1: 0.0997628
[673] valid_0's l2: 0.0234327 valid_0's auc: 1 valid_0's l1: 0.0997369
[674] valid_0's l2: 0.0234198 valid_0's auc: 1 valid_0's l1: 0.09971
[675] valid_0's l2: 0.0234021 valid_0's auc: 1 valid_0's l1: 0.0996733
[676] valid_0's l2: 0.0233845 valid_0's auc: 1 valid_0's l1: 0.0996368
[677] valid_0's l2: 0.023367 valid_0's auc: 1 valid_0's l1: 0.0996009
[678] valid_0's l2: 0.0233498 valid_0's auc: 1 valid_0's l1: 0.0995647
[679] valid_0's l2: 0.0233326 valid_0's auc: 1 valid_0's l1: 0.0995291
[680] valid_0's l2: 0.0233158 valid_0's auc: 1 valid_0's l1: 0.0994935
[681] valid_0's l2: 0.0233087 valid_0's auc: 1 valid_0's l1: 0.0994723
[682] valid_0's l2: 0.0233023 valid_0's auc: 1 valid_0's l1: 0.099458
[683] valid_0's l2: 0.0232917 valid_0's auc: 1 valid_0's l1: 0.0994282
[684] valid_0's l2: 0.0232831 valid_0's auc: 1 valid_0's l1: 0.0994028
[685] valid_0's l2: 0.0232797 valid_0's auc: 1 valid_0's l1: 0.0993943
[686] valid_0's l2: 0.0232702 valid_0's auc: 1 valid_0's l1: 0.0993791
[687] valid_0's l2: 0.0232606 valid_0's auc: 1 valid_0's l1: 0.09936
[688] valid_0's l2: 0.0232535 valid_0's auc: 1 valid_0's l1: 0.099341
[689] valid_0's l2: 0.0232472 valid_0's auc: 1 valid_0's l1: 0.0993214
[690] valid_0's l2: 0.0232404 valid_0's auc: 1 valid_0's l1: 0.0993026
[691] valid_0's l2: 0.0232348 valid_0's auc: 1 valid_0's l1: 0.0992751
[692] valid_0's l2: 0.0232259 valid_0's auc: 1 valid_0's l1: 0.099247
[693] valid_0's l2: 0.0232206 valid_0's auc: 1 valid_0's l1: 0.0992234
[694] valid_0's l2: 0.0232149 valid_0's auc: 1 valid_0's l1: 0.0992004
[695] valid_0's l2: 0.0232068 valid_0's auc: 1 valid_0's l1: 0.0991761
[696] valid_0's l2: 0.0231992 valid_0's auc: 1 valid_0's l1: 0.0991446
[697] valid_0's l2: 0.0231857 valid_0's auc: 1 valid_0's l1: 0.0991116
[698] valid_0's l2: 0.0231754 valid_0's auc: 1 valid_0's l1: 0.0990857
[699] valid_0's l2: 0.0231602 valid_0's auc: 1 valid_0's l1: 0.0990553
[700] valid_0's l2: 0.0231551 valid_0's auc: 1 valid_0's l1: 0.09904
[701] valid_0's l2: 0.0231446 valid_0's auc: 1 valid_0's l1: 0.0990026
[702] valid_0's l2: 0.0231341 valid_0's auc: 1 valid_0's l1: 0.0989664
[703] valid_0's l2: 0.0231238 valid_0's auc: 1 valid_0's l1: 0.0989304
[704] valid_0's l2: 0.0231148 valid_0's auc: 1 valid_0's l1: 0.0988982
[705] valid_0's l2: 0.0231093 valid_0's auc: 1 valid_0's l1: 0.0988837
[706] valid_0's l2: 0.023099 valid_0's auc: 1 valid_0's l1: 0.098855
[707] valid_0's l2: 0.0230892 valid_0's auc: 1 valid_0's l1: 0.098826
[708] valid_0's l2: 0.0230816 valid_0's auc: 1 valid_0's l1: 0.0987991
[709] valid_0's l2: 0.023073 valid_0's auc: 1 valid_0's l1: 0.0987675
[710] valid_0's l2: 0.0230706 valid_0's auc: 1 valid_0's l1: 0.0987532
[711] valid_0's l2: 0.0230674 valid_0's auc: 1 valid_0's l1: 0.0987399
[712] valid_0's l2: 0.0230637 valid_0's auc: 1 valid_0's l1: 0.0987251
[713] valid_0's l2: 0.0230606 valid_0's auc: 1 valid_0's l1: 0.0987147
[714] valid_0's l2: 0.0230522 valid_0's auc: 1 valid_0's l1: 0.0986984
[715] valid_0's l2: 0.0230471 valid_0's auc: 1 valid_0's l1: 0.0986772
[716] valid_0's l2: 0.0230437 valid_0's auc: 1 valid_0's l1: 0.0986649
[717] valid_0's l2: 0.0230407 valid_0's auc: 1 valid_0's l1: 0.0986542
[718] valid_0's l2: 0.0230368 valid_0's auc: 1 valid_0's l1: 0.09864
[719] valid_0's l2: 0.0230339 valid_0's auc: 1 valid_0's l1: 0.0986295
[720] valid_0's l2: 0.023026 valid_0's auc: 1 valid_0's l1: 0.0986111
[721] valid_0's l2: 0.0230112 valid_0's auc: 1 valid_0's l1: 0.0985884
[722] valid_0's l2: 0.0229925 valid_0's auc: 1 valid_0's l1: 0.0985517
[723] valid_0's l2: 0.0229793 valid_0's auc: 1 valid_0's l1: 0.0985286
[724] valid_0's l2: 0.0229659 valid_0's auc: 1 valid_0's l1: 0.0985082
[725] valid_0's l2: 0.0229542 valid_0's auc: 1 valid_0's l1: 0.0984834
[726] valid_0's l2: 0.02294 valid_0's auc: 1 valid_0's l1: 0.0984593
[727] valid_0's l2: 0.0229256 valid_0's auc: 1 valid_0's l1: 0.0984322
[728] valid_0's l2: 0.0229126 valid_0's auc: 1 valid_0's l1: 0.0984147
[729] valid_0's l2: 0.0228998 valid_0's auc: 1 valid_0's l1: 0.0983973
[730] valid_0's l2: 0.0228861 valid_0's auc: 1 valid_0's l1: 0.0983736
[731] valid_0's l2: 0.0228742 valid_0's auc: 1 valid_0's l1: 0.0983469
[732] valid_0's l2: 0.0228615 valid_0's auc: 1 valid_0's l1: 0.0983203
[733] valid_0's l2: 0.0228499 valid_0's auc: 1 valid_0's l1: 0.0982938
[734] valid_0's l2: 0.0228384 valid_0's auc: 1 valid_0's l1: 0.0982674
[735] valid_0's l2: 0.022828 valid_0's auc: 1 valid_0's l1: 0.09824
[736] valid_0's l2: 0.0228175 valid_0's auc: 1 valid_0's l1: 0.098215
[737] valid_0's l2: 0.022808 valid_0's auc: 1 valid_0's l1: 0.0981827
[738] valid_0's l2: 0.0227979 valid_0's auc: 1 valid_0's l1: 0.0981537
[739] valid_0's l2: 0.0227885 valid_0's auc: 1 valid_0's l1: 0.0981308
[740] valid_0's l2: 0.022776 valid_0's auc: 1 valid_0's l1: 0.0980925
[741] valid_0's l2: 0.0227644 valid_0's auc: 1 valid_0's l1: 0.0980603
[742] valid_0's l2: 0.0227595 valid_0's auc: 1 valid_0's l1: 0.0980434
[743] valid_0's l2: 0.0227504 valid_0's auc: 1 valid_0's l1: 0.0980255
[744] valid_0's l2: 0.0227461 valid_0's auc: 1 valid_0's l1: 0.0980052
[745] valid_0's l2: 0.022741 valid_0's auc: 1 valid_0's l1: 0.097983
[746] valid_0's l2: 0.0227298 valid_0's auc: 1 valid_0's l1: 0.0979513
[747] valid_0's l2: 0.022726 valid_0's auc: 1 valid_0's l1: 0.0979315
[748] valid_0's l2: 0.0227209 valid_0's auc: 1 valid_0's l1: 0.0979215
[749] valid_0's l2: 0.0227068 valid_0's auc: 1 valid_0's l1: 0.0978799
[750] valid_0's l2: 0.0227007 valid_0's auc: 1 valid_0's l1: 0.0978718
[751] valid_0's l2: 0.0226925 valid_0's auc: 1 valid_0's l1: 0.0978519
[752] valid_0's l2: 0.0226845 valid_0's auc: 1 valid_0's l1: 0.0978272
[753] valid_0's l2: 0.0226766 valid_0's auc: 1 valid_0's l1: 0.0978053
[754] valid_0's l2: 0.0226688 valid_0's auc: 1 valid_0's l1: 0.0977835
[755] valid_0's l2: 0.0226618 valid_0's auc: 1 valid_0's l1: 0.0977609
[756] valid_0's l2: 0.0226531 valid_0's auc: 1 valid_0's l1: 0.0977488
[757] valid_0's l2: 0.0226434 valid_0's auc: 1 valid_0's l1: 0.0977201
[758] valid_0's l2: 0.0226344 valid_0's auc: 1 valid_0's l1: 0.0977079
[759] valid_0's l2: 0.0226241 valid_0's auc: 1 valid_0's l1: 0.0976758
[760] valid_0's l2: 0.0226162 valid_0's auc: 1 valid_0's l1: 0.0976525
[761] valid_0's l2: 0.0226093 valid_0's auc: 1 valid_0's l1: 0.0976584
[762] valid_0's l2: 0.0226016 valid_0's auc: 1 valid_0's l1: 0.0976575
[763] valid_0's l2: 0.022593 valid_0's auc: 1 valid_0's l1: 0.0976512
[764] valid_0's l2: 0.0225835 valid_0's auc: 1 valid_0's l1: 0.0976307
[765] valid_0's l2: 0.0225741 valid_0's auc: 1 valid_0's l1: 0.0976312
[766] valid_0's l2: 0.0225669 valid_0's auc: 1 valid_0's l1: 0.0976331
[767] valid_0's l2: 0.0225608 valid_0's auc: 1 valid_0's l1: 0.0976418
[768] valid_0's l2: 0.0225546 valid_0's auc: 1 valid_0's l1: 0.097648
[769] valid_0's l2: 0.0225477 valid_0's auc: 1 valid_0's l1: 0.0976495
[770] valid_0's l2: 0.0225419 valid_0's auc: 1 valid_0's l1: 0.0976581
[771] valid_0's l2: 0.0225314 valid_0's auc: 1 valid_0's l1: 0.0976287
[772] valid_0's l2: 0.0225203 valid_0's auc: 1 valid_0's l1: 0.0975971
[773] valid_0's l2: 0.0225098 valid_0's auc: 1 valid_0's l1: 0.0975687
[774] valid_0's l2: 0.0225022 valid_0's auc: 1 valid_0's l1: 0.0975514
[775] valid_0's l2: 0.022492 valid_0's auc: 1 valid_0's l1: 0.0975226
[776] valid_0's l2: 0.0224825 valid_0's auc: 1 valid_0's l1: 0.0974917
[777] valid_0's l2: 0.0224751 valid_0's auc: 1 valid_0's l1: 0.0974747
[778] valid_0's l2: 0.0224651 valid_0's auc: 1 valid_0's l1: 0.0974352
[779] valid_0's l2: 0.0224563 valid_0's auc: 1 valid_0's l1: 0.0974024
[780] valid_0's l2: 0.0224475 valid_0's auc: 1 valid_0's l1: 0.0973866
[781] valid_0's l2: 0.022442 valid_0's auc: 1 valid_0's l1: 0.0973718
[782] valid_0's l2: 0.0224364 valid_0's auc: 1 valid_0's l1: 0.0973555
[783] valid_0's l2: 0.022434 valid_0's auc: 1 valid_0's l1: 0.097347
[784] valid_0's l2: 0.0224285 valid_0's auc: 1 valid_0's l1: 0.0973352
[785] valid_0's l2: 0.0224241 valid_0's auc: 1 valid_0's l1: 0.0973262
[786] valid_0's l2: 0.0224211 valid_0's auc: 1 valid_0's l1: 0.0973114
[787] valid_0's l2: 0.0224159 valid_0's auc: 1 valid_0's l1: 0.0972998
[788] valid_0's l2: 0.022411 valid_0's auc: 1 valid_0's l1: 0.0972862
[789] valid_0's l2: 0.0224064 valid_0's auc: 1 valid_0's l1: 0.0972775
[790] valid_0's l2: 0.0224018 valid_0's auc: 1 valid_0's l1: 0.0972696
[791] valid_0's l2: 0.0223912 valid_0's auc: 1 valid_0's l1: 0.0972437
[792] valid_0's l2: 0.022381 valid_0's auc: 1 valid_0's l1: 0.0972193
[793] valid_0's l2: 0.0223709 valid_0's auc: 1 valid_0's l1: 0.097195
[794] valid_0's l2: 0.0223595 valid_0's auc: 1 valid_0's l1: 0.0971637
[795] valid_0's l2: 0.0223488 valid_0's auc: 1 valid_0's l1: 0.097135
[796] valid_0's l2: 0.0223395 valid_0's auc: 1 valid_0's l1: 0.0971072
[797] valid_0's l2: 0.0223297 valid_0's auc: 1 valid_0's l1: 0.0970839
[798] valid_0's l2: 0.0223216 valid_0's auc: 1 valid_0's l1: 0.0970579
[799] valid_0's l2: 0.0223143 valid_0's auc: 1 valid_0's l1: 0.0970413
[800] valid_0's l2: 0.0223048 valid_0's auc: 1 valid_0's l1: 0.097013
[801] valid_0's l2: 0.0222923 valid_0's auc: 1 valid_0's l1: 0.0969772
[802] valid_0's l2: 0.0222837 valid_0's auc: 1 valid_0's l1: 0.0969543
[803] valid_0's l2: 0.0222756 valid_0's auc: 1 valid_0's l1: 0.0969335
[804] valid_0's l2: 0.0222711 valid_0's auc: 1 valid_0's l1: 0.0969297
[805] valid_0's l2: 0.022259 valid_0's auc: 1 valid_0's l1: 0.0968944
[806] valid_0's l2: 0.0222467 valid_0's auc: 1 valid_0's l1: 0.0968602
[807] valid_0's l2: 0.0222348 valid_0's auc: 1 valid_0's l1: 0.0968276
[808] valid_0's l2: 0.0222229 valid_0's auc: 1 valid_0's l1: 0.0967921
[809] valid_0's l2: 0.0222112 valid_0's auc: 1 valid_0's l1: 0.0967598
[810] valid_0's l2: 0.0221994 valid_0's auc: 1 valid_0's l1: 0.0967237
[811] valid_0's l2: 0.0221973 valid_0's auc: 1 valid_0's l1: 0.0967099
[812] valid_0's l2: 0.0221926 valid_0's auc: 1 valid_0's l1: 0.0966938
[813] valid_0's l2: 0.0221872 valid_0's auc: 1 valid_0's l1: 0.0966742
[814] valid_0's l2: 0.0221808 valid_0's auc: 1 valid_0's l1: 0.0966562
[815] valid_0's l2: 0.0221742 valid_0's auc: 1 valid_0's l1: 0.0966514
[816] valid_0's l2: 0.022167 valid_0's auc: 1 valid_0's l1: 0.0966468
[817] valid_0's l2: 0.0221616 valid_0's auc: 1 valid_0's l1: 0.096643
[818] valid_0's l2: 0.0221554 valid_0's auc: 1 valid_0's l1: 0.0966228
[819] valid_0's l2: 0.0221513 valid_0's auc: 1 valid_0's l1: 0.0966189
[820] valid_0's l2: 0.0221455 valid_0's auc: 1 valid_0's l1: 0.0966117
[821] valid_0's l2: 0.0221351 valid_0's auc: 1 valid_0's l1: 0.0965911
[822] valid_0's l2: 0.0221266 valid_0's auc: 1 valid_0's l1: 0.0965861
[823] valid_0's l2: 0.0221174 valid_0's auc: 1 valid_0's l1: 0.0965672
[824] valid_0's l2: 0.0221089 valid_0's auc: 1 valid_0's l1: 0.096547
[825] valid_0's l2: 0.0221007 valid_0's auc: 1 valid_0's l1: 0.0965303
[826] valid_0's l2: 0.0220923 valid_0's auc: 1 valid_0's l1: 0.0965103
[827] valid_0's l2: 0.0220856 valid_0's auc: 1 valid_0's l1: 0.0964954
[828] valid_0's l2: 0.0220758 valid_0's auc: 1 valid_0's l1: 0.0964753
[829] valid_0's l2: 0.0220677 valid_0's auc: 1 valid_0's l1: 0.096462
[830] valid_0's l2: 0.0220592 valid_0's auc: 1 valid_0's l1: 0.096454
[831] valid_0's l2: 0.0220456 valid_0's auc: 1 valid_0's l1: 0.0964269
[832] valid_0's l2: 0.0220328 valid_0's auc: 1 valid_0's l1: 0.0963965
[833] valid_0's l2: 0.0220201 valid_0's auc: 1 valid_0's l1: 0.0963663
[834] valid_0's l2: 0.0220057 valid_0's auc: 1 valid_0's l1: 0.0963352
[835] valid_0's l2: 0.021994 valid_0's auc: 1 valid_0's l1: 0.096311
[836] valid_0's l2: 0.0219816 valid_0's auc: 1 valid_0's l1: 0.0962853
[837] valid_0's l2: 0.0219693 valid_0's auc: 1 valid_0's l1: 0.0962577
[838] valid_0's l2: 0.021956 valid_0's auc: 1 valid_0's l1: 0.0962395
[839] valid_0's l2: 0.021944 valid_0's auc: 1 valid_0's l1: 0.0962122
[840] valid_0's l2: 0.0219321 valid_0's auc: 1 valid_0's l1: 0.0961869
[841] valid_0's l2: 0.0219236 valid_0's auc: 1 valid_0's l1: 0.0961607
[842] valid_0's l2: 0.0219141 valid_0's auc: 1 valid_0's l1: 0.0961355
[843] valid_0's l2: 0.0219029 valid_0's auc: 1 valid_0's l1: 0.0961025
[844] valid_0's l2: 0.0218954 valid_0's auc: 1 valid_0's l1: 0.0960801
[845] valid_0's l2: 0.0218895 valid_0's auc: 1 valid_0's l1: 0.0960733
[846] valid_0's l2: 0.0218818 valid_0's auc: 1 valid_0's l1: 0.0960567
[847] valid_0's l2: 0.021876 valid_0's auc: 1 valid_0's l1: 0.0960502
[848] valid_0's l2: 0.0218667 valid_0's auc: 1 valid_0's l1: 0.0960288
[849] valid_0's l2: 0.0218647 valid_0's auc: 1 valid_0's l1: 0.0960228
[850] valid_0's l2: 0.0218561 valid_0's auc: 1 valid_0's l1: 0.0960013
[851] valid_0's l2: 0.0218542 valid_0's auc: 1 valid_0's l1: 0.0959922
[852] valid_0's l2: 0.0218525 valid_0's auc: 1 valid_0's l1: 0.0959836
[853] valid_0's l2: 0.0218466 valid_0's auc: 1 valid_0's l1: 0.0959631
[854] valid_0's l2: 0.0218402 valid_0's auc: 1 valid_0's l1: 0.0959444
[855] valid_0's l2: 0.0218338 valid_0's auc: 1 valid_0's l1: 0.0959251
[856] valid_0's l2: 0.0218294 valid_0's auc: 1 valid_0's l1: 0.0959016
[857] valid_0's l2: 0.0218232 valid_0's auc: 1 valid_0's l1: 0.0958825
[858] valid_0's l2: 0.021817 valid_0's auc: 1 valid_0's l1: 0.0958635
[859] valid_0's l2: 0.0218154 valid_0's auc: 1 valid_0's l1: 0.0958555
[860] valid_0's l2: 0.0218138 valid_0's auc: 1 valid_0's l1: 0.0958475
[861] valid_0's l2: 0.0218084 valid_0's auc: 1 valid_0's l1: 0.0958269
[862] valid_0's l2: 0.021803 valid_0's auc: 1 valid_0's l1: 0.0958065
[863] valid_0's l2: 0.0217976 valid_0's auc: 1 valid_0's l1: 0.0957874
[864] valid_0's l2: 0.0217907 valid_0's auc: 1 valid_0's l1: 0.0957678
[865] valid_0's l2: 0.0217852 valid_0's auc: 1 valid_0's l1: 0.0957519
[866] valid_0's l2: 0.0217804 valid_0's auc: 1 valid_0's l1: 0.0957391
[867] valid_0's l2: 0.0217751 valid_0's auc: 1 valid_0's l1: 0.0957225
[868] valid_0's l2: 0.0217693 valid_0's auc: 1 valid_0's l1: 0.0957035
[869] valid_0's l2: 0.0217643 valid_0's auc: 1 valid_0's l1: 0.0956873
[870] valid_0's l2: 0.0217587 valid_0's auc: 1 valid_0's l1: 0.0956703
[871] valid_0's l2: 0.0217513 valid_0's auc: 1 valid_0's l1: 0.0956623
[872] valid_0's l2: 0.0217466 valid_0's auc: 1 valid_0's l1: 0.0956575
[873] valid_0's l2: 0.0217422 valid_0's auc: 1 valid_0's l1: 0.0956528
[874] valid_0's l2: 0.0217374 valid_0's auc: 1 valid_0's l1: 0.0956486
[875] valid_0's l2: 0.021732 valid_0's auc: 1 valid_0's l1: 0.0956435
[876] valid_0's l2: 0.0217281 valid_0's auc: 1 valid_0's l1: 0.0956366
[877] valid_0's l2: 0.0217234 valid_0's auc: 1 valid_0's l1: 0.0956334
[878] valid_0's l2: 0.0217189 valid_0's auc: 1 valid_0's l1: 0.0956316
[879] valid_0's l2: 0.0217146 valid_0's auc: 1 valid_0's l1: 0.0956247
[880] valid_0's l2: 0.0217109 valid_0's auc: 1 valid_0's l1: 0.0956179
[881] valid_0's l2: 0.0217062 valid_0's auc: 1 valid_0's l1: 0.095603
[882] valid_0's l2: 0.0217008 valid_0's auc: 1 valid_0's l1: 0.0955885
[883] valid_0's l2: 0.021693 valid_0's auc: 1 valid_0's l1: 0.0955768
[884] valid_0's l2: 0.0216884 valid_0's auc: 1 valid_0's l1: 0.095562
[885] valid_0's l2: 0.021684 valid_0's auc: 1 valid_0's l1: 0.0955486
[886] valid_0's l2: 0.0216798 valid_0's auc: 1 valid_0's l1: 0.0955406
[887] valid_0's l2: 0.0216736 valid_0's auc: 1 valid_0's l1: 0.0955193
[888] valid_0's l2: 0.0216686 valid_0's auc: 1 valid_0's l1: 0.0955051
[889] valid_0's l2: 0.0216642 valid_0's auc: 1 valid_0's l1: 0.0954907
[890] valid_0's l2: 0.0216582 valid_0's auc: 1 valid_0's l1: 0.0954697
[891] valid_0's l2: 0.0216569 valid_0's auc: 1 valid_0's l1: 0.0954542
[892] valid_0's l2: 0.021655 valid_0's auc: 1 valid_0's l1: 0.0954495
[893] valid_0's l2: 0.0216523 valid_0's auc: 1 valid_0's l1: 0.0954382
[894] valid_0's l2: 0.0216481 valid_0's auc: 1 valid_0's l1: 0.0954301
[895] valid_0's l2: 0.0216463 valid_0's auc: 1 valid_0's l1: 0.0954258
[896] valid_0's l2: 0.0216417 valid_0's auc: 1 valid_0's l1: 0.0954165
[897] valid_0's l2: 0.0216412 valid_0's auc: 1 valid_0's l1: 0.0954163
[898] valid_0's l2: 0.0216387 valid_0's auc: 1 valid_0's l1: 0.0954053
[899] valid_0's l2: 0.0216375 valid_0's auc: 1 valid_0's l1: 0.0954015
[900] valid_0's l2: 0.0216359 valid_0's auc: 1 valid_0's l1: 0.0953982
[901] valid_0's l2: 0.0216322 valid_0's auc: 1 valid_0's l1: 0.0953865
[902] valid_0's l2: 0.0216286 valid_0's auc: 1 valid_0's l1: 0.0953726
[903] valid_0's l2: 0.021625 valid_0's auc: 1 valid_0's l1: 0.0953611
[904] valid_0's l2: 0.021622 valid_0's auc: 1 valid_0's l1: 0.095351
[905] valid_0's l2: 0.0216204 valid_0's auc: 1 valid_0's l1: 0.0953431
[906] valid_0's l2: 0.0216174 valid_0's auc: 1 valid_0's l1: 0.0953332
[907] valid_0's l2: 0.0216141 valid_0's auc: 1 valid_0's l1: 0.0953195
[908] valid_0's l2: 0.0216103 valid_0's auc: 1 valid_0's l1: 0.0953033
[909] valid_0's l2: 0.0216082 valid_0's auc: 1 valid_0's l1: 0.0952955
[910] valid_0's l2: 0.0216061 valid_0's auc: 1 valid_0's l1: 0.0952889
[911] valid_0's l2: 0.0216058 valid_0's auc: 1 valid_0's l1: 0.0952842
[912] valid_0's l2: 0.0216037 valid_0's auc: 1 valid_0's l1: 0.0952856
[913] valid_0's l2: 0.0216012 valid_0's auc: 1 valid_0's l1: 0.0952732
[914] valid_0's l2: 0.0216009 valid_0's auc: 1 valid_0's l1: 0.0952746
[915] valid_0's l2: 0.0215993 valid_0's auc: 1 valid_0's l1: 0.0952651
[916] valid_0's l2: 0.021597 valid_0's auc: 1 valid_0's l1: 0.0952528
[917] valid_0's l2: 0.0215963 valid_0's auc: 1 valid_0's l1: 0.0952526
[918] valid_0's l2: 0.0215941 valid_0's auc: 1 valid_0's l1: 0.0952403
[919] valid_0's l2: 0.021593 valid_0's auc: 1 valid_0's l1: 0.0952397
[920] valid_0's l2: 0.0215911 valid_0's auc: 1 valid_0's l1: 0.0952237
[921] valid_0's l2: 0.0215922 valid_0's auc: 1 valid_0's l1: 0.0952161
[922] valid_0's l2: 0.0215924 valid_0's auc: 1 valid_0's l1: 0.0952078
[923] valid_0's l2: 0.0215947 valid_0's auc: 1 valid_0's l1: 0.0952031
[924] valid_0's l2: 0.0215955 valid_0's auc: 1 valid_0's l1: 0.0951948
[925] valid_0's l2: 0.0215939 valid_0's auc: 1 valid_0's l1: 0.0951858
[926] valid_0's l2: 0.0215937 valid_0's auc: 1 valid_0's l1: 0.0951802
[927] valid_0's l2: 0.0215958 valid_0's auc: 1 valid_0's l1: 0.0951758
[928] valid_0's l2: 0.0215931 valid_0's auc: 1 valid_0's l1: 0.0951683
[929] valid_0's l2: 0.0215937 valid_0's auc: 1 valid_0's l1: 0.095165
[930] valid_0's l2: 0.0215943 valid_0's auc: 1 valid_0's l1: 0.095169
[931] valid_0's l2: 0.0215862 valid_0's auc: 1 valid_0's l1: 0.0951457
[932] valid_0's l2: 0.0215834 valid_0's auc: 1 valid_0's l1: 0.095131
[933] valid_0's l2: 0.02158 valid_0's auc: 1 valid_0's l1: 0.0951186
[934] valid_0's l2: 0.0215747 valid_0's auc: 1 valid_0's l1: 0.0951052
[935] valid_0's l2: 0.021567 valid_0's auc: 1 valid_0's l1: 0.0950842
[936] valid_0's l2: 0.0215607 valid_0's auc: 1 valid_0's l1: 0.0950656
[937] valid_0's l2: 0.0215549 valid_0's auc: 1 valid_0's l1: 0.0950501
[938] valid_0's l2: 0.0215492 valid_0's auc: 1 valid_0's l1: 0.0950333
[939] valid_0's l2: 0.0215442 valid_0's auc: 1 valid_0's l1: 0.0950181
[940] valid_0's l2: 0.021538 valid_0's auc: 1 valid_0's l1: 0.0949997
[941] valid_0's l2: 0.0215329 valid_0's auc: 1 valid_0's l1: 0.0949882
[942] valid_0's l2: 0.0215296 valid_0's auc: 1 valid_0's l1: 0.0949695
[943] valid_0's l2: 0.0215246 valid_0's auc: 1 valid_0's l1: 0.094958
[944] valid_0's l2: 0.0215218 valid_0's auc: 1 valid_0's l1: 0.0949549
[945] valid_0's l2: 0.0215169 valid_0's auc: 1 valid_0's l1: 0.0949435
[946] valid_0's l2: 0.0215124 valid_0's auc: 1 valid_0's l1: 0.0949348
[947] valid_0's l2: 0.021508 valid_0's auc: 1 valid_0's l1: 0.0949246
[948] valid_0's l2: 0.021504 valid_0's auc: 1 valid_0's l1: 0.094918
[949] valid_0's l2: 0.0214996 valid_0's auc: 1 valid_0's l1: 0.0949079
[950] valid_0's l2: 0.0214969 valid_0's auc: 1 valid_0's l1: 0.0948961
[951] valid_0's l2: 0.0214896 valid_0's auc: 1 valid_0's l1: 0.0948728
[952] valid_0's l2: 0.0214833 valid_0's auc: 1 valid_0's l1: 0.0948522
[953] valid_0's l2: 0.0214762 valid_0's auc: 1 valid_0's l1: 0.0948291
[954] valid_0's l2: 0.0214693 valid_0's auc: 1 valid_0's l1: 0.0948044
[955] valid_0's l2: 0.021469 valid_0's auc: 1 valid_0's l1: 0.0948003
[956] valid_0's l2: 0.021462 valid_0's auc: 1 valid_0's l1: 0.0947774
[957] valid_0's l2: 0.0214615 valid_0's auc: 1 valid_0's l1: 0.0947748
[958] valid_0's l2: 0.0214549 valid_0's auc: 1 valid_0's l1: 0.0947515
[959] valid_0's l2: 0.0214553 valid_0's auc: 1 valid_0's l1: 0.0947529
[960] valid_0's l2: 0.0214544 valid_0's auc: 1 valid_0's l1: 0.0947481
[961] valid_0's l2: 0.0214478 valid_0's auc: 1 valid_0's l1: 0.0947334
[962] valid_0's l2: 0.0214413 valid_0's auc: 1 valid_0's l1: 0.0947188
[963] valid_0's l2: 0.0214348 valid_0's auc: 1 valid_0's l1: 0.0947043
[964] valid_0's l2: 0.0214305 valid_0's auc: 1 valid_0's l1: 0.094698
[965] valid_0's l2: 0.0214241 valid_0's auc: 1 valid_0's l1: 0.0946836
[966] valid_0's l2: 0.0214197 valid_0's auc: 1 valid_0's l1: 0.09468
[967] valid_0's l2: 0.0214164 valid_0's auc: 1 valid_0's l1: 0.0946764
[968] valid_0's l2: 0.0214101 valid_0's auc: 1 valid_0's l1: 0.0946622
[969] valid_0's l2: 0.0214039 valid_0's auc: 1 valid_0's l1: 0.094648
[970] valid_0's l2: 0.0213978 valid_0's auc: 1 valid_0's l1: 0.0946339
[971] valid_0's l2: 0.0213927 valid_0's auc: 1 valid_0's l1: 0.0946141
[972] valid_0's l2: 0.021387 valid_0's auc: 1 valid_0's l1: 0.094594
[973] valid_0's l2: 0.021382 valid_0's auc: 1 valid_0's l1: 0.0945744
[974] valid_0's l2: 0.0213781 valid_0's auc: 1 valid_0's l1: 0.0945629
[975] valid_0's l2: 0.0213727 valid_0's auc: 1 valid_0's l1: 0.0945424
[976] valid_0's l2: 0.0213678 valid_0's auc: 1 valid_0's l1: 0.09452
[977] valid_0's l2: 0.0213651 valid_0's auc: 1 valid_0's l1: 0.0945122
[978] valid_0's l2: 0.0213646 valid_0's auc: 1 valid_0's l1: 0.0945037
[979] valid_0's l2: 0.0213597 valid_0's auc: 1 valid_0's l1: 0.0944836
[980] valid_0's l2: 0.0213544 valid_0's auc: 1 valid_0's l1: 0.0944663
[981] valid_0's l2: 0.0213504 valid_0's auc: 1 valid_0's l1: 0.0944575
[982] valid_0's l2: 0.0213456 valid_0's auc: 1 valid_0's l1: 0.09444
[983] valid_0's l2: 0.0213383 valid_0's auc: 1 valid_0's l1: 0.09442
[984] valid_0's l2: 0.0213354 valid_0's auc: 1 valid_0's l1: 0.0944138
[985] valid_0's l2: 0.0213293 valid_0's auc: 1 valid_0's l1: 0.0943943
[986] valid_0's l2: 0.0213251 valid_0's auc: 1 valid_0's l1: 0.0943832
[987] valid_0's l2: 0.0213192 valid_0's auc: 1 valid_0's l1: 0.0943559
[988] valid_0's l2: 0.0213131 valid_0's auc: 1 valid_0's l1: 0.0943363
[989] valid_0's l2: 0.0213049 valid_0's auc: 1 valid_0's l1: 0.094306
[990] valid_0's l2: 0.0212989 valid_0's auc: 1 valid_0's l1: 0.0942866
[991] valid_0's l2: 0.0212984 valid_0's auc: 1 valid_0's l1: 0.0942869
[992] valid_0's l2: 0.021298 valid_0's auc: 1 valid_0's l1: 0.0942872
[993] valid_0's l2: 0.0212958 valid_0's auc: 1 valid_0's l1: 0.0942803
[994] valid_0's l2: 0.0212936 valid_0's auc: 1 valid_0's l1: 0.0942735
[995] valid_0's l2: 0.0212881 valid_0's auc: 1 valid_0's l1: 0.0942607
[996] valid_0's l2: 0.0212847 valid_0's auc: 1 valid_0's l1: 0.0942505
[997] valid_0's l2: 0.0212826 valid_0's auc: 1 valid_0's l1: 0.0942442
[998] valid_0's l2: 0.0212772 valid_0's auc: 1 valid_0's l1: 0.0942321
[999] valid_0's l2: 0.0212751 valid_0's auc: 1 valid_0's l1: 0.0942275
[1000] valid_0's l2: 0.0212723 valid_0's auc: 1 valid_0's l1: 0.0942257
[1001] valid_0's l2: 0.0212714 valid_0's auc: 1 valid_0's l1: 0.0942273
Early stopping, best iteration is:
[1] valid_0's l2: 0.186477 valid_0's auc: 1 valid_0's l1: 0.333038
LGBMRegressor(bagging_fraction=0.7, bagging_freq=10, boosting_type='gbdt',
class_weight=None, colsample_bytree=1.0, feature_fraction=0.9,
importance_type='split', learning_rate=0.005, max_bin=512,
max_depth=8, metric=['l2', 'auc'], min_child_samples=20,
min_child_weight=0.001, min_split_gain=0.0, n_estimators=1000,
n_jobs=-1, num_iterations=100000, num_leaves=128,
objective='regression', random_state=None, reg_alpha=0.0,
reg_lambda=0.0, silent=True, subsample=1.0,
subsample_for_bin=200000, subsample_freq=0, task='train',
verbose=0)
(6) 모델 평가
- 모델을 평가한다. (RMSE)
y_pred = gbm.predict(X_train, num_iteration=gbm.best_iteration_)
print('The rmse of prediction is:', round(mean_squared_log_error(y_pred, y_train) ** 0.5, 5))
The rmse of prediction is: 0.02951
(7) 결과 제출
- 이제 결과를 제출한다.
test_pred = np.expm1(gbm.predict(df_test, num_iteration=gbm.best_iteration_))
df_test["SalePrice"] = test_pred
df_test.to_csv("results.csv", columns=["Id", "SalePrice"], index=False)
