{ "cells": [ { "cell_type": "markdown", "id": "requested-robertson", "metadata": {}, "source": [ "
\n", " MSDS 7333 Spring 2021: Case Study 06 \n", "
\n", "
\n", "
\n", " Classification Using Neural Networks \n", "
\n", "\n", "
\n", "
\n", " Sachin Chavan,Tazeb Abera, Gautam Kapila, Sandesh Ojha \n", "
" ] }, { "cell_type": "markdown", "id": "circular-segment", "metadata": { "toc": true }, "source": [ "

Table of Contents

\n", "
" ] }, { "cell_type": "markdown", "id": "adaptive-automation", "metadata": {}, "source": [ "# Import Modules" ] }, { "cell_type": "code", "execution_count": 41, "id": "stainless-pennsylvania", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import random\n", "import seaborn as sns\n", "import matplotlib.pyplot as pyplot\n", "from sklearn.model_selection import train_test_split\n", "\n", "import matplotlib.pyplot as plt\n", "import tensorflow as tf\n", "from sklearn.preprocessing import MinMaxScaler\n", "from sklearn.metrics import accuracy_score, precision_score, recall_score\n", "from sklearn.model_selection import train_test_split\n", "\n", "from tensorflow.keras import layers, losses\n", "from tensorflow.keras.models import Model\n", "\n", "from tensorflow import keras\n", "from tensorflow.keras import regularizers\n", "from os import path\n", "import pickle \n", "import warnings\n", "warnings.filterwarnings('ignore')" ] }, { "cell_type": "markdown", "id": "economic-tooth", "metadata": {}, "source": [ "# Function definitions" ] }, { "cell_type": "code", "execution_count": 51, "id": "ranging-japan", "metadata": {}, "outputs": [], "source": [ "def plot_train_test(model_fit_history):\n", " \n", " if(path.exists(model_fit_history)):\n", " history = pickle.load(open(model_fit_history, \"rb\")) \n", " \n", " plt.figure(figsize=(15,8))\n", " pyplot.subplot(211)\n", " pyplot.title('Loss')\n", " pyplot.plot(history['loss'], label='train')\n", " pyplot.plot(history['val_loss'], label='test')\n", " pyplot.legend()\n", "\n", " pyplot.subplot(212)\n", " pyplot.title('AUC')\n", " pyplot.plot(history['auc'], label='train')\n", " pyplot.plot(history['val_auc'], label='test')\n", " pyplot.legend()\n", " pyplot.show()\n", "\n", "def model_summary(stored_model):\n", " \n", " if(path.exists(stored_model)):\n", " model = keras.models.load_model(stored_model)\n", " model.summary()\n", " # evaluate the model\n", " print('Model Evaluation : ')\n", " _,train_acc,train_auc = model.evaluate(X_train, y_train)\n", " _,test_acc,test_auc = model.evaluate(X_test, y_test)\n", " print(' ')\n", " print('Train: %.3f, Test: %.3f' % (train_auc, test_auc))\n", "\n", "def print_logs(filename):\n", " # Using readlines()\n", " log_file = open(filename, 'r')\n", " Lines = log_file.readlines()\n", " count = 0\n", " for line in Lines:\n", " if line.strip().find('2160000/2160000')!=-1:\n", " count += 1\n", " print(\"Epoch {}: {}\".format(count, line.strip()))" ] }, { "cell_type": "markdown", "id": "sweet-austin", "metadata": {}, "source": [ "# Introduction\n", "\n", "This case study is about using neural networks for classification problem with the Higgs Boson dataset. The dataset that contains observations of kinematic properties measured by particle detectors in accelerator [[1]](#References).Higgs Boson is the unusal kind of subautomic particle discovered by Scottish physicist Peter Higgs [[2]](#References). The mainstream media always referred this particle as God particle after launch of a book The God particle by Leon Lederman. This particles are produced by quantum excitation of Higgs field [[2]](#References).In 1964, Peter Higgs proposed a mechanism to explain why some particle have mass. There are several ways by which particle can attain a mass like by interacting with Higgs field. Higgs field exist just like gravitational or magnetic field that doesn't change [(P. Onyisi,2013)](#References). The experiment was carried out in year 2012 by ATLAS and CMS and they found subautomic particle have properties similar to explained by Higgs mechanism.\n", "\n", "The dataset for this case study contains 11 million observations produced using Monte Carlo simulations and has observations of singal processes that produces Higgs Boson and background process that does not and shall be used to distinguish between signal processes and background process.So this is signal vs background classification problem.\n", "\n", " " ] }, { "cell_type": "markdown", "id": "approved-worthy", "metadata": {}, "source": [ "# Business Understanding\n", "\n", "Deep learning is a new area in Machine Learning that attempts to model high level abstractions present in the raw data to understand the high varying functions underlying the data and to perform well generalized predictions for unseen data. This is accomplished through certain non-linear transformations of data through varying deep architectures such as Neural Networks. Deep learning aims at fulfilling the objective of true Artificial Intelligence and has recently been of great interest to researchers in machine learning. Tech giants like Google, Microsoft, Facebook and Baidu are investing hundreds of millions of dollars in bleeding-edge deep learning research and developing its applications [[2]](#References).\n", "\n", "As described in the paper (Baldi,2014) collisions at high energy particles are great source of finding exotic particles, basically these are classification problems and requires machine learning. Classical machine learning have limitations in learning non-linear patterns in the data and often requires features to be manually crafted and process is quite time consuming.However, Deep learning approach found to be more effective in reading and learning such non-linear structures and classifiying signals vs background processs more effectively compared to classical machine learning methods and that too witout manually crafting features as it is done in other modeling techniques.\n", "\n", "This field deals with fast and high energy collision of particles and how they form and decay. The formation and decay of these Higgs Boson can be observed and recorded. In the paper “Searching for Exotic Particles in High-Energy Physics with Deep Learning,” published in 2014, the authors used deep learning with neural networks to classify “exotic particle(s)” that results in particle collision. The Higgs Boson data was collected from the Large Hadron Collider’s detectors. In the paper above, they focused on improving past research that used other machine learning techniques. The deep learning method they used was built using the library standards in 2014 and it outperformed the previous methods. The model was implemented using Pylearn2 which is no longer supported.\n", "\n", "\n", "\n", "\n", "\n", "**Objective**\n", "\n", "Build a neural network model similar to that implemented in the paper (Baldi,2014) using TensorFlow to effectively classify signal and background processes (to find Higgs Boson particle) and to recommend ways of improving the model published in the paper." ] }, { "cell_type": "markdown", "id": "persistent-inspection", "metadata": {}, "source": [ "# Data Exploration & Quality\n", "\n", "The dataset was obtained from UCI website[[1]](#References). It contains data that was produced usign Monte Carlo simulations. It has 11 million observations. Out of 21 features first 21 after target variables are low level kinematic properties measured by particle detectors and remaining 7 featuresa are function of 21 features.These are high level features as described on the UCI website. These are derived by physicists for the purpose of classification specially for deep learning. This eliminates the need for manually crafting feautre for data modeling. This data does not contain any missing values as indicated by the website." ] }, { "cell_type": "markdown", "id": "grave-penny", "metadata": {}, "source": [ "## Load Data\n", "\n", "Out of 11 million observations, 2.7 million are randomly sampled from the HIGGS.csv file." ] }, { "cell_type": "code", "execution_count": 3, "id": "million-ecuador", "metadata": {}, "outputs": [], "source": [ "#number of records in file (excludes header)\n", "#Random sample of 2.7 Million records from the dataset \n", "random.seed(10)\n", "filename = \"data/HIGGS.csv\"\n", "n = sum(1 for line in open(filename)) - 1 \n", "s = 2700000\n", "skip = sorted(random.sample(range(1,n+1),n-s)) \n", "higgs_ds = pd.read_csv(filename,header=None,skiprows=skip)\n", "#higgs_ds = pd.read_csv(filename,header=None)" ] }, { "cell_type": "markdown", "id": "searching-ceramic", "metadata": {}, "source": [ "## DataFrame\n", "\n", "* First column is target variable 1 for signal and 0 for background followed by 28 features.\n", "* next 21 features are low level features\n", "* remaining 7 features are high level features.\n", "* Feature names obtained from the UCI website [[1]](#References)" ] }, { "cell_type": "code", "execution_count": 4, "id": "consolidated-raleigh", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
targetlepton_pTlepton_etalepton_phimissing_energy_magnitudemissing_energy_phijet_1ptjet_1etajet_1phijet_1b-tag...jet_4etajet_4phijet_4b-tagm_jjm_jjjm_lvm_jlvm_bbm_wbbm_wwbb
01.00.869293-0.6350820.2256900.327470-0.6899930.754202-0.248573-1.0920640.000000...-0.010455-0.0457673.1019611.3537600.9795630.9780760.9200050.7216570.9887510.876678
11.00.7988351.470639-1.6359750.4537730.4256291.1048751.2823221.3816640.000000...1.1288480.9004610.0000000.9097531.1083300.9856920.9513310.8032520.8659240.780118
21.00.9459741.1112441.2183370.9076390.8215371.153243-0.365420-1.5660550.000000...-0.4510180.0636533.1019610.8290240.9806480.9943600.9082480.7758790.7833110.725122
31.01.1024470.4265441.7171570.9343020.7757431.279386-0.249563-0.9263062.173076...1.207966-1.1506000.0000000.7086350.5219081.0543131.2726540.8346340.9349800.865305
41.01.0144190.012607-0.4846350.6952561.7011710.5970960.0762220.1426352.173076...1.2945790.2639770.0000001.5757661.0672651.0719920.8057691.1302060.8382510.752052
..................................................................
26999960.00.8595940.750876-0.2133080.7131650.9057921.503366-0.151531-1.0682262.173076...-1.056481-1.5867600.0000000.9730161.0599630.9899770.7277381.0579130.8755850.757173
26999970.01.379889-0.9282461.4530431.2497770.7017281.018581-1.090268-0.5454482.173076...-0.398550-0.4014660.0000000.8273990.9084121.1390071.3268751.7722001.3370611.038975
26999981.00.922366-0.263026-0.5334630.7066171.1348271.180817-0.0208200.7474590.000000...-2.092513-0.1234550.0000000.4572680.9181681.1159620.9111630.8005971.0156390.853639
26999991.01.5954731.246626-1.3213680.8657051.5324270.4560211.729906-0.3946570.000000...-2.1349870.5225660.0000000.9014680.7861230.9806191.1448890.6923460.7887540.725130
27000001.00.7005590.7742511.5201820.8471120.2112301.0955310.0524570.0245532.173076...1.5852351.7139620.0000000.3373740.8452080.9876100.8834221.8884381.1537660.931279
\n", "

2700001 rows × 29 columns

\n", "
" ], "text/plain": [ " target lepton_pT lepton_eta lepton_phi missing_energy_magnitude \\\n", "0 1.0 0.869293 -0.635082 0.225690 0.327470 \n", "1 1.0 0.798835 1.470639 -1.635975 0.453773 \n", "2 1.0 0.945974 1.111244 1.218337 0.907639 \n", "3 1.0 1.102447 0.426544 1.717157 0.934302 \n", "4 1.0 1.014419 0.012607 -0.484635 0.695256 \n", "... ... ... ... ... ... \n", "2699996 0.0 0.859594 0.750876 -0.213308 0.713165 \n", "2699997 0.0 1.379889 -0.928246 1.453043 1.249777 \n", "2699998 1.0 0.922366 -0.263026 -0.533463 0.706617 \n", "2699999 1.0 1.595473 1.246626 -1.321368 0.865705 \n", "2700000 1.0 0.700559 0.774251 1.520182 0.847112 \n", "\n", " missing_energy_phi jet_1pt jet_1eta jet_1phi jet_1b-tag ... \\\n", "0 -0.689993 0.754202 -0.248573 -1.092064 0.000000 ... \n", "1 0.425629 1.104875 1.282322 1.381664 0.000000 ... \n", "2 0.821537 1.153243 -0.365420 -1.566055 0.000000 ... \n", "3 0.775743 1.279386 -0.249563 -0.926306 2.173076 ... \n", "4 1.701171 0.597096 0.076222 0.142635 2.173076 ... \n", "... ... ... ... ... ... ... \n", "2699996 0.905792 1.503366 -0.151531 -1.068226 2.173076 ... \n", "2699997 0.701728 1.018581 -1.090268 -0.545448 2.173076 ... \n", "2699998 1.134827 1.180817 -0.020820 0.747459 0.000000 ... \n", "2699999 1.532427 0.456021 1.729906 -0.394657 0.000000 ... \n", "2700000 0.211230 1.095531 0.052457 0.024553 2.173076 ... \n", "\n", " jet_4eta jet_4phi jet_4b-tag m_jj m_jjj m_lv \\\n", "0 -0.010455 -0.045767 3.101961 1.353760 0.979563 0.978076 \n", "1 1.128848 0.900461 0.000000 0.909753 1.108330 0.985692 \n", "2 -0.451018 0.063653 3.101961 0.829024 0.980648 0.994360 \n", "3 1.207966 -1.150600 0.000000 0.708635 0.521908 1.054313 \n", "4 1.294579 0.263977 0.000000 1.575766 1.067265 1.071992 \n", "... ... ... ... ... ... ... \n", "2699996 -1.056481 -1.586760 0.000000 0.973016 1.059963 0.989977 \n", "2699997 -0.398550 -0.401466 0.000000 0.827399 0.908412 1.139007 \n", "2699998 -2.092513 -0.123455 0.000000 0.457268 0.918168 1.115962 \n", "2699999 -2.134987 0.522566 0.000000 0.901468 0.786123 0.980619 \n", "2700000 1.585235 1.713962 0.000000 0.337374 0.845208 0.987610 \n", "\n", " m_jlv m_bb m_wbb m_wwbb \n", "0 0.920005 0.721657 0.988751 0.876678 \n", "1 0.951331 0.803252 0.865924 0.780118 \n", "2 0.908248 0.775879 0.783311 0.725122 \n", "3 1.272654 0.834634 0.934980 0.865305 \n", "4 0.805769 1.130206 0.838251 0.752052 \n", "... ... ... ... ... \n", "2699996 0.727738 1.057913 0.875585 0.757173 \n", "2699997 1.326875 1.772200 1.337061 1.038975 \n", "2699998 0.911163 0.800597 1.015639 0.853639 \n", "2699999 1.144889 0.692346 0.788754 0.725130 \n", "2700000 0.883422 1.888438 1.153766 0.931279 \n", "\n", "[2700001 rows x 29 columns]" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "features = ['target','lepton_pT','lepton_eta','lepton_phi','missing_energy_magnitude','missing_energy_phi',\n", "'jet_1pt','jet_1eta','jet_1phi','jet_1b-tag','jet_2pt','jet_2eta','jet_2phi','jet_2b-tag',\n", "'jet_3pt','jet_3eta','jet_3phi','jet_3b-tag','jet_4pt','jet_4eta','jet_4phi','jet_4b-tag',\n", "'m_jj','m_jjj','m_lv','m_jlv','m_bb','m_wbb','m_wwbb']\n", "higgs_ds.rename(columns=dict(zip(higgs_ds.columns, features)),inplace=True)\n", "higgs_ds" ] }, { "cell_type": "code", "execution_count": 5, "id": "wooden-adventure", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 2700001 entries, 0 to 2700000\n", "Data columns (total 29 columns):\n", " # Column Dtype \n", "--- ------ ----- \n", " 0 target float64\n", " 1 lepton_pT float64\n", " 2 lepton_eta float64\n", " 3 lepton_phi float64\n", " 4 missing_energy_magnitude float64\n", " 5 missing_energy_phi float64\n", " 6 jet_1pt float64\n", " 7 jet_1eta float64\n", " 8 jet_1phi float64\n", " 9 jet_1b-tag float64\n", " 10 jet_2pt float64\n", " 11 jet_2eta float64\n", " 12 jet_2phi float64\n", " 13 jet_2b-tag float64\n", " 14 jet_3pt float64\n", " 15 jet_3eta float64\n", " 16 jet_3phi float64\n", " 17 jet_3b-tag float64\n", " 18 jet_4pt float64\n", " 19 jet_4eta float64\n", " 20 jet_4phi float64\n", " 21 jet_4b-tag float64\n", " 22 m_jj float64\n", " 23 m_jjj float64\n", " 24 m_lv float64\n", " 25 m_jlv float64\n", " 26 m_bb float64\n", " 27 m_wbb float64\n", " 28 m_wwbb float64\n", "dtypes: float64(29)\n", "memory usage: 597.4 MB\n" ] } ], "source": [ "higgs_ds.info()" ] }, { "cell_type": "markdown", "id": "consolidated-johns", "metadata": {}, "source": [ "## Features Summary" ] }, { "cell_type": "code", "execution_count": 6, "id": "pressing-purple", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
targetlepton_pTlepton_etalepton_phimissing_energy_magnitudemissing_energy_phijet_1ptjet_1etajet_1phijet_1b-tag...jet_4etajet_4phijet_4b-tagm_jjm_jjjm_lvm_jlvm_bbm_wbbm_wwbb
count2.700001e+062.700001e+062.700001e+062.700001e+062.700001e+062.700001e+062.700001e+062.700001e+062.700001e+062.700001e+06...2.700001e+062.700001e+062.700001e+062.700001e+062.700001e+062.700001e+062.700001e+062.700001e+062.700001e+062.700001e+06
mean5.297354e-019.912009e-011.954370e-04-7.047962e-049.991829e-011.148560e-039.909048e-01-4.237584e-051.133937e-041.000003e+00...5.290199e-043.115851e-049.986060e-011.034535e+001.024836e+001.050533e+001.009803e+009.730135e-011.033091e+009.598680e-01
std4.991151e-015.652594e-011.008588e+001.006442e+006.009023e-011.006664e+004.749358e-011.009384e+001.005909e+001.027669e+00...1.007802e+001.006712e+001.399785e+006.767933e-013.816140e-011.646220e-013.978606e-015.250037e-013.655881e-013.135694e-01
min0.000000e+002.746966e-01-2.434976e+00-1.742508e+002.370088e-04-1.743944e+001.375940e-01-2.969725e+00-1.741237e+000.000000e+00...-2.497265e+00-1.742691e+000.000000e+007.900884e-022.477852e-018.304866e-021.636103e-015.163348e-023.191644e-013.475562e-01
25%0.000000e+005.903873e-01-7.383225e-01-8.724857e-015.767537e-01-8.708085e-016.790843e-01-6.882352e-01-8.680962e-010.000000e+00...-7.133574e-01-8.720338e-010.000000e+007.907076e-018.461264e-019.857475e-017.674400e-016.740847e-018.194916e-017.703549e-01
50%1.000000e+008.531884e-019.198132e-04-2.410638e-048.920108e-011.531822e-038.950025e-01-2.543566e-051.269625e-031.086538e+00...1.204956e-032.906335e-040.000000e+008.949236e-019.506630e-019.897699e-019.164546e-018.735536e-019.473060e-018.718703e-01
75%1.000000e+001.235677e+007.382142e-018.704391e-011.294226e+008.734688e-011.170740e+006.881843e-018.677583e-012.173076e+00...7.141017e-018.727152e-013.101961e+001.024506e+001.083515e+001.020404e+001.142138e+001.139039e+001.140598e+001.059480e+00
max1.000000e+001.142379e+012.434868e+001.743236e+001.284386e+011.743257e+008.848616e+002.969674e+001.741454e+002.173076e+00...2.498009e+001.743372e+003.101961e+003.355602e+011.673047e+017.553898e+001.289145e+011.373569e+011.097622e+017.458594e+00
\n", "

8 rows × 29 columns

\n", "
" ], "text/plain": [ " target lepton_pT lepton_eta lepton_phi \\\n", "count 2.700001e+06 2.700001e+06 2.700001e+06 2.700001e+06 \n", "mean 5.297354e-01 9.912009e-01 1.954370e-04 -7.047962e-04 \n", "std 4.991151e-01 5.652594e-01 1.008588e+00 1.006442e+00 \n", "min 0.000000e+00 2.746966e-01 -2.434976e+00 -1.742508e+00 \n", "25% 0.000000e+00 5.903873e-01 -7.383225e-01 -8.724857e-01 \n", "50% 1.000000e+00 8.531884e-01 9.198132e-04 -2.410638e-04 \n", "75% 1.000000e+00 1.235677e+00 7.382142e-01 8.704391e-01 \n", "max 1.000000e+00 1.142379e+01 2.434868e+00 1.743236e+00 \n", "\n", " missing_energy_magnitude missing_energy_phi jet_1pt \\\n", "count 2.700001e+06 2.700001e+06 2.700001e+06 \n", "mean 9.991829e-01 1.148560e-03 9.909048e-01 \n", "std 6.009023e-01 1.006664e+00 4.749358e-01 \n", "min 2.370088e-04 -1.743944e+00 1.375940e-01 \n", "25% 5.767537e-01 -8.708085e-01 6.790843e-01 \n", "50% 8.920108e-01 1.531822e-03 8.950025e-01 \n", "75% 1.294226e+00 8.734688e-01 1.170740e+00 \n", "max 1.284386e+01 1.743257e+00 8.848616e+00 \n", "\n", " jet_1eta jet_1phi jet_1b-tag ... jet_4eta \\\n", "count 2.700001e+06 2.700001e+06 2.700001e+06 ... 2.700001e+06 \n", "mean -4.237584e-05 1.133937e-04 1.000003e+00 ... 5.290199e-04 \n", "std 1.009384e+00 1.005909e+00 1.027669e+00 ... 1.007802e+00 \n", "min -2.969725e+00 -1.741237e+00 0.000000e+00 ... -2.497265e+00 \n", "25% -6.882352e-01 -8.680962e-01 0.000000e+00 ... -7.133574e-01 \n", "50% -2.543566e-05 1.269625e-03 1.086538e+00 ... 1.204956e-03 \n", "75% 6.881843e-01 8.677583e-01 2.173076e+00 ... 7.141017e-01 \n", "max 2.969674e+00 1.741454e+00 2.173076e+00 ... 2.498009e+00 \n", "\n", " jet_4phi jet_4b-tag m_jj m_jjj m_lv \\\n", "count 2.700001e+06 2.700001e+06 2.700001e+06 2.700001e+06 2.700001e+06 \n", "mean 3.115851e-04 9.986060e-01 1.034535e+00 1.024836e+00 1.050533e+00 \n", "std 1.006712e+00 1.399785e+00 6.767933e-01 3.816140e-01 1.646220e-01 \n", "min -1.742691e+00 0.000000e+00 7.900884e-02 2.477852e-01 8.304866e-02 \n", "25% -8.720338e-01 0.000000e+00 7.907076e-01 8.461264e-01 9.857475e-01 \n", "50% 2.906335e-04 0.000000e+00 8.949236e-01 9.506630e-01 9.897699e-01 \n", "75% 8.727152e-01 3.101961e+00 1.024506e+00 1.083515e+00 1.020404e+00 \n", "max 1.743372e+00 3.101961e+00 3.355602e+01 1.673047e+01 7.553898e+00 \n", "\n", " m_jlv m_bb m_wbb m_wwbb \n", "count 2.700001e+06 2.700001e+06 2.700001e+06 2.700001e+06 \n", "mean 1.009803e+00 9.730135e-01 1.033091e+00 9.598680e-01 \n", "std 3.978606e-01 5.250037e-01 3.655881e-01 3.135694e-01 \n", "min 1.636103e-01 5.163348e-02 3.191644e-01 3.475562e-01 \n", "25% 7.674400e-01 6.740847e-01 8.194916e-01 7.703549e-01 \n", "50% 9.164546e-01 8.735536e-01 9.473060e-01 8.718703e-01 \n", "75% 1.142138e+00 1.139039e+00 1.140598e+00 1.059480e+00 \n", "max 1.289145e+01 1.373569e+01 1.097622e+01 7.458594e+00 \n", "\n", "[8 rows x 29 columns]" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "higgs_ds.describe()" ] }, { "cell_type": "markdown", "id": "dynamic-delhi", "metadata": {}, "source": [ "## Distribution of features\n", "\n", "Distribution of high level features is almost same. Skewness exists on feautures like lepton_phi,jet_2pt,jet_3pt and so on but all high level features shows skewness. Below two plot indicates dimensionality reduction may help to get unique features." ] }, { "cell_type": "code", "execution_count": 7, "id": "optimum-grenada", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.figure(figsize=(20,4))\n", "x=sns.boxplot(x=\"variable\", y=\"value\", data=higgs_ds.melt())\n", "loc, labels = plt.xticks()\n", "x.set_xticklabels(labels, rotation=45)\n", "x" ] }, { "cell_type": "markdown", "id": "hybrid-picnic", "metadata": {}, "source": [ "## Heatmap\n", "\n", "Heatmap shows lititle evidence of correlated features so all features (21 low level and 7 high level) shall be used for modeling." ] }, { "cell_type": "code", "execution_count": 8, "id": "historic-central", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAABIgAAAJVCAYAAAC1XM4IAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nOzde7hdVX3v//cnEeQSIJSLBSSmIpSrRoggqIg9NPVC1f4EOSBFij8pP9pS21Mqp/Z4pOfxiOI5GrBV09byUxBbQ6sUL9CqaBuCJARIAAVFcwCxVUtBUiBc9vf8sWbaxWLfkr1X5lp7v1/PM58155hjju+Ya+29s/c3Y4yZqkKSJEmSJEmz15y2OyBJkiRJkqR2mSCSJEmSJEma5UwQSZIkSZIkzXImiCRJkiRJkmY5E0SSJEmSJEmznAkiSZIkSZKkWc4EkSRJkiRJ0oBI8okkP0py2xjnk+TiJN9NsjbJ4dMR1wSRJEmSJEnS4LgUePU4518D7N9sZwEfnY6gJogkSZIkSZIGRFV9A3hgnCpvAD5ZHTcA85PsNdW4z5pqA9J4nvjJ96qt2Ccefm5boQfCHY/+sNX4B28/5Z9PU/LSzG81/g31YKvx2zTScvxnkVbjj9Daj72B0PbnXy2//3Nb/vpr25wW7/+xerK12ADbZm6r8We7HdLunzVPtvyz5+TH57Ua/+Znt3f/36oNrcUG2Dc7tBp/F9r/2fNH6y+fsf/49evv2W332O/X6Yz82WRZVS3bjCb2Ae7tOr6vKZvSH4EmiCRJkjRlbSaHJEkaJk0yaHMSQluFCSJJkiRJkqReI0+13YOx/ADYt+v4uU3ZlLgGkSRJkiRJ0vC4Cji9eZrZS4GHqmrKa4w4gkiSJEmSJKlXtbO6YpIrgOOA3ZPcB/x3YBuAqvoY8EXgtcB3gUeAX5uOuCaIJEmSJEmSBkRVnTLB+QJ+Y7rjOsVsACTZ4qX3k7wj6f/S+Ul+KcktzbYhyZ3N/if7HVuSJEmSpK1uZKQ/24AyQTT83gH0PUFUVddU1aKqWgSsBt7SHJ/e79iSJEmSJKm/TBANmCTnJVmVZG2SC5qyhUm+neTyJN9KsjzJDknOBfYGvpbka03dU5KsS3Jbkvd3tbshyXuT3JrkhiTPGacPlyb5WJLVSe5KcsJm3sNZzbWr/+yTV2zZGyFJkiRJUouqRvqyDSoTRAMkyRJgf+BIYBFwRJJjm9M/D/xJVR0E/BQ4p6ouBu4HXlVVr0qyN/B+4Bea61+S5I3N9TsCN1TVi4BvAG+foDsLm368DvhYku0mex9VtayqFlfV4v/39HGnTkqSJEmSNJicYqYWLWm2m4E1wIF0EkYA91bVimb/MuDlo1z/EuC6qvpxVT0JXA5sSjA9Dlzd7N9EJwE0nr+qqpGq+g7wvaYvkiRJkiRpBvIpZoMlwPuq6uNPK0wWAtVTt/d4Ik80K50DPMXEn/1U40mSJEmSNLwGeDpYPziCaLBcA5yZZB5Akn2S7NmcW5Dk6Gb/VOAfm/2HgZ2a/RuBVybZPclc4BTg61vYl5OSzEmyH/B84M4tbEeSJEmSJA04RxANkKq6NslBwMokABuA0+iM+LkT+I0knwDuAD7aXLYM+HKS+5t1iM4HvkZnNNIXqurzW9ide+gknHYGzq6qx7b0viRJkiRJGjojT7Xdg63KBNEAqKp5XftLgaXd55spZk9W1WmjXHsJcEnX8RXAMx4d1hNjObB8gm79fVWdPUZ/j5vgWkmSJEmShtssm2Jmgkh9deLh57YWe/mai1uLDe3eO8DB2+/Vavy23VAPthr/1Cd2aTX+p7d5qLXYbc9dHml5ybTZ/NlD+59/ZwBte04Ymd9q/KvntPezr+3vvW0zt9X4L0u7n/2Klv/da9sj9WTbXWjVp1r+2c/s+hv6adbXhra7IE0bE0RDoKrWA4dOd7tJ3gWc1FP82ao6Y7pjSZIkSZI0VAb4kfT9YIJoFquq9wLvbbsfkiRJkiSpXSaIJEmSJEmSepRrEEmSJEmSJM1ys2yKWftrSUqSJEmSJKlVJohakGSLl7pP8o4kO0xnf8aJdVySY7ZGLEmSJEmSBkqN9GcbUCaIhs87gK2SIAKOA0wQSZIkSZI0w5kgalmS85KsSrI2yQVN2cIk305yeZJvJVmeZIck5wJ7A19L8rWm7ilJ1iW5Lcn7u9rdkOS9SW5NckOS54zThz2SXNn0Y1WSlyVZCJwN/E6SW5K8IskvJ/lmkpuT/P14bUqSJEmSNNRGnurPNqBMELUoyRJgf+BIYBFwRJJjm9M/D/xJVR0E/BQ4p6ouBu4HXlVVr0qyN/B+4Bea61+S5I3N9TsCN1TVi4BvAG8fpytLgQ9V1UuANwF/VlXrgY815Yuq6h+AfwReWlUvBj4D/P4Y93VWktVJVq/fcM8WvDOSJEmSJGlr8ilm7VrSbDc3x/PoJIzuAe6tqhVN+WXAucAHe65/CXBdVf0YIMnlwLHA54DHgaubejcBvzhOP44HDk6y6XjnJPNGqfdc4C+T7AVsC3x/tMaqahmwDOANC06oceJKkiRJkjSYBni9oH4wQdSuAO+rqo8/rbAzvas3sbK5iZYnqmrTNU8x/mc9h87IoMd6+tFb7xLgf1fVVUmOA96zmX2SJEmSJGk4+Jh7bUXXAGduGq2TZJ8kezbnFiQ5utk/lc70LoCHgZ2a/RuBVybZPclc4BTg61vQj2uB39p0kGTRKLEAdgF+0Oy/dQviSJIkSZKkAWSCqEVVdS3waWBlknXAcv4jIXMn8BtJvgXsCny0KV8GfDnJ16rqh8D5wNeAW4GbqurzW9CVc4HFzULZd9BZnBrgb4Ff2bRINZ0RQ59NchPwky2II0mSJEnScJhlj7l3ilkLqmpe1/5SOotE/7tmitmTVXXaKNdeQmeq16bjK4ArJoixnE7yaaz+/AQ4eZTyu4AX9hRvSQJKkiRJkiQNMBNEkiRJkiRJvWbZGkT5j3WMNdMleRdwUk/xZ6vqvf2KOZufYrZ8zcWtxj/x8HNbjf/TkY2txt95zrNbjd+2mzasby32EfMWthZbcO8TD7Yaf99t5rcaf7b74ZMPtxp/r2ftNHEl9cVPnnqk1fi7z92h1fiS2vP5e65+xtONZorHbv1iX/6e3e5Frx3I98wRRLNIkwjqWzJIkiTNXiaHJEkabiaIJEmSJEmSeg3wgtL94FPMJEmSJEmSZjlHEEmSJEmSJPWaZYtUmyCSJEmSJEnq5RQzbQ1JNkzh2nck2SqPikhyRpKPjHHui0l8XI0kSZIkSUPOEUTD6R3AZUCrzzOtqte2GV+SJEmSpL4ZeartHmxVjiAaAEnOS7IqydokFzRlC5N8O8nlSb6VZHmSHZKcC+wNfC3J15q6pyRZl+S2JO/vandDkvcmuTXJDUmeM04fLk3ysSSrk9yV5ISu03sn+XKS7yT5QNc165PsPkpbZzXtrF6/4Z5peIckSZIkSVI/mSBqWZIlwP7AkcAi4Igkxzanfx74k6o6CPgpcE5VXQzcD7yqql6VZG/g/cAvNNe/JMkbm+t3BG6oqhcB3wDePkF3Fjb9eB3wsSTbNeWLgJOBw4CTk+w7XiNVtayqFlfV4oXzFkzqfZAkSZIkaaDUSH+2AWWCqH1Lmu1mYA1wIJ2EEcC9VbWi2b8MePko178EuK6qflxVTwKXA5sSTI8DVzf7N9FJAI3nr6pqpKq+A3yv6QvAV6rqoap6DLgDeN5m3J8kSZIkSRpwrkHUvgDvq6qPP60wWQhUT93e44k8UVWbrnmKiT/vseJt7CqbTDuSJEmSJA23WfaYe0cQte8a4Mwk8wCS7JNkz+bcgiRHN/unAv/Y7D8M7NTs3wi8MsnuSeYCpwBf38K+nJRkTpL9gOcDd25hO5IkSZIkDbdZNsXMkSAtq6prkxwErEwCsAE4jc5InTuB30jyCTpTuz7aXLYM+HKS+5t1iM4HvkZnNNIXqurzW9ide+gknHYGzq6qx5o+SZIkSZKkGcwEUUuqal7X/lJgaff5ZorZk1V12ijXXgJc0nV8BXDFBDGWA8sn6NbfV9XZPW1cClzadXxC1/7CCdqTJEmSJGk4zbIpZiaI1Fd3PPrD1mIfvP1ercUGOPHwc1uNv3zNxa3Gb/v+j6/5rcb/+zzYavwj5i1sLfaj9WRrsQH2nLNDq/Efrsdbjb/vNu1+7bf9a9R2mdtq/MfrqVbj7/WsnSau1Edz097qBf+x7GI7RjZ7qcjptfvcdn/2tfnZA2xHu9/7bXshO7Ya/4CN7f70/8tnP9Ja7FeNzJu4Uh/t+3i7/+5oZjFBNKCqaj1w6HS3m+RdwEk9xZ+tqjOmO5YkSZo92k4QSJqd2kwOaRZwBJFmsqp6L/DetvshSZIkSdIgq5ZHBm9t/lePJEmSJEnSLOcIIkmSJEmSpF6zbIqZI4gkSZIkSZJmuWlJECV5fZLzt+C666cjvsa26T1OsjDJqVtw/RlJPjL9PZMkSZIkaYDVSH+2ATUtU8yq6irgqi247pjpiN9vSebWkK5O1fUeLwROBT7dXm8kSZIkSRoSTjF7umbkybeTXJrkriSXJzk+yYok30lyZPcokyQnJbktya1JvtGUHZLkxiS3JFmbZP+mfEPzelyS65Isb2JdniTNudc2ZTcluTjJ1eP0dcckn2hi3ZzkDU35GUn+OsmXmz5/oOuaJUlWJlmT5LNJ5jXl65O8P8ka4KTR+pFkTtPeHs01c5J8d9PxKP27NMlHk9yQ5HvNfX8iybeSXNpV76NJVie5PckFXeWjvhdJ3tO0c13T7rld12xodi8EXtF8Br/TOzKouZ/jmv1faz7rG4GXddXZI8mVSVY127+fkyRJkiRJw2uyU8xeAPwv4MBmOxV4OfB7wB/01H038EtV9SLg9U3Z2cDSqloELAbuGyXGi4F3AAcDzwdelmQ74OPAa6rqCGDUxEuXdwFfraojgVcBFyXZsTm3CDgZOAw4Ocm+SXYH/hA4vqoOB1YDv9vV3r805Z8brR9VNQJcBrylqX88cGtV/XicPu4KHA38Dp1RVx8CDgEOS7Jo031U1WLghcArk7xwEu/FgcAvAUcC/z3JNj3nzwf+oaoWVdWHxupckr2AC+gkhl5O5/PYZCnwoap6CfAm4M/GaOOsJsG1+qHHfjLOWyFJkiRJ0oCaZVPMJpsg+n5VrWsSIrcDX6mqAtbRmbrUbQVwaZK3A3ObspXAHyR5J/C8qnp0lBg3VtV9TYxbmnYPBL5XVd9v6lwxQT+XAOcnuQW4DtgOWNCc+0pVPVRVjwF3AM8DXkonAbKiueatTfkmf9m8jtePTwCnN/tnAn8xQR//tuu9++ee93VhU+fNzcilm+kkjw6eoA8AX6iqjVX1E+BHwHMm6MdYjgKuq6ofV9Xj/Md7AJ0E2Eea9+oqYOdNI666VdWyqlpcVYt32W73LeyGJEmSJEnaWia7BtHGrv2RruOR3jaq6uwkRwGvA25KckRVfTrJN5uyLyb59ar66jgxntqMvnUL8KaquvNphZ3+jNZ+gL+rqlPGaO/fJgpYVfcm+eckv0Bn9M5bJrik+73rfV+fleTn6IzMeklV/Wsz9Wy7ifrB5r9/T/L0BOFkYswBXtok2SRJkiRJmrlcg2hqkuxXVd+sqncDPwb2TfJ8OqNfLgY+T2fq1GTcCTw/ycLm+OQJ6l8D/FbX+kUvnqD+DXSmsr2gqb9jkgO2oB9/Rmeq2WenYTHrnekkph5K8hzgNZPsw0QeBnbqOl4PLGrWTdqXTnIL4Jt0prXt1kxTO6nrmmuB39p00DUlTpIkSZIkDbFpTxDRWfdnXZLbgOuBW4E3A7c1U5MOBT45mYaaqWjnAF9OchOdJMdD41zyP4BtgLVJbm+Ox2v/x8AZwBVJ1tKZCnfgFvTjKmAeE08vm1BV3Upnatm36TxxbMUk+zCRtcBT6Swe/jtNu9+nM93uYmBNE+eHwHvovBcrgG91tXEusDidhcbvoLO2lCRJkiRJM88sW4MoneVwBleSeVW1oRkV9MfAd8ZbZLmNfiRZTGfx5le01YdBtf8eR7T2BXbw9nu1FXogLF9zcavxTzz83Ikr9dHxNb/V+H+fB1uN36ZH68lW4+85Z4dW4z9cj7cav21t/8qzXeZOXKmPHp/yQOLhNTf9+H/HyWv7d9oRBvt36n5r+/Pfjna/99v2QnacuFIfHbCxvZ/+f/nsR1qLDfCqkWcsybpV7ft4+//uvO6fr0jbfeiXR790cV9+uG//mnMH8j1r9yf55Ly9GXl0O7ALnSd5DUw/kpwPXAn817b6IEmSJEmSNBUDP4JoNEl+DfjtnuIVVfUbbfSnV5J38fS1e6CzPtF72+hPm96w4ITh+wKbJj8d2ThxpT7aec6zW40/20cwtW3tv93bWuwX7rhva7EFP3mq3f9J3X1uuyO4Zrt/fWq0B8VuPbvO3b7V+LPZhpF2Ry/Om7Ntq/Eltefz91w9kKNhpsOjX/hwf0YQve4dA/mebcmTwlpXVX/BNKz30y9NImjWJYMkSdLsZXJIkqThNpQJIkmSJEmSpL4a4AWl+8EEkSRJkiRJUq+R2ZUgGoZFqiVJkiRJkmaNJK9OcmeS7zYPx+o9vyDJ15LcnGRtktdONaYjiCRJkiRJknq1NMUsyVzgj4FfBO4DViW5qqru6Kr2h8BfVdVHkxwMfBFYOJW4M34EUZLXj5Ztm8R11/ejP8MmyRlJPjLGuS8mmb+1+yRJkiRJ0gx2JPDdqvpeVT0OfAZ4Q0+dAnZu9ncB7p9q0Bk/gqiqrgKu2oLrjulDd6ZdkrlV9VQbsatqykPYJEmSJEkaSH1agyjJWcBZXUXLqmpZ1/E+wL1dx/cBR/U08x7g2iS/BewIHD/Vfg31CKIkC5N8O8mlSe5KcnmS45OsSPKdJEd2j4BJclKS25LcmuQbTdkhSW5Mckszb2//pnxD83pckuuSLG9iXZ4kzbnXNmU3Jbk4ydXj9HXHJJ9oYt2c5A1N+RlJ/jrJl5s+f6DrmiVJViZZk+SzSeY15euTvD/JGuCk0fqRZE7T3h7NNXOauYt7jNG/S5N8LMnq5r08oev03mP0b32S3Udp66ymndXrN9wzuQ9TkiRJkqRBUiN92apqWVUt7tqWTdyZZzgFuLSqngu8FvhUkinleIY6QdR4AfC/gAOb7VTg5cDvAX/QU/fdwC9V1YuA1zdlZwNLq2oRsJhOZq7Xi4F3AAcDzwdelmQ74OPAa6rqCGDUxEuXdwFfraojgVcBFyXZsTm3CDgZOAw4Ocm+TeLlD4Hjq+pwYDXwu13t/UtT/rnR+lFVI8BlwFua+scDt1bVj8fp40I6Q9leB3ysucdR+zfejXZ/sS+ct2DcN0WSJEmSJD3ND4Duv7uf25R1exvwVwBVtRLYDnjGAI7NMRMSRN+vqnVNQuR24CtVVcA6nrlA0wrg0iRvB+Y2ZSuBP0jyTuB5VfXoKDFurKr7mhi3NO0eCHyvqr7f1Llign4uAc5PcgtwHZ0Pb1P25CtV9VBVPQbcATwPeCmdhNSK5pq3NuWb/GXzOl4/PgGc3uyfCfzFBH38q6oaqarvAN9r2h6rf5IkSZIkzVwjI/3ZJrYK2D/JzyXZFvjPPHPpnHuA/wSQ5CA6OYbxBoRMaCasQbSxa3+k63iEnvurqrOTHEVnhMxNSY6oqk8n+WZT9sUkv15VXx0nxlO97U5SgDdV1Z1PK+z0Z7T2A/xdVZ0yRnv/NlHAqro3yT8n+QU6I4PeMtElYxxPx/1LkiRJkqQJVNWTSX4TuIbO4JZPVNXtSf4IWN2stfxfgD9N8jt0/nY/oxkss8VmwgiiSUuyX1V9s6reTSeztm+S59MZgXMx8HnghZNs7k7g+UkWNscnT1D/GuC3utYvevEE9W+gM5XtBU39HZMcsAX9+DM6U80+O4nFrE9q1iraj85UujsnqC9JkiRJ0szU3ggiquqLVXVAVe1XVe9tyt7dJIeoqjuq6mVV9aKqWlRV1071dmdVgojOuj/rktwGXA/cCrwZuK2ZxnUo8MnJNNRMRTsH+HKSm4CHgYfGueR/ANsAa5Pc3hyP1/6PgTOAK5KspTMV7sBR6k3Uj6uAeUw8vQw6Q9RuBL4EnN1MKZMkSZIkSTPcUE8Vqqr1dJI6m47PGOPcpU3Z/zNKMxc2W2/b85rX6+isGbSp/De7qn2tqg5sRgX9MZ2FpMfq66PAr49Sfumm/jXHJ3TtfxV4ySjXLOwpGq8fL6KzOPW3x+pbl7+vqrM3o3+9/ZAkSZIkaWaY2oytoTPUCaIB8PYkbwW2BW6m8zSxgelHkvOB/4+J1x7qm5dmfluhuaEebC02wM5znt1q/OOrvfce4MTDz201/vI1F7cav+37f+GO4z5ssK+eYHLDZvvlzxeM9qyBrefse3acuFIf7T53h1bjP1pPthr/7U/u1mr8y7YZbzBx/+06d/tW4z824Wz2/jluTruffdu/d8ybs22r8dv9yQ/H0e7vPXs/2e4fkX+9zYZW45+ysd1/+36mnmgt9gH7/aS12ACPP+Kf9H01yelgM4VfTVNQVR8CPtRdluTXgN/uqbqiqn5ja/ajKX/G6Kgk7wJO6qn62e7RV5IkSZurzeSQpNmrzeSQNNOYIJpmVfUXTG69n1Y0i1u9t+1+SJIkSZI00GbZCKLZtki1JEmSJEmSejiCSJIkSZIkqVfNrhFEJogkSZIkSZJ6OcVMkiRJkiRJs4kJoiGX5Ppxzs1Pcs4k2vhykgeTXD3JmG9McvDm9FOSJEmSpKFS1Z9tQJkgGnJVdcw4p+cDEyaIgIuAX92MsG8ETBBJkiRJkjRDmCAackk2NK/nJVmVZG2SC5rTFwL7JbklyUVjtVFVXwEeHqXt9Uk+kGRdkhuTvCDJMcDrgYuadvcb5bqzkqxOsvrGDd+ZlvuUJEmSJGmrGhnpzzagXKR6BkiyBNgfOBIIcFWSY4HzgUOratEUmn+oqg5Lcjrw4ao6IclVwNVVtXy0C6pqGbAM4H3PO21wx89JkiRJkjSWAU7m9IMjiGaGJc12M7AGOJBOwmg6XNH1evQ0tSlJkiRJkgaII4hmhgDvq6qPP60wWTgNbdcY+5IkSZIkzVzlCCINn2uAM5PMA0iyT5I96awrtNMU2z6563Vlsz8d7UqSJEmSpAHhCKLhV1V1bZKDgJVJADYAp1XV3UlWJLkN+FJVnTdaA0n+gc60tHlJ7gPeVlXXNKd3TbIW2Aic0pR9BvjTJOcCJ1bV3f27PUmSJEmStr4amV2TaEwQDbEkuwEPAFTVUmBpb52qOnWidqrqFeOcvqiq3tlTfwU+5l6SJEmSpBkjVbMrIzZTJNkbuA64pKou6VOM9cDiqvrJlrbxhgUntPYFduoTu7QVGoBPb/NQq/HVruVrLm41/omHn9tq/NnsTU/NbzX+lXMfbDX+bPf6kXY//6vm+Pm35Tja/eyvw89eUjs+f8/VabsP/fLIx367L3/P7nD20oF8zxxBNKSq6n7ggMnWT3IY8Kme4o1VddQ4MRZuWe8kSZIkSRpys2yRahNEs0RVrQMWtd0PSZIkSZI0eEwQSZIkSZIk9Zpli1T7mHtJkiRJkqRZzhFEkiRJkiRJvUZm1xpEjiAaEkmuH+fc/CTnTKKNLyd5MMnVk4x5RvO0NEmSJEmSZpeRkf5sA8oE0ZCoqmPGOT0fmDBBBFwE/OpmhD0DMEEkSZIkSdIMZ4JoSCTZ0Lyel2RVkrVJLmhOXwjsl+SWJBeN1UZVfQV4eJS2j0jy9SQ3JbkmyV5JTgQWA5c37W6f5N1N7NuSLEuSMfp6VpLVSVav33DPlO9dkiRJkqStrqo/24AyQTREkiwB9geOpPPI+iOSHAucD9xdVYuq6rzNbHMb4BLgxKo6AvgE8N6qWg6sBt7StPso8JGqeklVHQpsD5wwWptVtayqFlfV4oXzFmzh3UqSJEmSpK3FRaqHy5Jmu7k5nkcnYTSVYTo/DxwK/F0zIGgu8MMx6r4qye8DOwA/A9wO/O0UYkuSJEmSNJgGeL2gfjBBNFwCvK+qPv60wmThFNu8vaqOHrdSsh3wJ8Diqro3yXuA7aYQV5IkSZKkwTUyuNPB+sEpZsPlGuDMJPMAkuyTZE866wrttIVt3gnskeTops1tkhzSnOtud1My6CdN/BO3MJ4kSZIkSRowjiAaHlVV1yY5CFjZTAfbAJxWVXcnWZHkNuBLY61DlOQfgAOBeUnuA95WVdc0C1JfnGQXOl8TH6YzfexS4GNJHgWOBv4UuA34J2BVP29WkiRJkqRWlVPMNGCS7AY8AFBVS4GlvXWq6tSJ2qmqV4xRfgtw7CjlVwJXdhX9YbNJkiRJkqQZxATRgEuyN3Ad8MGWuyJJkiRJ0uwxy9YgMkE04KrqfuCAydZPchjwqZ7ijVV11LR2bAh8epuHWo1/04b1rcY/Yt7CVuOv/bd7W43/wh33bTX+iYef22r85Wsubi122/fetivnPthq/BUP3tVq/FfM//lW44/Q7i9yV81p9/P/1qP/1Gr8g7b/2Vbjt+k62v3s1z/+QKvxF277M63GlyRNnQmiGaaq1gGL2u6HJEmaXWZzckiSNDOVj7mXJEmSJEma5WbZFDMfcy9JkiRJkjTLOYJIkiRJkiSp1yx7zL0jiCRJkiRJkmY5E0RDJMn145ybn+ScSbTx5SQPJrl6kjEvTXLiKOV7J1k+mTYkSZIkSRo6I9WfbUCZIBoiVXXMOKfnAxMmiICLgF+dhr7cX1XPSBxJkiRJkjQjjIz0ZxtQJoiGSJINzet5SVYlWZvkgub0hcB+SW5JctFYbVTVV4CHR2l7fZIPJFmX5MYkL+g6fWyS65N8b9NooiQLk9w2Rj/PSrI6yer1G+7Z0tuVJEmSJElbiYtUD5kkS4D9gSOBAFclORY4Hzi0qhZNofmHquqwJKcDHwZOaMr3Al4OHAhcBYw7tayqlgHLAN6w4ITBHT8nSZIkSdJYBng6WD84gmj4LGm2m4E1dJI2+09T21d0vR7dVf65qhqpqjuA50xTLEmSJEmSNCAcQTR8Aryvqj7+tMJk4TS0XWPsb+yJL0mSJEnSzOZj7jXgrgHOTDIPIMk+SYAVgnoAACAASURBVPaks67QTlNs++Su15VTbEuSJEmSpOE1y55i5gii4VJVdW2Sg4CVSQA2AKdV1d1JVjQLR3+pqs4brYEk/0BnWtq8JPcBb6uqa5rTuyZZS2fE0Cl9vxtJkiRJkjQQTBANiSS7AQ8AVNVSYGlvnao6daJ2quoV45y+qKre2VP/jJ7jec3reuDQieJJkiRJkjSMaoAfSd8PJoiGQJK9geuAD7bclc3W5rdT2/Mnj5i3sNX4j9aTrcZ/4Y77thr/iVa/+mCblr8CTzz83NZiL19zcWuxAQ4+6KR242+/V6vxXzb/gFbj/+0/rWk1/oKd92w1/mE77NNq/IO2/9lW43/hn25uLfZs/+wXbvszrca/5kdrW43/gl32bjX+Ts/avtX4e87dsdX4h87ZubXYiza2u0TqN5/d7u+cd49saDW+ZhYTREOgqu4HJv0bf5LDgE/1FG+sqqPGibFwy3onSZLUbnJIkqS+GOD1gvrBBNEMVFXrgEVt90OSJEmSJA0HE0SSJEmSJEm9HEEkSZIkSZI0y9XsWqS67XV8JUmSJEmS1DITRC1Lcv045+YnOWcSbXw5yYNJru4pX59k90lc/weT660kSZIkSbPESPVnG1AmiFpWVceMc3o+MGGCCLgI+NUpdMMEkSRJkiRJs5gJopYl2dC8npdkVZK1SS5oTl8I7JfkliQXjdVGVX0FeHiM07+fZF2SG5O8YJT4FwLbNzEub8o+l+SmJLcnOaur7tuS3NW09adJPjLGPZ2VZHWS1f9nwz2Teh8kSZIkSRokNVJ92QaVi1QPgCRLgP2BI4EAVyU5FjgfOLSqpvLI+oeq6rAkpwMfBk7oPllV5yf5zZ4YZ1bVA0m2B1YluRJ4NvDfgMPpJKO+Ctw6WsCqWgYsA/jlBScM7le/JEmSJEljGeBkTj+YIBoMS5rt5uZ4Hp2E0XQMv7mi6/VDk7zm3CS/0uzv2/TlZ4GvV9UDAEk+CxwwDf2TJEmSJEktc4rZYAjwvqpa1GwvqKo/n6a2u1OelWRuM53sliR/9IyOJMcBxwNHV9WL6CSttpumvkiSJEmSNBxGRvqzTUKSVye5M8l3k5w/Rp03J7mjWR7m01O9XRNEg+Ea4Mwk8wCS7JNkTzpTuXaaYtsnd72urKqnuhJR727OPZFkm2Z/F+Bfq+qRJAcCL23KVwGvTLJrkmcBb5pivyRJkiRJUo8kc4E/Bl4DHAyckuTgnjr7A/8VeFlVHQK8Y6pxnWLWvqqqa5McBKxMArABOK2q7k6yIsltwJeq6rzRGkjyD8CBwLwk9wFvq6prmtO7JlkLbAROGaMPy4C1SdYAZwJnJ/kWcCdwQ9PJHyT5n8CNwAPAt4GHpnz3kiRJkiQNovbWIDoS+G5VfQ8gyWeANwB3dNV5O/DHVfWvAFX1o6kGNUHUoiS70Um2UFVLgaW9darq1InaqapXjFG+sNl95wTXv7OnzmvGqPrpqlrWjCD6G+BzE/VNkiRJkqSh1KcEUfO08LO6ipY1D3vaZB/g3q7j+4Cjepo5oGlrBTAXeE9VfXkq/TJB1JIkewPXAR9suSub4z1JjqezJtG1mCCSJEmSJGmzdD/5ewqeReeBUscBzwW+keSwqnpwKg2qBVV1P5vxFLAkhwGf6ineWFW9WcS+qarf29xrnkX60ZVJGWF2PZKw155zdmg1/sP1eKvx/3zBo63GP/ueHVuN36aDDzqp1fh3fOuzrcY/8fBzW43ftvP3fmWr8Y96rN2f/X/Gw63Gb9PrfvbF/HRkY2vxT5jznNZiA3yDLf59fEZ45R6HtBp/SXZrNf5zn2j3Z89n5v601fh7PdXe0rY/N3dDa7EBXrxDu79zPrzB5wn1U1Vr39s/oPNE8U2e25R1uw/4ZlU9AXw/yV10EkartjSoCaIhUVXrgEVt90OSJGk0bSaHJEmaYVYB+yf5OTqJof8M9C4/8zk66wz/RZLd6QxA+d5UgpogkiRJkiRJ6tXSItVV9WSS36TzxPO5wCeq6vYkfwSsrqqrmnNLktwBPAWcV1X/MpW4JogkSZIkSZJ6tfcUM6rqi8AXe8re3bVfwO8227Rob7KoJEmSJEmSBoIjiCRJkiRJknpUiyOI2uAIoiGX5Ppxzs1Pcs4E1y9KsjLJ7UnWJjl5EjHfmOTgLemvJEmSJEkaPCaIhlxVHTPO6fnAuAki4BHg9Ko6BHg18OEk8ye45o2ACSJJkiRJ0sw1Uv3ZBpQJoiGXZEPzel6SVc0ooAua0xcC+yW5JclFo11fVXdV1Xea/fuBHwF7NG2uT/KBJOuS3JjkBUmOAV4PXNS0u98ofToryeokq9dv+D/Tf9OSJEmSJGlauQbRDJBkCbA/cCQQ4KokxwLnA4dW1aJJtnMksC1wd1fxQ1V1WJLTgQ9X1QlJrgKurqrlo7VTVcuAZQC/suCXBzc9KkmSJEnSWEba7sDWZYJoZljSbDc3x/PoJIzumWwDSfYCPgW8taq6vw2u6Hr90NS7KkmSJEnS4Jtti1SbIJoZAryvqj7+tMJk4aQuTnYGvgC8q6pu6DldY+xLkiRJkqQZwjWIZoZrgDOTzANIsk+SPYGHgZ3GuzDJtsDfAJ8cY8rYyV2vK5v9CduVJEmSJGmouUi1hkxV1bXAp4GVSdYBy4GdqupfgBVJbhtrkWrgzcCxwBnNotO3JOles2jXJGuB3wZ+pyn7DHBekptHW6RakiRJkiQNF6eYDbEkuwEPAFTVUmBpb52qOnW8NqrqMuCycapcVFXv7LlmBT7mXpIkSZI0k82yRapTNbjDmzS2JHsD1wGXVNUlfYqxHlhcVT/Z0jbesOCE1r7ATn1il7ZCA/DpbR5qNb7a9aan5rca/8q5D7YafzZbvubiVuOfePi5rcaf7V5T7X7vfyl+77flZWn3s19RfvaS2vH5e65O233ol3896bi+/D2762evG8j3zBFEQ6qq7gcOmGz9JIfReUpZt41VddQ4MRZuWe8kSZIkSdIwMUE0S1TVOmDRhBUlSZIkSdKsm2LmItWSJEmSJEmznCOIJEmSJEmSetQAP5K+H0wQSZIkSZIk9XKKmQZRkuvHOTc/yTkTXL8oycoktydZm+TkScQ8o3lamiRJkiRJmsFMEA2JqjpmnNPzgXETRMAjwOlVdQjwauDDyYTPYz0DMEEkSZIkSZp1aqQ/26AyQTQkkmxoXs9LsqoZBXRBc/pCYL8ktyS5aLTrq+quqvpOs38/8CNgj6bNI5J8PclNSa5JsleSE4HFwOVNu9sneXcT+7Yky5JkjL6elWR1ktXrN9wzvW+EJEmSJEmadiaIhkiSJcD+wJF0Hll/RJJjgfOBu6tqUVWdN4l2jgS2Be5Osg1wCXBiVR0BfAJ4b1UtB1YDb2nafRT4SFW9pKoOBbYHThit/apaVlWLq2rxwnkLpnzfkiRJkiRtdSN92gaUi1QPlyXNdnNzPI9OwmjSw3SS7AV8CnhrVY0kORg4FPi7ZkDQXOCHY1z+qiS/D+wA/AxwO/C3W3AfkiRJkiRpgJggGi4B3ldVH39aYbJwUhcnOwNfAN5VVTd0tXl7VR09wbXbAX8CLK6qe5O8B9hus3ovSZIkSdKQGOT1gvrBKWbD5RrgzCTzAJLsk2RP4GFgp/EuTLIt8DfAJ5vpY5vcCeyR5Oim3jZJDmnOdbe7KRn0kyb+idNxQ5IkSZIkDSSnmGlAVVVdm+QgYGUzHWwDcFpV3Z1kRZLbgC+NsQ7Rm4Fjgd2SnNGUnVFVtzQLUl+cZBc6XxMfpjN97FLgY0keBY4G/hS4DfgnYFW/blSSJEmSJG1dJoiGQJLdgAcAqmopsLS3TlWdOl4bVXUZcNkY526hkzzqLb8SuLKr6A+bTZIkSZKkGc0pZhooSfYGVgIfbLsvkiRJkiRpZkpVtd0HTaMkh9F5Slm3jVV1VBv9ecOCE2btF9i9TzzYavx9t5nfavyfPPVIq/F3n7tDq/HbtuLBu1qL/bL5B7QWW7B8zcWtxj/x8HNbjT/b/eCJh1qNv882u7Qafzb70VP/1mr8Pefu2Gp8Se35/D1Xp+0+9MuP/tMr+/L37J5f+fpAvmdOMZthqmodsKjtfkiSpNnF5JAkaaZxipkkSZIkSZJmFUcQSZIkSZIk9aqBnAnWN44gkiRJkiRJmuUcQSRJkiRJktTDNYg0sJJcP865+UnOmeD6RUlWJrk9ydokJ08i5qVJThylfO8kyyfXc0mSJEmShkuNpC/boDJBNESq6phxTs8Hxk0QAY8Ap1fVIcCrgQ8n2aJnoVfV/VX1jMSRJEmSJEkaPiaIhkiSDc3reUlWNaOALmhOXwjsl+SWJBeNdn1V3VVV32n27wd+BOzRtLk+yQeSrEtyY5IXdF16bJLrk3xv02iiJAuT3DZGP89KsjrJ6vUb7pmWe5ckSZIkaWuqkf5sg8oE0ZBJsgTYHzgSWAQckeRY4Hzg7qpaVFXnTaKdI4Ftgbu7ih+qqsOAjwAf7irfC3g5cAKdRNS4qmpZVS2uqsUL5y2Y5J1JkiRJkqS2uEj18FnSbDc3x/PoJIwmPVQnyV7Ap4C3Vj0tf3lF1+uHuso/19S7I8lztrTjkiRJkiQNi5plj7k3QTR8Aryvqj7+tMJk4aQuTnYGvgC8q6pu6DldY+xv7IkvSZIkSZJmEKeYDZ9rgDOTzANIsk+SPYGHgZ3GuzDJtsDfAJ+sqtGeQHZy1+vK6euyJEmSJEnDZbatQeQIouFSVXVtkoOAlUkANgCnVdXdSVY0C0d/aYx1iN4MHAvsluSMpuyMqrql2d81yVo6I4ZO6eudSJIkSZI0wAb5kfT9YIJoSCTZDXgAoKqWAkt761TVqeO1UVWXAZeNU+WiqnpnzzVn9BzPa17XA4dOouuSJEmSJGnAmSAaAkn2Bq4DPthyVzZbm6Pn2p4/ue8281uN3/bIxd3n7tBq/EfryVbjb592f7y+Yv7Ptxb7b/9pTWuxAc7f+5Wtxl838tNW4594+Lmtxl++5uJW4x992Ftbjb/PNrvM6vhf+udbJq7UJ4fs+rzWYgMs2HbXVuPvOXfHVuO3+dkD/Kc9D2s1/s5znt1q/MfrqVbjz8s2rcXej+1biw1wXzZOXKmPHhvk+UozQNXEdWYSE0RDoKruBw6YbP0kh9F5Slm3jVV11DgxFm5Z7yRJktpPEEiSpKkxQTQDVdU6YFHb/ZAkSZIkaVi5BpEkSZIkSdIsN9sSRG0v0yJJkiRJkqSWOYJIkiRJkiSpx2xbpNoRRC1Lcv045+YnOWeC6xclWZnk9iRrk5zcdW59kt0n0Yc/2LxeS5IkSZKkmcQEUcuq6phxTs8Hxk0QAY8Ap1fVIcCrgQ8n2dznq5sgkiRJkiSpS42kL9ugMkHUsiQbmtfzkqxqRgFd0Jy+ENgvyS1JLhrt+qq6q6q+0+zfD/wI2KOryu8nWZfkxiQvGCX+hcD2TYzLm7LPJbmpGZV0VlfdtyW5q2nrT5N8ZIx7OivJ6iSr/8+Gezb/TZEkSZIkqWVV6cs2qFyDaAAkWQLsDxwJBLgqybHA+cChVTWpR9YnORLYFri7q/ihqjosyenAh4ETuq+pqvOT/GZPjDOr6oEk2wOrklwJPBv4b8DhwMPAV4FbR+tHVS0DlgH88oITZtmsTUmSJEmSho8JosGwpNlubo7n0UkYTXr4TZK9gE8Bb62qka5TV3S9fmiSzZ2b5Fea/X2bvvws8PWqeqCJ91nggMn2T5IkSZKkYfK0v6xnARNEgyHA+6rq408rTBZO6uJkZ+ALwLuq6oae090jeCrJXOCm5viqqnp3T1vHAccDR1fVI0muA7ab3G1IkiRJkqRh5BpEg+Ea4Mwk8wCS7JNkTzpTuXYa78Ik2wJ/A3yyqpaPUuXkrteVVfVUVS1qtk3JoSeSbNPs7wL8a5McOhB4aVO+Cnhlkl2TPAt40xbeqyRJkiRJA2+k0pdtUDmCqH1VVdcmOQhYmQRgA3BaVd2dZEWS24AvVdV5o1z/ZuBYYLckZzRlZ1TVLc3+rknWAhuBU8bowzJgbZI1wJnA2Um+BdwJ3NB08gdJ/idwI/AA8G3goSnduSRJkiRJGggmiFqUZDc6yRaqaimwtLdOVZ06XhtVdRlw2RjnFja775ygjXf21HnNGFU/XVXLmhFEfwN8brx2JUmSJEkaVoP8xLF+MEHUkiR7A9cBH2y5K5vjPUmOp7Mm0bWYIJIkSZIkzVA1YoJIW0FV3c9mPAUsyWF0nlLWbWNVHTWtHRtHVf3eZl9Dm0+5n13fzL22y9xW4z9eT7Ua/+1P7tZq/Mu2aXcG5kiL33sLdt6ztdgARz3W5s8dWLdtq+Fbd/Rhb201/sp1/3+r8U88/NxW47fpNc9ZxHHMby3+8x9v91Ezn+CnrcZv27F7HtJq/GPm/Eyr8Z/3ZLu/d14598FW4z837T3TZv/H233vXzzS7j/87f7GrZnGBNGQqKp1wKK2+yFJkjSaNpNDkiT1Q7X7/45bnU8xkyRJkiRJGiBJXp3kziTfTXL+OPXelKSSLJ5qTEcQSZIkSZIk9WhrDaIkc4E/Bn4RuA9YleSqqrqjp95OwG8D35yOuI4gkiRJkiRJ6jFS6cs2CUcC362q71XV48BngDeMUu9/AO8HHpuO+zVBJEmSJEmSNDj2Ae7tOr6vKft3SQ4H9q2qL0xXUBNEQy7J9eOcm5/knAmuf16SNUluSXJ7krMnEfOMJHtvSX8lSZIkSRoGVenLluSsJKu7trM2p19J5gD/G/gv03m/rkE05KrqmHFOzwfOAf5knDo/BI6uqo1J5gG3NXMb7x/nmjOA24Dx6kiSJEmSpB5VtQxYNk6VHwD7dh0/tynbZCfgUOC6JAA/C1yV5PVVtXpL++UIoiGXZEPzel6SVUnWJrmgOX0hsF8zOuii0a6vqseramNz+Gy6viaSbEjyoWZk0VeS7JHkRGAxcHnT7vaj9Onfs6H3bLhnOm9XkiRJkqStoqo/2ySsAvZP8nNJtgX+M3DVf/SrHqqq3atqYVUtBG4AppQcAhNEM0KSJcD+dBayWgQckeRY4Hzg7qpaVFXnjXP9vknW0pnj+P6u0UM7Aqur6hDg68B/r6rlwGrgLU27j/a2V1XLqmpxVS1eMG/BdN6qJEmSJElbRVuLVFfVk8BvAtcA3wL+qqpuT/JHSV7fr/t1itnMsKTZbm6O59FJGE1q+E5V3Qu8sFlX6HNJllfVPwMjwF821S4D/npaey1JkiRJkp6hqr4IfLGn7N1j1D1uOmKaIJoZAryvqj7+tMJk4eY0UlX3J7kNeAWwfLQqW9pBSZIkSZKGSU3ukfQzhlPMZoZrgDObRaZJsk+SPYGH6SxeNaYkz920jlCSXYGXA3c2p+cAJzb7pwL/2OxP2K4kSZIkSRoejiAaflVV1yY5CFjZrGC+ATitqu5OsqIZFfSlMdYhOgj4X0mKzkikD1bVuubcvwFHJvlD4EfAyU35pcDHkjxK5wloz1iHSJIkSZKkYTbJBaVnDBNEQyzJbsADAFW1FFjaW6eqTh2vjar6O+CF45z/3VHKrgSu3Nz+SpIkSZKkwZSabSmxGaJZUPo64JKquqRPMTZU1byptPGGBSe09gV2wsj8tkIDcPWcB1uNr3a9vuWvv6v8+mvNa6rdz/5L8bNv0/I1F7ca/8TDz201/mz24uzSavyb66FW40uavT5/z9UzdqGe1c99Y1/+nl183+cG8j1zBNGQah5Ff8Bk6yc5DPhUT/HGqjpqnBhTSg5JkiRJkjSsZtsi1SaIZolmXaFFbfdDkiRJkiQNHhNEkiRJkiRJPUZm2QgiH3MvSZIkSZI0yzmCSJIkSZIkqcdse6SXI4iGRJLrxzk3P8k5E1z/vCRrktyS5PYkZ08i5juS7LAl/ZUkSZIkaZiNVPqyDSoTREOiqo4Z5/R8YNwEEfBD4OiqWgQcBZyfZO8JrnkHYIJIkiRJkqQZzgTRkEiyoXk9L8mqJGuTXNCcvhDYrxkddNFo11fV41W1sTl8Nl2ffZIlSVY2I4z+L3v3HiZpWd55/PubkfNwFlQQGAIaREGUcQwqCIqs7hrdKB6CRlET4mKixgs2RFFRs1EjxKBmo2wMeIpByUE8oBgUkRGUEQgDCiiKomhQUWSQg9L3/lHvSE3Z3dPDTNVT3fX9zPVe89Z7up+3n+qqrruew0eTLEnycmAX4PNJPt8d9/dJVnYtkN7wm1EkSZIkSVoYqjKUZVyZIJpHkhwBPAhYTm/K+gOTHAKcAFxXVQdU1fGznL9bkiuAG4C3VtWNSe4LnAgcXlWPBFYCr6qqdwA3AodV1WHdJV5TVcuA/YHHJ9l/hjjHdImkldev/u5GuXdJkiRJkjQ8DlI9vxzRLZd1j5fQSxjNKQtTVTcA+3ddy/49yVnAo4B9gRVJADYFLprhEs9Ocgy9580DuvOumCbOacBpAE/f/amTNq6XJEmSJGkBmGpdgBEzQTS/BHhzVb1nrY3J0vW5SNdy6ErgYOBO4LNV9fuzBk72BI4DHlVVP01yBrD5+sSVJEmSJGm+KMa3O9gw2MVsfvkM8OIkSwCS7JpkZ+BWYOvZTkzywCRbdOvbA48DrgEuBh6bZO9u31ZJHtyd1n/dbYDbgFuS3A94yka9M0mSJEmS1IwtiOaPqqpzkzwEuKjrDrYaeH5VXZdkRdcq6JwZxiF6CHBKkqLXEunkqloFkORo4MNJNuuOPRG4ll43sU8nubGqDktyGXA1vTGMVgzvViVJkiRJamtqwgZMMUE0DyTZEbgZoKpOBU4dPKaqjprtGlX1WXqDS0+373P0xiIa3P5O4J19j49en3JLkiRJkqT5wQTRmOsGlD4fOLlxUSRJkiRJmhhTEzYGkQmiMVdVNwIPXueBnST7AR8Y2HxnVT16oxZsHvjEop81jf+DX93aNP4D7jPrsFRD99O7b28af/vFWzSNf3bj59/Xb/9hs9gP2eL+zWKPg3PStu6//8tbmsbfdZNtm8Zv7chHvrxp/LMufUfT+K3vv6XLqu3v3o/v/kXT+PddvGXT+JKkDWeCaIHpxhU6oHU5JEnSZJnk5JAkaWGatFnMTBBJkiRJkiQNmGpdgBFzmntJkiRJkqQJZwsiSZIkSZKkAZPWxcwWRJIkSZIkSRPOBNE8kuRLs+zbLsmx6zh/jySXJrk8yVVJXjqHmOcnWTbN9mVJ2k6VIkmSJEnSkEwNaRlXdjGbR6rqMbPs3g44Fvi/sxzzA+CgqrozyRLgyiRnV9WN96IsK4GV63ueJEmSJEnzwTgnc4bBFkTzSJLV3f/HJ7kkyRVJ3tDtfguwV9c66G3TnV9Vd1XVnd3Dzeir/ySrk7y9a1l0XpKd+k59VpKvJLk2ycHd8Ycm+cQM5TwmycokK69f/d0NvGtJkiRJkjRsJojmmSRHAA8ClgMHAAcmOQQ4Abiuqg6oquNnOX+3JFcANwBv7Ws9tBWwsqoeCnwBeH3fafepquXAKwe2T6uqTquqZVW1bOmS3e/FXUqSJEmS1FaRoSzjygTR/HNEt1wGXArsQy9hNCdVdUNV7Q/sDbwwyf26XVPAmd36B4HH9Z32r93/XwWW3uuSS5IkSZKkseQYRPNPgDdX1XvW2pgsXZ+LVNWNSa4EDgbOmu6QvvU13dLuxueMJEmSJGkCTI1vY5+hsAXR/PMZ4MXdINMk2TXJzsCtwNaznZjkgUm26Na3p9dK6Jpu9yLgyG79KODCIZRdkiRJkqR5YYoMZRlXtgaZX6qqzk3yEOCiJACrgedX1XVJVnStgs6ZYRyihwCnJCl6LZFOrqpV3b7bgOVJTgRuAp4z9LuRJEmSJEljwQTRPJFkR+BmgKo6FTh18JiqOmq2a1TVZ4H9Z9n/qmm2Hdq3/mO6MYiq6nzg/DkUXZIkSZKkeafWfciCYoJoHkiyC71kzMmNi7LeFjVsPjfV+Nf5AfeZtcff0C1O2x6k2y/eomn8O+rupvE3z+Km8R+yxf2bxf7kDy9rFhvg4J33bRp/m0WbNY2/6ybbNo1/zn9d3jT+W+93aNP45/OzpvGPfOTLm8Y/69J3NIv9hIf/UbPYADs0ft+77+Itm8Zv/dp/9C4HNY2fxl1Gbpq6vWn8ln933Vm/bBYbYOtFmzeNv2X8SK+Nx2fTPNBNRf/guR6fZD/gAwOb76yqR88SY8m9LJ4kSVLT5JAkScMw1boAI2aCaAHqxhU6oHU5JEmSJEnS/GCCSJIkSZIkacBUxnfGsWEwQSRJkiRJkjRg0gapbjuKrSRJkiRJkpozQdRYki/Nsm+7JMeu4/w9klya5PIkVyV5ad++1XOIv84YkiRJkiRNmqkhLePKBFFjVfWYWXZvB6wrefMD4KCqOgB4NHBCkl3WowhziSFJkiRJkhYwE0SNrWnlk+T4JJckuSLJG7rdbwH26loHvW2686vqrqq6s3u4GQN1muTtXcui85LsNM0l1oqRZEl37KVJViV5et+1XpvkmiQXJvlwkuM29P4lSZIkSRpHUxnOMq4cpHoMJDkCeBCwHAhwdpJDgBOAh3Wtg2Y7fzfgk8DewPFVdWO3aytgZVX9WZLXAa8H/mTg9LViJLkP8HtV9fMk9wUuTnI2sAx4JvBwYBPgUuCrM5TnGOAYgAO234+lS/aY+w9DkiRJkqQxMMUYZ3OGwBZE4+GIbrmMXuJlH3oJozmpqhuqan96CaIXJrlft2sKOLNb/yDwuDlcLsBfJbkC+A9gV+B+wGOBj1XVHVV1K/DxWcpzWlUtq6plJockSZIkSRp/tiAaDwHeXFXvWWtjsnR9LlJVNya5EjgYOGu6Q7rWRmuSO+8GPj1wzPOAnYADq+qXSa4HNl+fckiSJEmSNN85zb1a+Azw4iRLAJLsmmRn4FZg69lOTPLAJFt069vTayV0Tbd7EXBkt34UcGHX2uiAbnn3NDG2BW7qkkOHAWuaAK0AfjfJ5l05HCJmhgAAIABJREFUn7qB9yxJkiRJksaELYjaq6o6N8lDgIuSAKwGnl9V1yVZ0bUKOqeqjp/m/IcApyQpei2RTq6qVd2+24DlSU4EbgKeM03wn/THAN4KfDzJKmAlcHV33CXdWERXAP8FrAJu2Vg/BEmSJEmSxsk4Dyg9DCaIGkqyI3AzQFWdCpw6eExVHTXbNarqs8D+M+xbMpdyTBPjoBkOPbmqTkqyJXABMwxSLUmSJEnSfDfVugAjZoKokSS7AOcDJzcuyvo4Lcm+9MYkel9VXdq6QJIkSZIkacOZIGqkm4r+wXM9Psl+wAcGNt9ZVY/eqAWbxbpaM03njvrVMIoyJ5tmcbPY46Bq0oZUW9uhi3ZsGv/i+lnT+C3tvs3OTeM/ddH91n3QEF3A5NY9wEO3bzt75W/d1fa7vvM3bRq+qSMf+XJuvvv2ZvE/95//r1ls6N3/JDvl/oc1jf8d2v3NCXD/avux6oe0+90D2G3xVs1i35+2L7xbVNs+SIsnbBr2UZu0T1QmiOaJblyhA1qXQ5IkaTotk0OSJGnDmSCSJEmSJEka4CDVkiRJkiRJE27SBqle1LoAkiRJkiRJassWRJIkSZIkSQNsQaR5JcmXZtm3XZJj53idbZJ8L8m75nDs0Ul2WZ9ySpIkSZKk8WWCaJ6rqsfMsns7YE4JIuBNwAVzPPZowASRJEmSJGnBqgxnGVcmiOa5JKu7/49PckmSK5K8odv9FmCvJJcnedss1zgQuB9w7uC1k7w9yVVJzkuyU5IjgWXAh7rrbjHN9Y5JsjLJyhtW37CxblWSJEmSJA2JCaIFIMkRwIOA5cABwIFJDgFOAK6rqgOq6vgZzl0EnAIcN83urYCVVfVQ4AvA66vqLGAl8LzuurcPnlRVp1XVsqpattuS3TbGLUqSJEmSNFJTQ1rGlQmiheGIbrkMuBTYh17CaC6OBT5VVd+bZt8UcGa3/kHgcRtYTkmSJEmS5oWWCaIkT05yTZJvJjlhmv2vSvK1rhfReUn2uPd32uMsZgtDgDdX1XvW2pgsncO5BwEHd4NZLwE2TbK6qn7jCQjUhhZUkiRJkiTNLMli4O+AJwHfAy5JcnZVfa3vsMuAZVX1iyT/C/hr4DkbEtcWRAvDZ4AXJ1kCkGTXJDsDtwJbz3ZiVT2vqnavqqX0upm9vy85tAg4sls/CriwW1/ndSVJkiRJms9qSMscLAe+WVXfqqq7gH8Gnr5W2ao+X1W/6B5eDDzw3t3lPUwQzX9VVecC/wRclGQVcBawdVX9BFiR5MrZBqmexW3A8iRXAk8A3thtPwN490yDVEuSJEmSpOn1T+zULccMHLIr0D/j0/e6bTN5CXDOhpbLLmbzWJIdgZsBqupU4NTBY6rqqLler6rOoJf86d/2qmmO+xfgX9avtJIkSZIkzR9TQ5qSvqpOA07bGNdK8nx6M40/fkOvZYJonkqyC3A+cHLjosxq0yxuFvux2a5ZbIAV9bOm8acmfMioixv//A+l7fPvfNrd/35bzvblxvBd0PDewdee3Tfdvmn8f+TnTeM/Its2jX9Z3dIs9g6L2zYqPvKRL28a/6xL39E0fuv7/1zj197W0wJd1zZ8824hP5q6o11s2sXWwtfwpeX7QP+U4A/stq0lyeHAa4DHV9WdGxrUBNE8VVU3Ag+e6/FJ9gM+MLD5zqp69CwxltzL4kmSJEmSpHvnEuBBSfaklxh6Lr1xgX8tySOA9wBPrqqbNkZQE0QToqpWAQe0LockSZIkSfNBqxZEVfWrJH9Cb0KqxcA/VtVVSd4IrKyqs4G30ZuJ/KNJAL5bVU/bkLgmiCRJkiRJksZIVX0K+NTAttf1rR++sWOaIJIkSZIkSRowaaO6miCSJEmSJEkaMKxZzMZV6wHvNUdJvjTLvu2SHDvH62yT5HtJ3jWHY1+ZZMv1KackSZIkSZp/TBDNE1X1mFl2bwfMKUEEvAm4YI7HvhIwQSRJkiRJmjhTQ1rGlQmieSLJ6u7/45NckuSKJG/odr8F2CvJ5UneNss1DgTuB5w7sP2IJBcluTTJR5MsSfJyYBfg80k+3x3390lWJrmqL7YkSZIkSZrnTBDNI0mOAB4ELKc3Zf2BSQ4BTgCuq6oDqur4Gc5dBJwCHDew/b7AicDhVfVIYCXwqqp6B3AjcFhVHdYd/pqqWgbsDzw+yf4zxDqmSyStvH71dzfwriVJkiRJGr0a0jKuHKR6fjmiWy7rHi+hlzCaSxbmWOBTVfW9ZK2Rtn4H2BdY0W3fFLhohms8O8kx9J43D+jOu2LwoKo6DTgN4Om7P3Wcn/+SJEmSJAkTRPNNgDdX1XvW2pgsncO5BwEHd4NZLwE27bqtrQA+W1W/P2vgZE96rY8eVVU/TXIGsPl634EkSZIkSfPA1Fi399n47GI2v3wGeHGSJQBJdk2yM3ArsPVsJ1bV86pq96paSi/R8/6qOgG4GHhskr27a26V5MHdaf3X3Qa4Dbglyf2Ap2zcW5MkSZIkaXxM2iDVtiCaP6qqzk3yEOCirjvYauD5VXVdkhVJrgTOmWkcohku+qMkRwMfTrJZt/lE4Fp63cQ+neTGqjosyWXA1cAN9FoeSZIkSZKkBcAE0TyQZEfgZoCqOhU4dfCYqjpqrterqjOAM/oefw541DTHvRN4Z9/jo+deakmSJEmS5q/J6mBmF7Oxl2QXeoNGn9y6LJIkSZIkaWGyBdGYq6obgQev88BOkv2ADwxsvrOqHr1RCzYPrKifNY3/47t/0TT+fRdv2TT+6qm7msZfsmjTpvHPp+3z7/q7bm4We+mmOzSLPQ5av/bcdPdtTePvvHirpvFbu6xuaRp/0t97WjrykS9vGv+sS9/RNH7r+5ekYRjn8YKGwQTRAlNVq4ADWpdDkiRNlklODkmSFqaptC7BaNnFTJIkSZIkacLZgkiSJEmSJGnA1IQNU20LIkmSJEmSpAlnCyJJkiRJkqQBk9V+yBZE80qSL82yb7skx87xOtsk+V6Sd83h2POTLJtm+7IkbafLkCRJkiRpSKaGtIwrE0TzSFU9Zpbd2wFzShABbwIu2MCyrKwq5zOVJEmSJGkBMEE0jyRZ3f1/fJJLklyR5A3d7rcAeyW5PMnbZrnGgcD9gHMHr53k7UmuSnJekp36dj8ryVeSXJvk4O74Q5N8YoYYxyRZmWTl9au/uwF3LEmSJElSG1PUUJZxZYJonklyBPAgYDlwAHBgkkOAE4DrquqAqjp+hnMXAacAx02zeytgZVU9FPgC8Pq+ffepquXAKwe2T6uqTquqZVW1bOmS3dfj7iRJkiRJUgsOUj3/HNEtl3WPl9BLGM2lqc6xwKeq6ntJBvdNAWd26x8E/rVv35r1rwJL17/IkiRJkiTNL+Pb1mc4TBDNPwHeXFXvWWtjsnQO5x4EHNwNZr0E2DTJ6qo6YZpj+38X7uz+vxufM5IkSZIkLTh2MZt/PgO8OMkSgCS7JtkZuBXYerYTq+p5VbV7VS2l183s/X3JoUXAkd36UcCFwyi8JEmSJEnzwaTNYmZrkPmlqurcJA8BLuq6ia0Gnl9V1yVZkeRK4JyZxiGaxW3A8iQnAjcBz9moJZckSZIkaR4Z5wGlh8EE0TyRZEfgZoCqOhU4dfCYqjpqrterqjOAMwa2vWqa4w7tW/8x3RhEVXU+cP5c40mSJEmSpPFlgmgeSLILvWTMyY2LovVw38VbNo2/OG17kC5ZtGnT+K2bbrbuv7t00x2axf7MTVc0iw3w+J0e2jT+5lncNP7Oi7dqGv+c/7q8afxDdm5b/1tlk6bxW7/3fPKHl637oCE55f6HNYsN8Dl+1jT+kY98edP4Z136jqbxT1z2mqbxb+KupvF/PHXnug8aoh/9anXT+Nfe+v1msR+6TdtZm3dYvEXT+AvdZLUfMkE0L1TVjcCD53p8kv2ADwxsvrOqHj1LjCX3sniSJElNk0OSJlfL5JC00JggWoCqahVwQOtySJIkSZI0X7XulTBqJogkSZIkSZIG1IR1Mms9TIYkSZIkSZIaswWRJEmSJEnSgEnrYmYLIkmSJEmSpAlngqixJF+aZd92SY6d43W2SfK9JO/q27bO+SbXJ4YkSZIkSZNiihrKMq5MEDVWVY+ZZfd2wFyTN28CLrgXRVifGJIkSZIkTYQa0jKuTBA1tqaVT5Ljk1yS5Iokb+h2vwXYK8nlSd42yzUOBO4HnDvNvrcnuSrJeUl2mub0tWIkWdIde2mSVUme3net1ya5JsmFST6c5LgZynNMkpVJVl6/+rtz/2FIkiRJkqQmTBCNgSRHAA8ClgMHAAcmOQQ4Abiuqg6oquNnOHcRcAowXbJmK2BlVT0U+ALw+mmOGYxxB/B7VfVI4DDglPQ8Cngm8HDgKcCyme6nqk6rqmVVtWzpkt3n8iOQJEmSJGmsTFoXM2cxGw9HdMtl3eMl9BJGc2l+cyzwqar6XpLBfVPAmd36B4F/ncP1AvxVl6CaAnal1zrpscDHquoO4I4kH5/DtSRJkiRJ0jxggmg8BHhzVb1nrY3J0jmcexBwcDfQ9BJg0ySrq+qEaY6tJLsBa5I77wY+PXDM84CdgAOr6pdJrgc2n+uNSJIkSZK0EDjNvVr4DPDiJEsAkuyaZGfgVmDr2U6squdV1e5VtZReN7P39yWHFgFHdutHARdW1Q1dd7IDqurd08TYFripSw4dBuzRbV8B/G6SzbtyPnVDb1qSJEmSJI0HWxC1V1V1bpKHABd13cRWA8+vquuSrEhyJXDOTOMQzeI2YHmSE4GbgOdME/wn/TGAtwIfT7IKWAlc3R13SZKzgSuA/wJWAbfcmxuWJEmSJGnc1RiPFzQMJogaSrIjcDNAVZ0KnDp4TFUdNdfrVdUZwBl9j5fM8bzBGAfNcOjJVXVSki2BC4CvzrVskiRJkiTNJ5PWxcwEUSNJdgHOB05uXJT1cVqSfemNSfS+qrp0XSdsmXZPsV/Ur5rFHgebs7hp/Nsav5weynZN41/Az5rGb2nvbXdpGv+I7Ng0/iTXPcATd96vafzHLNqhafyVNbmNa//H/R/BTovaDVv4HRq/70/ap4gBJy57TdP4f7ny/zSN/6sL/rlp/D/4s4ubxj9o0/s3i/3AHbZpFhvgb3a6rWl8uL1xfC0kJogaqaobgQfP9fgk+wEfGNh8Z1U9eqMWbBbr05pJkiRNlpbJIUmShsEuZhpLVbUKOKB1OSRJkiRJ0sJjgkiSJEmSJGnApPUeNkEkSZIkSZI0YKomq4vZotYFkCRJkiRJUlsmiDRnSZ6W5IRu/aVJXtC6TJIkSZIkDUMNaRlXdjHTnFXV2cDZ3fq7GxdHkiRJkiRtJLYgmkBJlia5OskZSa5N8qEkhydZkeQbSZbPcN7RSd7VrZ+U5LgZjjsmycokK7+5+voh3okkSZIkScMxRQ1lGVcmiCbX3sApwD7dchTwOOA44NUbcuGqOq2qllXVsr2XLN3QckqSJEmSNHI1pH/jygTR5Pp2Va2qqingKuC8qipgFbC0ackkSZIkSdJIOQbR5Lqzb32q7/EUPi8kSZIkSRNuqnUBRswWRJIkSZIkSRPOliJaXzXDuiRJkiRJC8Y4Dyg9DCaIJlBVXQ88rO/x0TPtG7AjcHPf+neGUkBJkiRJkjRSJog0J0leChwNPCPJm4BHAyet67xfNcy4bprF3FV3N4uvtnb5VeNs/wS/uu612X256e7bmsU/6+7v88qpXZrFP4pt+adNbmkWv7VtFm3WNP4ev0rT+CsXNw3f1I+m7mDnRVs0i38rd/Ogavf8u3+2Y0X9rFn81m7irqbxf3XBPzeNf59Dnts0/hQXN42/Ce1ee38rW7F5w5FT/uHHW3P809q+79ftbX//FrJxnnFsGCb4I4xmkuRFwCsGNq+oqv269dd2y1gzOSS10TI5BDRNDgETnRzSZGuZHAKaJoeAiU4OSS21TA4BJocWuEkbpNoEkX5DVZ0OnN66HJIkSZIkTaIkTwZOBRYD/1BVbxnYvxnwfuBA4CfAc7ohY+41ZzGTJEmSJEkaUFVDWdYlyWLg74CnAPsCv59k34HDXgL8tKr2Bt4OvHVD79cEkSRJkiRJ0vhYDnyzqr5VVXcB/ww8feCYpwPv69bPAp6YZIMGBDNBJEmSJEmSNGCKGsqS5JgkK/uWYwZC7wrc0Pf4e922aY+pql8Bt9CbbfxecwwiSZIkSZKkAcMapLqqTgNOG9Ll7zVbEGlWSZ6W5IRu/aVJXtCtvzHJ4W1LJ0mSJEnSgvN9YLe+xw/stk17TJL7ANvSG6z6XrMFkWZVVWcDZ3fr7+7b/rpmhZIkSZIkaciKdQ8oPSSXAA9Ksie9RNBzgaMGjjkbeCFwEXAk8LmaywjYs7AF0YRIsjTJ1UnOSHJtkg8lOTzJiiTfSLJ8hvOOTvKubv2kJMd162ckOXKGc37dn/Jbq68f2j1JkiRJkrTQdGMK/QnwGeDrwEeq6qquJ8/TusPeC+yY5JvAq4ATNjSuLYgmy97As4AX08tIHgU8Dnga8Grgf26MIP39KZ+1x9ObpVwlSZIkSbq3ptq1IKKqPgV8amDb6/rW76D3+X6jMUE0Wb5dVasAklwFnFdVlWQVsLRpySRJkiRJGiMb2GNr3rGL2WS5s299qu/xFCYLJUmSJEmaWCYFJEmSJEmSBgxrmvtxZQsizUXNYV2SJEmSJM1TtiCaEFV1PfCwvsdHz7RvwI7AzX3r35lmuyRJkiRJC0rDae6byKQNuqS5S/JS4GXAM4AXAP8NeArwNmAP4MlV9cvZrnHWA57X7An2gU1uaRV6LByU7ZrGv6h+1jT+plncNP5ddXfT+JNsEWkav+VsF+PAn79aad0NYNKb5bf++W+WtjXQ+v7P/OrfNo1/4rLXNIt99dStzWIDbJVNmsbfpPFzH+B91/9L2zf/ITpitycP5Q+Lc2/49Fj+zGxBJACSvAh4xcDmFVW1X7f+2m4BePHICiZJkiRJUgOT9sWTCSIBUFWnA6e3LockSZIkSeNg0npctW+PJkmSJEmSpKZsQSRJkiRJkjRg0rqY2YJIkiRJkiRpwpkg0qySHJ3kXa3LIUmSJEnSKNWQ/o0ru5hJkiRJkiQNmHKQai1ESZYmuTrJGUmuTfKhJIcnWZHkG0mWr+P8bZN8J8mi7vFWSW5Issk0xx6TZGWSlZ/9xTeHdUuSJEmSJGkjMUE0WfYGTgH26ZajgMcBxwGvnu3EqroFuBx4fLfpqcBnquqX0xx7WlUtq6plT9py741YfEmSJEmSRqOGtIwrE0ST5dtVtaqqpoCrgPOqqoBVwNI5nH8m8Jxu/bndY0mSJEmSNM85BtFkubNvfarv8RRzey6cDfxVkh2AA4HPbdziSZIkSZI0HiZtmnsTRJqzqlqd5BLgVOATVXV36zJJkiRJkjQMJoik2Z0JfBQ4tHE5JEmSJEnSRmKCaEJU1fXAw/oeHz3TvoHzzgDO6Ht8FpChFFKSJEmSpDFRTnMvSZIkSZKkSWILIgGQ5EXAKwY2r6iql23IdS/brGHGdapd6HHw4Dvb/gAu2rRpeH7/zq2axn/fpj9vGr+lhy3apmn8B9zd9ruPz+ZnTeO3tiSbNI3/wGzeNP7Xpib3dx/gjobDE+62uO3r/o+m7mgav7Uf/Wp10/gHbXr/pvE3adzA/sRlr2ka/y9X/p9msT/1sBObxQZ4/BN/2DR+3THhH3qGzDGINJGq6nTg9NblkCRJ81PL5JAkSdpwJogkSZIkSZIGlC2IJEmSJEmSJpuDVEuSJEmSJGmi2IJIkiRJkiRpwKQNUm0LIv2GJE9LckK3flKS41qXSZIkSZIkDY8tiPQbqups4OzW5ZAkSZIkqRXHINKCkWRpkquTnJHk2iQfSnJ4khVJvpFk+QznHZ3kXQPb9knylYFrr5rh/GOSrEyy8rJbv7lxb0qSJEmSpBGYooayjCsTRAvf3sApwD7dchTwOOA44NVzvUhVXQ1smmTPbtNzgDNnOPa0qlpWVcsesfXeG1J2SZIkSZI0AiaIFr5vV9WqqpoCrgLOq147uVXA0vW81kfoJYZglgSRJEmSJEnzXQ3p37gyQbTw3dm3PtX3eIr1H4PqTODZSR4MVFV9YyOUT5IkSZIkNeYg1Zqzqrouyd3Aa7H1kCRJkiRpAZuasEGqTRBpJjP9JpwJvA3Yc4b9kiRJkiTNe+PcHWwYTBAtYFV1PfCwvsdHz7RvwI7Azd1xJw1c82Tg5I1aUEmSJEmS1JQJIq0lyUuBo4FnbIzrfb1Wb4zL6F44c7NftC1A42T7DvXLtgWYYAfcmabx91zc9nXns21vv7m92KJp/Afd1bYCvjbBf1ltnsXcMnVHs/j3Z9NmsQF+RLt7HwfX3vr9pvEfuMM2TePvm62bxv/PqVuaxv/Uw05sFvu/X/mXzWID3PaylzSN/8MrtmwaH2D71gUYIruYaWIkeRHwioHNK6pqvxblkSRJ81fL5JAkSdpwJogmWFWdDpzeuhySJEmSJI2bSRuDyGnuJUmSJEmSJpwtiCRJkiRJkgY4BpEkSZIkSdKEs4uZJl6Sk5IcN832Q5N8okWZJEmSJEnS8NiCSJIkSZIkacCkdTGzBdEClmRpkquTnJHk2iQfSnJ4khVJvpFk+SynPzzJRd1xf9S3fZskn0xyTZJ3J/mN51CSY5KsTLLy26u/s/FvTJIkSZIkbVQmiBa+vYFTgH265SjgccBxwKtnOW9/4AnAQcDrkuzSbV8O/CmwL7AX8IzBE6vqtKpaVlXL9lyyx8a6D0mSJEmSRqaG9G9cmSBa+L5dVauqagq4CjivqgpYBSyd5byPVdXtVfVj4PP0EkMAX6mqb1XV3cCH6SWbJEmSJElaUKqmhrKMKxNEC9+dfetTfY+nmH0MqsG0Zq1juyRJkiRJmqdMEGkmT0+yeZIdgUOBS7rty5Ps2Y099BzgwlYFlCRJkiRpWKaooSzjygSRZnIFva5lFwNvqqobu+2XAO8Cvg58G/i3NsWTJEmSJEkbi9PcL2BVdT3wsL7HR8+0b+C8k2bYfj5wyMYroSRJkiRJ46kmbJp7E0SSJEmSJEkDxrk72DCYIJpgSV4EvGJg84qqetnGirFbttxYl1pv19fqZrHHwWFTS5rGPyc/axr/wXv9uGl8vrdV2/gNfXmztjMzPGLL25vGZ/UmbeM39r3cue6DhugRU5s2jT/Jtl20OS1/+7eoNIyuh26ze9P4f7PTbU3jb/+Ytu99f/yxtu89j3/iD5vFvu1lL2kWG2Crv3tv0/h7fueKpvG1sJggmmBVdTpweutySJKk+W98J+2VJOnembQuZg5SLUmSJEmSNOFsQSRJkiRJkjRgasJaEJkgkiRJkiRJGlATNki1XcwkSZIkSZImnAkirSXJ0UneNc32pUmubFEmSZIkSZJGraqGsowrE0SSJEmSJEkTzgTRPNW16Lk6yRlJrk3yoSSHJ1mR5BtJls9w3qok26XnJ0le0G1/f5IndYftluT87jqv7zv9Pl2cryc5K8mWM8Q4JsnKJCuvvPW6jXvjkiRJkiSNwBQ1lGVDJNkhyWe7z+ufTbL9NMcckOSiJFcluSLJc+ZybRNE89vewCnAPt1yFPA44Djg1TOcswJ4LPBQ4FvAwd32g4AvdevLgWcC+wPPSrKs2/7bwP+tqocAPweOnS5AVZ1WVcuqatnDtt7r3t+dJEmSJEnqdwJwXlU9CDivezzoF8ALquqhwJOBv02y3boubIJofvt2Va2qqingKnpPkgJWAUtnOOeLwCHd8vfAfkl2BX5aVbd1x3y2qn5SVbcD/0ov6QRwQ1Wt6NY/2LddkiRJkqQFZUzHIHo68L5u/X3A/5ym3NdW1Te69RuBm4Cd1nVhE0Tz251961N9j6eA+8xwzgX0Wg0dDJwP/Ag4kl7iaI3BZ2ytY7skSZIkSQvKVNVQlv5hWbrlmPUo1v2q6gfd+g+B+812cDf8zKbAOsd/mSmJoAWqqm5Icl9g06r6VpIL6XVJ+5O+w56UZAfgdnrZyBd323dPclBVXUSvO9uFoyy7JEmSJEnzXVWdBpw20/4k/wHcf5pdrxm4TiWZseFGkgcAHwBe2PU8mpUJosn0ZWBxt/5F4M2snez5CvAvwAOBD1bVyiRLgWuAlyX5R+Br9LqoSZIkSZK04LSakr6qDp9pX5L/SvKAqvpBlwC6aYbjtgE+Cbymqi6eS1wTRPNUVV0PPKzv8dEz7Zvm3D/oW/8SfV0Nq+oM4IwZ4u2zAUWWJEmSJEkb5mzghcBbuv8/NnhAkk2BfwPeX1VnzfXCJog0VNv+uqGSRm23u+5uW4DN2oa/6xe+vLVy3dTqpvFvXb150/jQ+HevsTvW3Xp5qCb7p9/WImDztHvtXUyaxRbssHiLxiW4vWn0uv2upvE3Sds/vOqOdq/9P7xiy2axAfb8zhVN4y/eY/+m8Re6DZ2SfkjeAnwkyUuA7wDPBuhmH39pVf1ht+0QYMckR3fnHV1Vl892YT9BLVBJXgS8YmDziqp6WYvySJKkha1lckiSpGFo1cVsNlX1E+CJ02xfCfxht/5BejOPrxffyReoqjodOL11OSRJkiRJ0vgzQSRJkiRJkjRgagxbEA3TonUfIkmSJEmSpIXMFkSSJEmSJEkDajwHqR4aWxBpLUkOTfKJGfa1nZpIkiRJkqQRmaoayjKuTBBJkiRJkiRNOBNEYyrJ0iRXJzkjybVJPpTk8CQrknwjyfIZzluVZLv0/CTJC7rt70/ypCSfTLJ/t+2yJK/r1t+Y5I+6y2zTHXdNkncnWdR3/bcnuSrJeUl2mqEMxyRZmWTlpbd+c6P+XCRJkiRJGoWqGsoyrkwQjbe9gVOAfbrlKOBxwHHAq2c4ZwXwWOChwLeAg7vtBwFfAr4IHJxkW+BX3bF0x13QrS8H/hTYF9gLeEa3fStgZVU9FPgC8PrpClBVp1XVsqreHOc9AAAgAElEQVRa9sit917PW5YkSZIkSaNmgmi8fbuqVlXVFHAVcF710o2rgKUznPNF4JBu+XtgvyS7Aj+tqtv69j8W+CSwJMmWwJ5VdU13ja9U1beq6m7gw/SSUgBTwJnd+gf7tkuSJEmStKDUkP6NKxNE4+3OvvWpvsdTzDwD3QX0WgMdDJwP/Ag4kl5iCOASYBn3tBi6DPgj4Kt91xh8xs70DB7fZ7YkSZIkSZozE0QLTFXdANwXeFBVfQu4kF6XtAu6/XcBNwDPAi6ilzj69f7O8iR7dmMPPae7BvSeL0d260f1bZckSZIkaUFxDCItBF8Gru3WvwjsytrJnC8CN1XV7d36A7mnhRH0Whm9C/g68G3g37rtt9FLHl0JPAF447BuQJIkSZKkliYtQTRTNyU1VlXXAw/re3z0TPumOfcP+ta/xEAisKpeC7y2W78RSN++8+mNUTTddZeszz1IkiRJkqT5wQSRJEmSJEnSgPFt6zMcGefmTZpZkhcBrxjYvKKqXtaiPMOS5JiqOs34kxXb+MY3/uTGn+R7N77xJzn+JN+78Y0/6fE1PkwQaawlWVlVy4w/WbGNb3zjT278Sb534xt/kuNP8r0b3/iTHl/jw0GqJUmSJEmSJpwJIkmSJEmSpAlngkjjrnVf2EmOP8n3bnzjG38yYxvf+MafzNjGN77xJRyDSJIkSZIkaeLZgkiSJEmSJGnCmSCSJEmSJEmacCaIJKmTZM+5bNPCY91PtiSbzWWbFh7rXpKkezgGkSR1klxaVY8c2PbVqjpwRPH/B/BQYPM126rqjaOIPela130Xz/pvZIb6/41tQ4z/MGBf1q77948idmtJXjXN5luAr1bV5SOI37Tuu3jW/9pGVv+TLsniqrq7dTkkjY/7tC6AtEaSM6rq6NblaCXJNlX18yQ7TLe/qm4ecXm2rKpfjDBes/tPsg+9D+bbJnlG365t6PuDfZiSvBvYEjgM+AfgSOArI4j7kap6dpJVQP83BgGqqvYfdhm6crxjms23ACur6mNDjNu87rtyWP+/aRT1f39gV2CLJI+gd9/Qq/8thxV3oAyvBw6llyD4FPAU4EJgqAmCJH9bVa9M8nHWrnsAquppw4zfZ1m3fLx7/FTgCuClST5aVX89jKDjUPddOaz/BvUPkOT5VfXBGZJUBdwMnF1VPx1S/CdU1ecG3nsG41845ATOt5N8GjgT+FyNuOVAkiuAfwbOrKrrRhm7rwzPAB5H72d+YVX92whjbw4c2x8f+PuqumNE8XcETgIe2xf/jVX1k1HE13iyBZHGxqi/sZulHDsBf85vfpv3hCHH/URVPTXJt+m9SKdvd1XVbw0zfl85HkPvA+qSqto9ycOBP66qY4cct9n9J3k68D+BpwFn9+26FfjnqvrSsGL3leGKqtq/7/8lwDlVdfCQ4z6gqn6QZI/p9lfVd4YZv68cpwH7AB/tNj0T+DawI/CtqnrlkOI2r/uuHNZ/m/p/IXA0vQ+oK/t23QqcUVX/Ooy4A2VYBTwcuKyqHp7kfsAHq+pJQ457YFV9Ncnjp9tfVV8YZvy+clwA/PeqWt09XgJ8EngyvVYk+w4pbvO678ph/Teo/y7WH1fVe7ok3XR2BJZX1e8MKf4bqur1SU6fJf4Ww3wuJNmSXlLuucAjgU/Qe++7cFgxB+LvATynW6boJao+UlXfHVH8/wvsDXy42/Qc4LqqetmI4n+E3mvOB7tNRwHbVdWzRhT/s8AFffGfBxxaVYePIr7GkwkijY0kVwO/z9qJgV+rqktHVI5z6b1BHQe8FHgh8KOq+vNRxG8tyZfptV44u6oe0W27sqoe1rZkw5fkoKq6qFHsL1fVo5NcDDwD+AlwVVXt3aI8o9bd92PXfFOa5D7AF+l9q7ZqmB8SunjN6r6Lb/23rf9nVtW/DDPGLLG/UlXLk3yVXguyW4GvV9U+Lcozat17/35V9cvu8WbAf1bVPkkuW/M+NMT4zeq+i2/9N6z/OZTvjVX1uobx31tVLxlRrO2BU4HnVdXiUcQciP8g4LWjjN89/x6ypuVUkkX03nsfMqL4Xxt8f5tu2xDj/8bf90lWVdV+o4iv8WQXM42TXYFTmD5BVMBQW/D02bGq3pvkFd03aF9IcsmIYgOQZFdgD/p+R6vqglHFr6obkrWqYaT90xve/391ze1/h95z7iLgz6rqWyOI/Ykk2wFvAy7t4v/DCOICv25i/VZgZ3q/g2u6GG0zoiJsDyyh160IYCtgh6q6O8mdI4jfsu7B+m9d/+d33dz6m/mPqpn9yq7u/x/wVWA1veffSCR5LL0uBmtec9fU/UharQIfAr6cZE1Xwt8F/inJVsDXRhC/Zd2D9d+s/pP876r66yTv5De72a3p4vW+IcafSxe344YVv68cj6fXcubJ9FrTPXvYMQfi97ciuhv43yMM/01gd2BNa9ndum2jcmmS36mqiwGSPJq1WzQO27lJngt8pHt8JPCZEcbXGLIFkcbGOHxT1JXj4qr6nSSfAd4B3AicVVV7jSj+W+m9SX6NexIzNarxAJKcBfwN8C7g0cArgGVV9dwRxW92/10rhr/jnqbGzwX+tKoePYLYm1XVnWvW6XVvvGPNthHE/ybwu1X19VHEmyb+S4ATgfPpfUA5BPgrenVxUlUdP+T4zeq+i2/9t63/sWhmn2QpsE1VXTHCmFcDf0YvOfHrLwNGmCAhyaOAx3QPV1TVyD4gjUvdd2VZivU/svpP8rtV9fGuu+F0dgReWFUPH1L8pl3cujJcD1xGL0FwdlXdNqxYM8T/MrAJve7FZ47qS5ncM/bWtsCjuGfMv+XAV6rq0CHHXzPu3ybAbwNrutTtDlw9glazt3LPcA5b0eveB70ZzleP8MshjSETRBobY5Qgeiq9rg27Ae+kN2DlSVX18VlP3HjxrwH2H9UHw2ni35deE+PD6b1xnAu8YlR/LLa8/3Tjvwxs+89h/XE4EKf1LEorquqxo4g1SxkeQO+PM4BLqurGEcZuVvddLOu/bf03a2af5LyqeuK6tg0x/pdHlQhdRzl2Zu1x/0Y1BknTLhbW/6/L0aT+1yXJS4GHVtWfNoo/1C5u6SYIGdb15xD/t6vqmgZxpx17a40a8hhcmWHcv774Ixn/T5qOXcw0Tn49xk+STekNWFrANVV11wjL8dOquoVeV4fDuvKM8oPTt+h9o9AkQVRVP6b3DWorLe//nCQn0JtRo+i1ZPpUupnVaggzqaXxTDq5Z/aUlUnOBP6dvp99jWig1s4dwA/ofUjYO8neI+xaOfK6B+t/QMv6H3kz+/Rmr9kSuG839kd/3e86zNhd/DXJx88neRvwr6xd96Ma9+9p9LqX7wLcRPcNOr3ZBUehSRcL6//X5Whd/7OqqncnGcrPomUXt/6YyW+O7FBVLx9G3L74r+pb/x/TxP+bYcbvTwB178PL6f08LqmqHw4zdhf/1wmg7ndxTRfXFaP63euL3z+L2xer6t9HGV/jxxZEGjvdG8W7gevo/cG0J71ZtM4ZUfwm3+T3vVnvSm9Gk/NY+4+1Yb9ZT/cHyq+NMH6T++/K8O1Zdg9lTIbMPJPOz4H3DfsDemaePQV69/ziYcbvK8cf0uvO+EDgcnpjAV1UQ549sC/+yOu+i2v9Mxb1fyu9ZvZ303vfWQSs6WoxlLGYkrwCeCW9D8b9raV+Dvy/qnrXxo45EP/zs+yuEf7s/5PeGIP/UVWPSHIY8Pwa3cC8I6/7Lq71T/v6n4th/Q3YsovbLDEBqKqhjb3UxZ+pW92a+G8YZvy+cvwh8Drgc/R+/x9PbwyyfxxR/NcBz6KXoIXerKofraq/HFH8prO4aTyZINLY6frDP7Wqvtk93gv4ZA15Ro8kB9HrA/9K4O19u7YBfm/YXU3G4M16TfzHAvvSm8kNem9cX6uql44o/rSGff+tpfFMOq11/fEfBVxcVQck2Qf4q6p6xjpOXRCs/8mt/yR/WlXvbF2OVpKsrKplXaLgEVU1Ncruna1Z/+Nf/6Ps7jtN7NZd3N7ZKvYodMMaPGbNMApJdgS+VFW/PcL4D6+qO7rHWwCXjzB+01ncNJ7sYqZxdOua5FDnW/SmfR22TenNonMfYOu+7T+n1+R8qPoTIC262K2Jn+R/AY+rql91j99Nb0ymkcTvYrbsYriWJE+qqs+OINSKJO8FdqmqpyTZFzioqt47gtgk+S16Y0/1z+L1yqqarWXNxnRHVd2RhPQGbL46yaj+QNoG2KmqrhvYvn+NbrBY679d/d8foKp+mGQn4GB6g4SOYgYtgH9MciKwe1Udk95Uz79dVZ8YRfDuA9HraTeL18+SLKE3UPSHktzEPS14RirJX1XVq0cc1vofk/qfxXSz647EMLu4zdFQhliYY/e6Dw6+Lw/BT1j7M8at3bZRuZFuUoru8WbA90cYv/UsbhpDJog0jlYm+RS98QCKXguWS9aMlTGsLhd1z5T2Z1TVd5JsWVW/GEas2ST578B76Otil95MFyPpYkdvuult6L05Qy9ptv2IYo/D/Q96L703z2E7vVte0z2+ll4rrpEkCIB/ojeL1+91j59LbzyeUQ1e+r30pnr+d+CzSX7KPX+wDE2SZwN/C9yUZBPg6Kq6pNt9BjCqb42t/zb1/8fACb3VvJVed78rgTcn+esRJej+kd4MUmtmcfo+vRl9RpIgoFfPFwDP7B4/j95zb1SzeD0duJ3eTFrPozer0NC7l6Q3tf1am4A/6JIVI+nW3LH+G9R/vyTL6L327kHvs1HodbNbM3HBqaMsz4RYM2PmTDPW7Uiv29WwZpBbMwbSN4EvJ/kYvc8cTweG/sVQX2LsFuCq9GZTLOBJ3DOj2jDjr5nFbWvg60m+0j1+9Cjia7zZxUxjp/WYGF1Xs/cCS6pq9yQPpzcG0rHDjNsXv0kXu774LwJOAj4Pv55u+qRRdfFqcf9Jzp5pF/CEqtpqWLH7ynBJVT0qfbP5Jbm8qg4YduwuVtNZvAbiPp7eh4RzquqXQ451OfCUqvpBkuXA+4G/qKp/ywhnVrT+14o7yvpfRe8P4i3oJaT27loSbQ98fhQ//74uNv11P8oZ9FrP4vXWqvrzdW0bQtwbgC/Qm6lzTQuRk4HjYHTdmq3/NvU/EO8a4HhgFfdM9z02M0k17uK2ILvXpfEYSGk/rETTWdw03mxBpLFTVS+abX+Sv6iqNw+xCH8L/Dfg7K48/5nkkCHGG9Sqix0AVXV6knO4p+XAn9cIZnTo0+L+DwaeD6we2B7umXZ72G7rmvqv6Qf+O/S+WRqVJrN4rZHkA1X1B12sL6zZBvzBMOMCi6vqB13cr6Q3QOonkuzGLIO2D4H136b+f9m1FP1FkuvWvNZV1U+TjKr+70pv3Ik1db8Xo53FscksXn2eRN8spp2nTLNtY9sXeBPwZOC4qroxyetHlRjqY/23qf9+P6qqmb4oGgfNuri1jD3M7nVzTQBlSGMw9Q3r8ER6Yx7dvrFjrCP+mvfZlwAXVNU3Rhlf480EkeajZwHDTBBRVTdk7Wk/7x5mvAFNutit0ZcM+2n3/4OTPLhGN910i/u/GPjFdN+YdN8sjsKr6CUl90qyAtiJEYx91efZ3f9/PLD9ufTqYSizePVZa0rjJIuBA4ccE+DWJHutGeega0l0KL2uTqOcZtn67zPC+q8km3QtlX491XJ6U5AvGkF86I3/8mlgtyQfojfmx9Ejig3wR/QmZ/gA3DOLV9f9rmp4s3j9L+BY4LeS9Hfp2BpYMYyY/arqVuCVSQ6kN/bNJxldnfez/hvU/4DXJ/kHfnP21KH+vbVGyy5udq9bp6GMwdTnBcDfJ7mZ3nifFwAXVtVPZz9to9kdeE+SpfS6ul5Ab6r7y0cUX2PILmaad4bd7SPJWcDfAO+i14rmFcCyqnrusGIOxG/dxe7jfQ83p9eC5qs1uilvx2La7RaS3Af4bXp/oF0z7O414yDJXwCvptfFZ82YXwHuAk6rqr8YcvyHA7cNtFojvfGInl1VHxpm/IGY1n+3mdHV/+7AjdUNyt+3fVd6M7v8xzDj98Xbkd4A4aE3k9uPRxG3pSTb0hvf7s30xoFa49Zht1ibpiyhl6w4qKqeP8rYXXzr/x4t6v+D9CbGuIp7upiN7O+Nll3c7F43HvGT7ELvS6Hj6E1WMdJGHF0rxj/q4u9aVYtHGV/jxQSR5p1hv1gnuS+9b0wOp/fH2rnAK2p0M3rMagRd7Abj7Qb8bVU9c50Hj8Co738g9kVVddAI441qBrXm8ZO8edjJgA0xzLpP41nUWsfvYk1k/Wf6GdSuqaqrNnas9Yg/yhncBstzTFWd1iL2TEb5up82s6iNU/wm9Z/kmhrRtOIzxL+wqh43abHnYthfCs8h/rA/czyf3uvufsCP6c0i+MWqumhYMQfin0ivldQS4LK++D8YRXyNJxNEmnfG4M2iWYKiiz/Sb1O6b1avqqp9RxVzNi2/TRr1cy/Jd6tqFDOojVX8JCdV1UmjjjubYdV9+mZRA9aaRW0Uz/XW8Wco00TUf/pmUOP/t3fvwZZW5Z3Hvz9EUZAGhFSEjMglCGkQUEFRGGOCOOhERnIRsTQqjpORUZhS8YKpImO8aywRkwJBuaoRSh0Ro0QtGMM0jjSIXCQdLwQn4yUSLUGNAvLMH+8+9D67d9OQ6vddL2d/P1Wn+uz3NOe32Kv3OXs/e631wHQHtcOA3juotc7fyJiarhaYp8fH/mwXNei2m5wH/XdRm5MfujO/BsnfyJha/cw5G3hXw8Lo4cCxNNji1jJ7kn+vW9ySvLiqzhliLBsZX9+7Fm6l69p7Ol1jhH/sK2sj+dcAdwGfoTu0/8qqGvIMNI2QZxDpgeiixvm9n4G0Cb0eGJj1rTehO4vgQKCXQwL/jVoe1rjZK+q59w5qO27uvLHlb8RRdJ30xqSvd1NOBp5Q67uonT8pQn+SYf6tt86fZ1Hm/xV0Zy/N7aBG102zT63z52n5831j+nrsH82GXdSOpTsHZAjz8p83YP48reb/EODaJDfTFUlmz+Hp20votrg9mKktbnRt3ldyNsCHmbPFbUnfxaHWZzBV1U5J9qXrGPyWJHvRrSLtu0HDUv7jJ6uID6U7MP4DSf55zKvK1D8LRBqdyTL3lwG7MfVvdGkveFW9tc3I7tH6CWzfy/7WTn1+F/DRqhr6wMh7s9KWPbbuoNY6f57Wj7Ehte6i1jp/nkWZ/9Yd1Frnz/N7jXJbaN1FrXX+PK3m/8hGuUsObrjFrWU2tO8g17pAtYruoOhH073u2W7eOHrM34/ueeBvAwcB/5fusGwtMAtEGqNP0f1w+gLDdg+7r1oXKPp+8bR9VS17xyTJibPXGlpp7V5bd1BrnT/PqLaYTPT17651F7XW+fMsyvy37qDWOn8pb0e6FWOHTsZ0BfCmsZz7R0+P/WrcRa11/pIxzP8IDmRek2R1oy1uLbOhcQc52heorpj6eH9V/dPA+W+ne831PuCqWoDmGNq0Fu08pU3ZuqpeV1UXVtXHlz5aD2pK63e3+95i96I5117cc+Y9Jk8W701v//9J3rGJa5t9yW9VPbOqLtvI1566ufPGlr8kyR5JPj3Zj/+DJJ9K0ndr9en8wed+4uXM/EyZvHA7Ehiig07rfGBh5/9oJm84zLwo2BF4dQ95Y8tf8td0Z2D9AV0Xnx8CHxsqvOFjH4Cquhr4XeBf6V4kDqp1Po3nfySWtritS3JdkuuTDNIgoHE2dFvcDqT7nfPsyceQK8lOSXJWkmOT/P7Sx1DhVbV/VR1fVR+ZVxyaHPvQp/cC76uqNRaHtMRDqjU6Sd4MrKmqv2k9lnmSnNznNrdNbbHrMfdY4Pl0B5ROLy/dFri7qg7vM39qHN8ArgXOBj5bA/6QmndAZpLrBjyHYKMycAe1ofOTfBn4S+Cjk0vPA15ZVU/qK3Mmf7RzD85/38Y8/wsw9zdU1X4z166vqsf2lTmTNdq5B+d/ESR59LzrQ6xsapk9yW/dQe4CujOYbmTqDKa+n3PfV30f3J7kXODJwI/onvt/Cbiiqn7cV6bGzy1mGqMTgZOT3AEsVbOrqlYNET6CM5BabbFbA3wP2An4i6nrtwNDvpv0GODpdKsX3pfkQuCcqvqHvgKTvBw4Hthj5p2zbYGxnL/00BWev3VVnT91+4IkJ/Wc+UCZe3D+e/EAmf+VPvd/m+R5wIWT238IXNpz5gNl7sH5X/FabnFb8O110P4Mpqaq6kUASXahe+z9JbAL1ggWmiuIpBlJ1tAVaK5mqkAz1Da3JNdW1YFDZI3d5MDcC4BtgK8Br6+qK3vI2Q7Yga473eunvnR7Vf1oc+f9W/T9LlKr/CSPmHz6OuDHdNsNCjgG2KGq3rC5M2fyRz/34Pz35YEw/yt47m+nm+vQ/Yz/1eTzLYCf9v2m0ANh7sH518qW5CZgT6BJB7kkZwPvaligulcDrCB6Ad0h1Y8FbqXbZvp3fTzX1gOHBSKNUpKj6Fo+AlxeVZcMmN20QNNqi12SK6rqsKknbfd8iWFXcO1I11XrhcAP6FotX0y3R/2iqtq95/zDgL2q6uwkOwHbVtXNfWbex3Gt1BcJN7P+RcKsqqohz6EZ5dyD8z+Esc7/Sp37MRnr3EP7+791vla2EWxxa1qg2pQkX62qx/X4/W8FvgWcDlxWVf/YV5YeOFw+ptFJ8nbgYLrWkwAnJjm073eSp1yS5FkNz0BqssWuqg6b/Lltnzn3wZXA+cBzZg7sW5vk9D6Dk5xC1+Zzb7ozkB5Ct4Lp0D5z76PWh6P31cmn14LffTXyuQfnv1cjn/8VOfcASR4JUFXfn2zv/vfA3w/5bv7I5x5W8PxvEJS8tapOHipP7Y1gi9uRLcOTHAS8ka7N/ZZsWKDqtYNwVe2UZF+6N+XfkmQvYF1V9Xo4v8bNLmYao2cBR1TVh6rqQ3Q/vP/jJv6bzelEuiLRL5LcPvm4bajwqtq2qraoqodOPt926KXWSR6UZJckuy59DBi/d1X9ec3p5lBVG3Sb2cyOBo4CfjbJ+y7deRS9S+NOOq3z50lyxIBxzeYe2t//LfOTrEqy55zrQ76D62N/4Pwkf0L3hsCXJ+cBXUL3u/6TSV7aR+ZG+NhvkJ/kfTMfpwHHL93uI1OaVVW3zPsYcAgfpitM/wHrO7g9e2p85/QZnmQVsCtdgWo3YDvWH9atBWWBSGO1/dTn2w0ZPJICzVFJ3j35GLLdJ0leSbe16/PAZyYfg23xAz6V5OKZj/OTnJik78My76hu320BJNmm57xp84ohz1z6pKpuWOH583xwwKyWcw/t7/8m+UmeC/w98PEkNyY5eOrL5/SRuRE+9ofPfwWwL/AE4F3Af6qql9K13X5lT5nz+Nhvk3808AhgLd2Zj2vpVk1fPfmQFsEPq+riqrq5UYHqCrqC1HXAMVW1d00OrtbicouZxuhtwFeTXEa31PKpwFDby4DmZyC13mJ3It0qnn8ZKG/WzcCvsb7d9TF0ndQeA5xJv++mXpjkDGD7JC8DXgqc1WNe8046I8i/eGNfAnbsO3/K4HMPo7j/W3dyOhl4QlV9L8kTgfOTvKGqPsmwW2t87A+cD9xZVT8Hfp7kW1X1fYCq+nGSIQ/I9LHfZv5XA39Ot0r8NVX13SSnVNW5A2RLY3FKkrOAL9KdgQRAVX1iiPBNnbWU5LSqGrJgrxHwkGqNUpKd6YokAF9ZeuI4UPZsgeZYYO1QBZrJE7UDq+ruye0HAV8dsKPDZXRb/O4aIm9O/lVVdfC8a0lurKp9e84/AnjG5OalVfWFnvOadtIZQf6P6Q4l/+nsl4CPVdWv9z2GqbEMOveTzNb3f+v866vqsVO3d6ZbsXgu8OIhD8f1sT94/tXAIVV1Z5J/t7SteLJS9P9U1QF9j2FqLD72B86fGscTgHfTrVZ+RVXtNlS21FqSC4B9gBtZv7Wrquq4dqNaLx5Sv5AsEGl0knyxqg7f1LUe81sXaK4Dnrb0BC1dG+jLB8z/IN1hnZ9h+bsZ7xko/ybgP1TVdya3d6V7wv5b6ambQzbs4Da9cuFu4Ed0bVD/anNnz4yjaSedFvlJPgu8s6oum/O1L1XVU+f8Z5szfxRzPxnLIs7/GuCFVfWtqWvbAv8TOKyqtuo5fxTzv6Bzvyvw3dk3I5L8BvBbAxToRjH3k7Es3PzP5IduNdOTq+oFQ+VKrSVZV1V7tx7HxlggWkwWiDQak3cNtwYuA57G+idrq4DPVdU+A42jdYHmWODtdPfDPVvsquqvB8o/Zd71qvofA+U/EziDru1mgN3pnjheDrysqt47xDhmxrQjsKbPX+KZ6qRTVY9JsgtwUVUN0kmndf5YDTH3k5yFnP8kBwA/q6pvzlx/MPDcqvrw/P9yGD7220tyZVU9uUGuj/0RaDX/0hCSnE1XiB6sc+P9YYFoMXkGkcbkT4D/DuwCXDN1/Tbg/QOOo+kZSFX10SSXs36L3euG3GI3VCFoniRb0J1/sBfdklvo2m3+YvL54MUhgKr6lyRP6znmaOBxTP7tT85jGKyTzgjy71WrFwkDzT20v/+b5FfV1zZy/U7Wb/Nd6fO/kHN/P/TdnGAuH/uj0WT+pYEcAlyb5Ga6Vfuzbe5bG/IsQI2EBSKNRlWdCpya5JVVdVrDcTQt0Extp7t4zrUh8j/NpJvLlJ/QdRg5Y6pYs9lV1d1JXltVFwJzXzi2UlXf6znijqqqTA5nzfCddFrnb0qzFwkDzD20v/9b52/KSp7/1vd96/xNabbU3cf+KLjVQSvZkS3DkxwEvJGuzf2WbFigOrXV2NSOBSKN0VlJXgUcRvfE4O+A0/ssTExrVaCZ2mK3U5IdWL7F7jf6zJ7xbdp1EQP4QpLXAB8DfrZ0sQY8NLORJp10RpS/KSv9RULr+791/qas5Plvfd+3zl90re//1vnSwqphW9rP82HgJOB61h+SfY+qOmfoAdtGiQ8AAA7sSURBVKk9zyDS6CS5kK4gccHk0vOB7avqj3rObXoGUpITWb/F7rtTX7oNOLOqBtlml/ZdxOYdjFlVtUefuWOQBp10xpR/bxZhH3zr+791/r1Z6fPf+r5vnX9v0lNzgjFpff+3zr83izD/UitLh/W3HofGxQKRRifJ16tq9aau9ZA7lgJN0y12adBFbJGlcSed1vn31Ur9t9f6/m+df1+txPlvfd+3zp8axzuq6nUbu5Zkv6q6oc8xtND6/m+dPzWOhZx/aQySHA4cC3yR5Z2LP9FsUGrOApFGJ8kFwPur6suT208C/ltV/fFA+a0LNA8DXk67LXbPAk6nURexJFsDrwJ2rar/kmQvuu4ql/SZO1YZqJNO63xfJMzn/C/u/C/Q3G+wOizJdSM6pLUJ53+x518awuQ11z7AjazfYlZVdVy7Uak1C0QanckKlr2B70wu7QqsA+5igJP9R1CgabLFbmYMWzG/i9gQ2R8Drgb+uKr2mxSM1lTVgUONYWyS7DzQYanN8n2RsHHO/+JayXOf5OV0bz7sQfeGxJJtgf9dVS/oI/eBxPmX1Kck61oVoTVeFog0OkkefW9f7/tAt9YFmlZb7Gby9gNWM9U5qKrOGyh7bVUdNL2lJMnXquqAIfI1LF8kLDbnf3El2Q7YAXgb8PqpL92+AE0JFp7zL7WX5Gy6raRfbz0WjYcFIo1SksOAvarq7CQ7AdtW1bzDi/vIblqgGcEWu1PoDuleDfwN8Ezgiqr6w4Hy1wCH0704fHySPYGPVtUTh8jXsHyRsNicf0Hb3/lqz/mX2pjs2tgTuJnuDKLZNvdaQBaINDqTAsVBdOfOPCbJLsBFVXXoQPmtCzStt9hdDxwAfLWqDkjy68AFVXVEn7lT+UcAf0pXoPpb4FDgxVV1+RD5ascXCYvN+V9MrX/nqy3nX2pnY7s2+t6toXHbsvUApDmOBh4HXANQVd9Nsu2A+U8A1iRZVqCZFE6GqKof2fP335R/raq7k9yVZBXwz8Cjhgqvqs8nuQY4hO6djBOr6tah8tXG9IsE4GzgIXTbPH2RsACc/4XW+ne+2nL+pUYsBGkeC0QaozuqqpIUQJJtBs5vWqCpqlsav5O+Nsn2wJl0h0X/FLhyoOwlDwV+TPczanUSqupLA49Bw/JFwmJz/hdX69/5asv5l6QRsUCkMbowyRnA9kleBhxHV6wYROsCTet30qvq+Mmnpyf5HLCqqq4bIhu61tbAMcy03AQsEK1svkhYbM7/4pr9nf9S4KzGY9JwnH9JGhHPINIoTc6heQbdFqNLq+rzA2a3PgPpWibvpE918Rq03XOS/YHdmCoiV9UnBspeB+xfVb8cIk/jkOQ1wF7AEXQHFr8U+EhVva/pwDQI53+xTf3Oh+53/hdajkfDcv4laTwsEEkzWhdoknylqp6Y5JpJF69tgCsHzP8QsD8zK3iq6riB8j8L/FFV/XSIPI2HLxIWm/O/WJJcUVWHJbmdbpVopr58N/AjuvbLf9VkgOqV8y9J4+QWM43G1JOEDb5EV6BYNdBQWm91aLrFDjikqlYPmDfr58C1Sb5I13ITgKo6od2Q1Jd7eZHwX5P4ImGFc/4XV1UdNvlz7llTSXYE1gDO/Qrk/EvSOLmCSJoxZ6vDcXRbHU4bcAwtt9h9EPiLqvr6UJkz+S+ad72qzh16LGpv6UVCVe3deiwanvO/2JLsXFXfaz0OteH8S9LwLBBJc7Qs0LSW5LeBi4Hv063gWVrBNeQZSA8Ddq2qdUNlarx8kbDYnH9JkqRhWCCSRmIsW+ySfBN4FXA9688goqpuGSj/2cC7gYdU1e5JDgTeVFVHDZEvSZIkSYvIM4ikidYFmo3tw2/gh1V1ccP8PwOeCFwOUFXXJtmj4XgkSZIkacWzQCRNjKhA09pXk3wE+DTLD4kepM09cGdV/SSZbmiyfiWTJEmSJGnzs0AkadbD6ApDz5i6VsBQBaIbkzwfeFCSvYAT6DqZSJIkSZJ64hlEku6XJG+oqrf1+P23Bt7I+gLVpcCbq+oXfWVKkiRJ0qKzQCTpfklyTVU9vmH+aVX1ylb5kiRJkrQSbdF6AJIecLLpv9KrQxvnS5IkSdKKY4FI0v3lskNJkiRJWmEsEEm6v1qvIJIkSZIkbWYWiCQtk2THTfyViwYZyMZZoJIkSZKkzcwCkaRZX05yUZJnJdmgGFNVb20xqCmnNs6XJEmSpBXHLmaSlpkUhZ4OHAccDFwInFNV/zBQ/qfZ8JyjnwBrgTNsdy9JkiRJm58FIkkbleR3gAuAbYCvAa+vqit7zjwV+DXgo5NLxwC30RWNVlXVC/vMlyRJkqRFZIFI0jKTM4heALwQ+AHwQeBi4EDgoqravef8q6rq4HnXktxYVfv2mS9JkiRJi2jL1gOQNDpXAucDz6mqf5q6vjbJ6QPkPzzJrlX1HYAkuwIPn3ztjgHyJUmSJGnhWCCSNGvv2sjSwqp6xwD5rwauSPItuo5luwPHJ9kGOHeAfEmSJElaOG4xk7RMkovnXB70kOgkWwH7TG6u82BqSZIkSeqXBSJJy4zhkOgkTwF2Y2qVY1Wd13euJEmSJC0qC0SSlml9SHSS84E9gWuBX00uV1Wd0GeuJEmSJC0yzyCSNKv1IdEHAas3dg6SJEmSJGnzs0AkadaraHtI9A3AI4HvDZAlSZIkScICkaQpSbYAtgX2Yv4h0e8dYBg7AV9P8hXgl0sXq+qoAbIlSZIkaSF5BpGkZZKsraqDGub/9rzrVfW/hh6LJEmSJC0KC0SSlknyduBW4GPAz5auV9WPmg1KkiRJktQrC0SSlkly85zLVVV79Jx7RVUdluR2YPoHUyb5q/rMlyRJkqRFZoFIkiRJkiRpwW3RegCSxiXJ1kn+NMkHJrf3SvJ7A+bvmWSryedPS3JCku2HypckSZKkRWSBSNKss4E7gKdMbv8/4M0D5n8c+FWS3wQ+ADwK+MiA+ZIkSZK0cCwQSZq1Z1W9E7gToKp+TncO0FDurqq7gKOB06rqJGDnAfMlSZIkaeFYIJI0644kD2NyUHSSPYFfDph/Z5JjgRcBl0yuPXjAfEmSJElaOBaIJM06Bfgc8KgkHwa+CLx2wPyXAE8G3lJVNyfZHTh/wHxJkiRJWjh2MZO0gSQ7AofQbS37clXd2mgcOwCPqqrrWuRLkiRJ0qJwBZGkeR4K/Bi4DVid5KlDBSe5PMmqJI8ArgHOTPKeofIlSZIkaRFt2XoAksYlyTuAY4Abgbsnlwv40kBD2K6qbkvyn4HzquqUJK4gkiRJkqQeWSCSNOs5wN5VNeTB1NO2TLIz8FzgjY3GIEmSJEkLxS1mkmZ9m7Zdw94EXAp8s6quSrIH8I2G45EkSZKkFc9DqiUtk+TjwAF03cvuWUVUVSc0G5QkSZIkqVduMZM06+LJx6CSvLaq3pnkNLozj5axQCVJkiRJ/bFAJGmZqjo3ycOAXatq3YDRN03+XMucApEkSZIkqT9uMZO0TJJnA+8GHlJVuyc5EHhTVR01UP7BwMnAbqwvYldV7T9EviRJkiQtIgtEkpZJcjXwu8DlVfW4ybUbqmq/gfLXAScB1wN3L12vqluGyJckSZKkReQWM0mz7qyqnySZvnb3xv5yD35YVYOfgSRJkiRJi8wCkaRZNyZ5PvCgJHsBJwBrBsw/JclZbNhF7RMDjkGSJEmSFopbzCQtk2Rr4I3AMyaXLgXeXFW/GCj/AmAf4EbWr1yqqjpuiHxJkiRJWkQWiCTdL0lOq6pX9vj911XV3n19f0mSJEnShrZoPQBJDziH9vz91yRZ3XOGJEmSJGmKZxBJGptDgGuT3Ex3BlGwzb0kSZIk9coCkaSxObL1ACRJkiRp0VggknR/pc9vXlW39Pn9JUmSJEkb8gwiSffXqa0HIEmSJEnavOxiJmmZJJ8GZn8w/ARYC5wxVLt7SZIkSdJwXEEkada3gZ8CZ04+bgNuBx4zuS1JkiRJWmFcQSRpmSRXVdXB864lubGq9m01NkmSJElSP1xBJGnWw5PsunRj8vnDJzfvaDMkSZIkSVKf7GImadargSuSfIuuY9nuwPFJtgHObToySZIkSVIv3GImaQNJtgL2mdxc58HUkiRJkrSyWSCStIEkTwF2Y2qVYVWd12xAkiRJkqReucVM0jJJzgf2BK4FfjW5XIAFIkmSJElaoVxBJGmZJDcBq8sfDpIkSZK0MOxiJmnWDcAjWw9CkiRJkjQct5hJmrUT8PUkXwF+uXSxqo5qNyRJkiRJUp8sEEma9WetByBJkiRJGpZnEEmSJEmSJC04VxBJAiDJFVV1WJLb6bqW3fMloKpqVaOhSZIkSZJ65goiSZIkSZKkBWcXM0nLJNkzyVaTz5+W5IQk27celyRJkiSpPxaIJM36OPCrJL8JfAB4FPCRtkOSJEmSJPXJApGkWXdX1V3A0cBpVXUSsHPjMUmSJEmSemSBSNKsO5McC7wIuGRy7cENxyNJkiRJ6pkFIkmzXgI8GXhLVd2cZHfg/MZjkiRJkiT1yC5mkjYqyQ7Ao6rqutZjkSRJkiT1xxVEkpZJcnmSVUkeAVwDnJnkPa3HJUmSJEnqjwUiSbO2q6rbgN8HzquqJwFPbzwmSZIkSVKPLBBJmrVlkp2B57L+kGpJkiRJ0gpmgUjSrDcBlwLfrKqrkuwBfKPxmCRJkiRJPfKQakmSJEmSpAW3ZesBSBqHJK+tqncmOQ3YoHJcVSc0GJYkSZIkaQAWiCQtuWny51rmFIgkSZIkSSuXW8wkLZPkYOBkYDfWF5GrqvZvNihJkiRJUq8sEElaJsk64CTgeuDupetVdUuzQUmSJEmSeuUWM0mzflhVF7cehCRJkiRpOK4gkrRMksOBY4EvAr9cul5Vn2g2KEmSJElSr1xBJGnWS4B9gAezfotZARaIJEmSJGmFcgWRpGWSrKuqvVuPQ5IkSZI0nC1aD0DS6KxJsrr1ICRJkiRJw3EFkaRlktwE7AncTHcGUbDNvSRJkiStaBaIJC2T5NHzrtvmXpIkSZJWLgtEkiRJkiRJC84ziCRJkiRJkhacBSJJkiRJkqQFZ4FIkiRJkiRpwVkgkiRJkiRJWnD/H2j6rQGcrE5zAAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.figure(figsize=(20,8))\n", "sns.heatmap(higgs_ds.iloc[:,1:].corr())" ] }, { "cell_type": "markdown", "id": "significant-softball", "metadata": {}, "source": [ "## More on Data Quality\n", "\n", "The HIGGS data set is nearly balanced, with 52.99% positive examples, that’s why we did not perform subsampling or oversampling on the data.\n", "\n", "|| label |count|%|\n", "| --- | --- |--- | --- |\n", "|signal| 1 |5829123| 52.99%|\n", "|background| 0 | 5170877 | 47.01%|\n", "\n", "The paper mentioned that various numbers of examples were used for different stages of their study.\n", " * Hyper-parameters selection: Using a subset of the HIGGS data consisting of 2.6 million training examples and 100,000 validation examples.\n", " * Hyper-parameters optimization: Using complete 11 million examples. \n", " * Performance testing: Classifiers were tested on 500,000 simulated examples generated from the same Monte Carlo procedures as the training sets.\n", " \n", "As the paper was published in 2014, the original study might be not thorough due to expensive computational cost. In this case study, the full dataset (11 million data) is used to build and validate models.\n" ] }, { "cell_type": "markdown", "id": "posted-channels", "metadata": {}, "source": [ "## Sampled Data \n", "\n", "Randomly sampled data too has sample proportion of singal (52.96%) and background (47.04%) observations which is nearly balanced." ] }, { "cell_type": "code", "execution_count": 9, "id": "outstanding-leisure", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
targetcounts
00.01269715
11.01430286
\n", "
" ], "text/plain": [ " target counts\n", "0 0.0 1269715\n", "1 1.0 1430286" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "higgs_ds.groupby(['target']).size().reset_index(name='counts')" ] }, { "cell_type": "markdown", "id": "still-damages", "metadata": {}, "source": [ "# Architecture\n", "\n", "The paper released by Baldi et.al (2014) has used pylearn to build neural network model. The Pylearn was supported with python 2.7 and is no longer available. This case study attempts to build similar model to evaluate and compare performance by using Tensorflow. Following are steps we have followed to build NN sequential model using tensorFlow with different hyperparameters.\n", "\n", "1. Randomly Sample 2.7 million records from the HIGGS.csv file\n", "2. Split data into train/test (80:20) for model building\n", "3. Normalize using MinMaxScaler Train and Test data separately to avoid data leakage.\n", "4. Setup hyperparameter and run the model.\n", "5. All models were built with separate python script (code in Appendix section with different hyperparameter) and models stored. \n", "6. This section shows summaries (viz Architecture of the model and learning curve) from stored model.\n", "7. All models ran with 1000 batch size and with 200 epochs.\n", "\n", "## NN Architecture used in Paper\n", "\n", "Author of paper built neural network using pylearn with following configuration\n", "\n", "* Number of layers= 5 (4 Dense layers + 1 output layer)\n", "* Number of Neurons in 4 dense hidden layers = 300 \n", "* tanh activation function for the dense layers\n", "* sigmoid function for output layer\n", "* initial learning rate - 0.05\n", "* Momemtum = 0.9\n", "* Learning rate Decay = Expoential Decay\n", "* Metric = AUC (result - 0.88 as per paper) \n", "* Total Epochs = 200\n", "* Batch Size = 100 \n", "* Dropout rate 0.5 on top hidden layer\n", "* Weights initialized \n", " * First layer with Mean 0 and standard deviation 0.1\n", " * Hidden layers with Mean 0 and standard deviation 0.05\n", " * Output layers with Mean 0 and standard deviation 0.001\n", " \n", "\n", "## Build Deep Neural Network\n", "\n", "First we attempted to built exact replica of the model with same hyperparameters and activation functions and then we tried different activation function (ReLU and ELU) by different dropouts and each model was trained for 200 epochs with batch size of 1000. We chose 1000 batch size because it helped us increase speed of the training without affecting accuracy. We used AUC as a metric to measure the goodness of the NN models to perform an apple to apple comparison to the model found in[2]. Finally, we visualized AUC trends for both train and test data\n", "and the learning rate decay curve through the model training process.\n", "\n", "We used TensorFlow with Keras package to build our model. To replicate the original\n", "model in the paper, we used the same hyperparameters from the paper as listed below.\n", "\n", "* Neurons = 300 units per layer\n", "* Number of Layers = 5 layers (4 Dense layers + 1 output layer)\n", "* Activation Function = tanh for the Dense layers, sigmoid for output layer\n", "* Initial Learning Rate = 0.05\n", "* Learning Rate Decay = Exponential Decay\n", "* Momentum = 0.9\n", "* Metrics = AUC\n", "* Epoch's = 20 (for all models) and 100 (for two first models)\n", "* Batch Size = 1000 (after trying both 100 and 1000 we finalized on 1000. We found 1000 speeds up the training without affecting AUC/Accuracy)\n" ] }, { "cell_type": "markdown", "id": "steady-amazon", "metadata": {}, "source": [ "## Split Train/Test (80/20)" ] }, { "cell_type": "code", "execution_count": 10, "id": "prepared-edition", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " \n", "Shape of the dataframe\n", "Train set (2160000, 28)\n", "Test set (540001, 28)\n" ] } ], "source": [ "X_train, X_test, y_train, y_test = train_test_split(\n", " np.array(higgs_ds.iloc[:,1:]), np.array(higgs_ds.iloc[:,0]), test_size=0.2, random_state=42)\n", "print(' ')\n", "print('Shape of the dataframe')\n", "print('Train set',X_train.shape)\n", "print('Test set',X_test.shape)" ] }, { "cell_type": "markdown", "id": "individual-uganda", "metadata": {}, "source": [ "## Feature Normalization \n", "\n", "Normalize features using MinMaxScaler to rescale all features that shall bring values of all features between 0 and 1. It shall bring all features on similar scale that is required for ML algorithm." ] }, { "cell_type": "code", "execution_count": 11, "id": "considerable-approach", "metadata": {}, "outputs": [], "source": [ "scaler = MinMaxScaler(feature_range=(0, 1))\n", "X_train = scaler.fit_transform(X_train)\n", "X_test = scaler.transform(X_test)" ] }, { "cell_type": "markdown", "id": "vocal-mason", "metadata": {}, "source": [ "## Replica Model - Replicated from Paper\n", "\n", "\n", "* Number of layers= 5 (4 Dense layers + 1 output layer)\n", "* Number of Neurons in 4 dense hidden layers = 300 \n", "* tanh activation function for the dense layers\n", "* sigmoid function for output layer\n", "* initial learning rate - 0.05\n", "* Momemtum = 0.9\n", "* Learning rate Decay = Expoential Decay\n", "* Metric = AUC (our result - 0.85 as per paper) \n", "* Total Epochs = 200\n", "* Batch Size = 1000 \n", "* Dropout rate 0.5 on top hidden layer\n", "* Weights initialized \n", " * First layer with Mean 0 and standard deviation 0.1\n", " * Hidden layers with Mean 0 and standard deviation 0.05\n", " * Output layers with Mean 0 and standard deviation 0.001\n", "\n", "Code that was used to replicate model with above configuration is in Appendix with same heading as this section." ] }, { "cell_type": "markdown", "id": "aggregate-movie", "metadata": {}, "source": [ "### Model summary" ] }, { "cell_type": "code", "execution_count": 52, "id": "closed-dublin", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"sequential\"\n", "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", "h0 (Dense) (None, 300) 8700 \n", "_________________________________________________________________\n", "h1 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "h2 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "h3 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "dropout (Dropout) (None, 300) 0 \n", "_________________________________________________________________\n", "y (Dense) (None, 1) 301 \n", "=================================================================\n", "Total params: 279,901\n", "Trainable params: 279,901\n", "Non-trainable params: 0\n", "_________________________________________________________________\n", "Model Evaluation : \n", "2160000/2160000 [==============================] - 106s 49us/sample - loss: 0.4727 - acc: 0.7691 - auc_16: 0.8536\n", "540001/540001 [==============================] - 27s 51us/sample - loss: 0.4850 - acc: 0.7614 - auc_16: 0.8451\n", " \n", "Train: 0.854, Test: 0.845\n" ] } ], "source": [ "model_summary('data/model.replica')" ] }, { "cell_type": "markdown", "id": "bound-excess", "metadata": {}, "source": [ "### Learning and Loss Curve\n", "\n", "We were able to replicate model for same configuration as in paper and learning curve and loss are plotted as below. Train and test curves are almost same for all 200 epochs and there is no sign or over or underfitting. Which indicates model has learnt well for the given sample of data. AUC is sligtly lower than the paper but it can be improved by increasing training size." ] }, { "cell_type": "code", "execution_count": 34, "id": "optimum-quest", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plot_train_test('data/model.replica_history')" ] }, { "cell_type": "markdown", "id": "secure-developer", "metadata": {}, "source": [ "## RELU with Dropout 0.5 in top hidden layer\n", "\n", "Here we tried same configuration as replica model except activation function. We have used ReLu instead of tanh.\n", "\n", "* Number of layers= 5 (4 Dense layers + 1 output layer)\n", "* Number of Neurons in 4 dense hidden layers = 300 \n", "* **ReLu** activation function for the dense layers\n", "* sigmoid function for output layer\n", "* initial learning rate - 0.05\n", "* Momemtum = 0.9\n", "* Learning rate Decay = Expoential Decay\n", "* Metric = AUC (our result AUC=0.8))\n", "* Total Epochs = 200\n", "* Batch Size = 1000 \n", "* **Dropout rate 0.5 on top hidden layer**\n", "* Weights initialized \n", " * First layer with Mean 0 and standard deviation 0.1\n", " * Hidden layers with Mean 0 and standard deviation 0.05\n", " * Output layers with Mean 0 and standard deviation 0.001\n", "\n", "Code that was used to replicate model with above configuration is in Appendix with same heading as this section." ] }, { "cell_type": "markdown", "id": "voluntary-salem", "metadata": {}, "source": [ "### Model Summary" ] }, { "cell_type": "code", "execution_count": 53, "id": "statistical-symphony", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"sequential\"\n", "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", "h0 (Dense) (None, 300) 8700 \n", "_________________________________________________________________\n", "h1 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "h2 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "h3 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "dropout (Dropout) (None, 300) 0 \n", "_________________________________________________________________\n", "y (Dense) (None, 1) 301 \n", "=================================================================\n", "Total params: 279,901\n", "Trainable params: 279,901\n", "Non-trainable params: 0\n", "_________________________________________________________________\n", "Model Evaluation : \n", "2160000/2160000 [==============================] - 117s 54us/sample - loss: 0.3956 - acc: 0.8114 - auc_18: 0.9000\n", "540001/540001 [==============================] - 27s 49us/sample - loss: 0.5201 - acc: 0.7566 - auc_18: 0.8355\n", " \n", "Train: 0.900, Test: 0.835\n" ] } ], "source": [ "model_summary('data/model.p')" ] }, { "cell_type": "markdown", "id": "federal-monroe", "metadata": {}, "source": [ "### Learning and Loss Curve\n", "\n", "Here we have used same configuration as replica except for activation function. For this one we have used ReLu and plot shows that his model overfits. Loss increases for test set as number of epochs which is not a good sign for the model. thats why we tried two more variation with more dropout rate for every hidden layer for regularization to control overfitting." ] }, { "cell_type": "code", "execution_count": 35, "id": "controversial-devices", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plot_train_test('data/model.p_hist')" ] }, { "cell_type": "markdown", "id": "german-florist", "metadata": {}, "source": [ "## RELU with all hidden layers with Dropout 0.4\n", "\n", "As shown in previous plot model with single dropout rate of 0.5 overfits i.e. regularizing only one hidden layer doesn't help to handle overfitting. So here we tried dropout rate of 0.4 for each hidden layer.\n", "\n", "Below configuration was used to build this model\n", "\n", "* Number of layers= 5 (4 Dense layers + 1 output layer)\n", "* Number of Neurons in 4 dense hidden layers = 300 \n", "* **ReLu** activation function for the dense layers\n", "* sigmoid function for output layer\n", "* initial learning rate - 0.05\n", "* Momemtum = 0.9\n", "* Learning rate Decay = Expoential Decay\n", "* Metric = AUC (result AUC=0.8))\n", "* Total Epochs = 200\n", "* Batch Size = 1000 \n", "* **Dropout rate 0.4 on all 4 hidden layer**\n", "* Weights initialized \n", " * First layer with Mean 0 and standard deviation 0.1\n", " * Hidden layers with Mean 0 and standard deviation 0.05\n", " * Output layers with Mean 0 and standard deviation 0.001\n", "\n", "Code that was used to replicate model with above configuration is in Appendix with same heading as this section." ] }, { "cell_type": "markdown", "id": "technical-hawaii", "metadata": {}, "source": [ "### Model summary" ] }, { "cell_type": "code", "execution_count": 54, "id": "prompt-thursday", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"sequential\"\n", "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", "h0 (Dense) (None, 300) 8700 \n", "_________________________________________________________________\n", "dropout (Dropout) (None, 300) 0 \n", "_________________________________________________________________\n", "h1 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "dropout_1 (Dropout) (None, 300) 0 \n", "_________________________________________________________________\n", "h2 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "dropout_2 (Dropout) (None, 300) 0 \n", "_________________________________________________________________\n", "h3 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "dropout_3 (Dropout) (None, 300) 0 \n", "_________________________________________________________________\n", "y (Dense) (None, 1) 301 \n", "=================================================================\n", "Total params: 279,901\n", "Trainable params: 279,901\n", "Non-trainable params: 0\n", "_________________________________________________________________\n", "Model Evaluation : \n", "2160000/2160000 [==============================] - 122s 56us/sample - loss: 0.5542 - acc: 0.7123 - auc_20: 0.8027\n", "540001/540001 [==============================] - 30s 56us/sample - loss: 0.5561 - acc: 0.7108 - auc_20: 0.8000\n", " \n", "Train: 0.803, Test: 0.800\n" ] } ], "source": [ "model_summary('data/model_keras_lr005.p')" ] }, { "cell_type": "markdown", "id": "material-vintage", "metadata": {}, "source": [ "### Learning and Loss curve\n", "\n", "Learning by this model looks much better than previous model. This appears to be tuned well and addressing overfitting issue. AUC is still lower (0.8) than original model (with tahnh activation function) due to size of training size likely and it needs to be trained with more data. Validation loss on the other hand looks decreasing but is graph indicates validation loss not stable and varies throughout as it gets dropped as number of epochs increases." ] }, { "cell_type": "code", "execution_count": 48, "id": "romance-fault", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plot_train_test('data/model_keras_lr005.p_history')" ] }, { "cell_type": "markdown", "id": "genuine-stevens", "metadata": {}, "source": [ "## ELU with all hidden layers with Dropout 0.4\n", "\n", "Here we tried different activation function (ELU-Exponential Linear Unit) with same configuration as previous\n", "\n", "Below configuration was used to build this model\n", "\n", "* Number of layers= 5 (4 Dense layers + 1 output layer)\n", "* Number of Neurons in 4 dense hidden layers = 300 \n", "* **ELU** activation function for the dense layers\n", "* sigmoid function for output layer\n", "* initial learning rate - 0.05\n", "* Momemtum = 0.9\n", "* Learning rate Decay = Expoential Decay\n", "* Metric = AUC (result AUC=0.8))\n", "* Total Epochs = 200\n", "* Batch Size = 1000 \n", "* **Dropout rate 0.4 on all 4 hidden layer**\n", "* Weights initialized \n", " * First layer with Mean 0 and standard deviation 0.1\n", " * Hidden layers with Mean 0 and standard deviation 0.05\n", " * Output layers with Mean 0 and standard deviation 0.001\n", "\n", "Code that was used to replicate model with above configuration is in Appendix with same heading as this section." ] }, { "cell_type": "markdown", "id": "southeast-compact", "metadata": {}, "source": [ "### Model Summary" ] }, { "cell_type": "code", "execution_count": 55, "id": "every-pavilion", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"sequential\"\n", "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", "h0 (Dense) (None, 300) 8700 \n", "_________________________________________________________________\n", "dropout (Dropout) (None, 300) 0 \n", "_________________________________________________________________\n", "h1 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "dropout_1 (Dropout) (None, 300) 0 \n", "_________________________________________________________________\n", "h2 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "dropout_2 (Dropout) (None, 300) 0 \n", "_________________________________________________________________\n", "h3 (Dense) (None, 300) 90300 \n", "_________________________________________________________________\n", "dropout_3 (Dropout) (None, 300) 0 \n", "_________________________________________________________________\n", "y (Dense) (None, 1) 301 \n", "=================================================================\n", "Total params: 279,901\n", "Trainable params: 279,901\n", "Non-trainable params: 0\n", "_________________________________________________________________\n", "Model Evaluation : \n", "2160000/2160000 [==============================] - 135s 63us/sample - loss: 0.5479 - acc: 0.7173 - auc_22: 0.7926\n", "540001/540001 [==============================] - 33s 61us/sample - loss: 0.5493 - acc: 0.7156 - auc_22: 0.7912\n", " \n", "Train: 0.793, Test: 0.791\n" ] } ], "source": [ "model_summary('data/model_keras_elu.p')" ] }, { "cell_type": "markdown", "id": "cosmetic-dynamics", "metadata": {}, "source": [ "### Learning and Loss curve \n", "\n", "AUC plot is almost similar to previous model and here loss is validation relatively smooth. There is no signs of overffiting as there not much difference in train and test sets. ELU activation function appears to handle overfitting much better and ReLu. Again accuracy is lower (0.79) due to size of the training. So it can be tested with more training data to improve AUC." ] }, { "cell_type": "code", "execution_count": 37, "id": "allied-dayton", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plot_train_test('data/model_keras_elu.p_history')" ] }, { "cell_type": "markdown", "id": "ordinary-capital", "metadata": {}, "source": [ "# Recommendation & Evaluations" ] }, { "cell_type": "markdown", "id": "plastic-updating", "metadata": {}, "source": [ "## Choice of activation functions\n", "\n", "Activation function determines the output of a node, given an input to the node. Mathematically it can be represented as:\n", "\n", " \ty = f(x), where x is input, and y is output\n", "\n", "Here, the input to a deep node is typically a weighted sum outputs from prior layer of nodes. \n", "\n", "For training a neural network, use of gradient descent involves calculation of error gradient that is back propagated from output layer towards input layer to train weights. Hence **properties of differential** of activation functions become critical.\n", "\n", "\n", "Multiple aspects to be considered in choice of activation function are:\n", "* Type of output: influences output of binary or multi-class problems.\n", " * Binary (e.g. binary step) or \n", "\t* Continuous (sigmoid). \n", "* Range of output: influences output of binary or multi-class problems.\n", " * 0 to 1 (e.g. logistic or sigmoid) or \n", " * -1 to 1 (tanh)\n", "* Symmetric about input or not: influences if direction of weights update needs to be changed.\n", " * Tanh (symmetric), or \n", " * **Re**ctified **L**inear **U**nit (one sided or asymmetric)\n", "*\tDerivative of activation function\n", " * Reducing for high input values (sigmoid or tanh)\n", " * Constant (e.g. RelU for positive values of x)\n", "\n", "**The paper** uses **tanh activation** function. The tanh function can lead to a problem of vanishing gradient, where the neural network stops training. Both sigmoid and tanh function are prone to this as the output saturates for large positive or negative values of inputs. In this region, the differential of the activation function can get very small.\n", "\n", "**The proposal is to use following two functions** for better training of the neural network:\n", "* RelU (**R**ectified **L**inear **U**nit)\n", " * Gets rid of vanishing gradient problem.\n", " * This is a more recent function that has been researched and extensively used. It was not available at time paper was published (2014).\n", " * However, it does not activate for negative inputs, and hence no weights would be updated for negative inputs.\n", "* ELU (**E**xponential **L**inear **U**nit)\n", " * Like RelU, it gets rid of vanishing gradient problem.\n", " * However, it has one additional advantage in that it activates for negative inputs also.\n", "\n", "It is recommended to use RelU, and ELU activation functions to build a model with better Accuracy in detecting the Higgs Boson.\n", "\n", "\n", "## Choice of Metric\n", "\n", "For real data where chances of collision producing Higgs Boson is very low. In this case the AUC may not be an ideal metric. \n", "\n", "It is important to consider implications of False Positives (FP) and False Negatives (FN)\n", "\n", "False Positive: \n", "•\tFalse positive is when a Higgins Boson is classified as detected, but actually it is not. \n", "•\tWhile critical, this may still be acceptable with a very low probability, as a positive will get additionally peer reviewed, and verified.\n", "\n", "False Negative: \n", "•\tFalse negative is when a Higgins Boson is classified as absent but actually it should be found.\n", "•\tThis is a very big miss, and is more critical than False Positive.\n", "•\tFN should be ~0.\n", "\n", "Since the cost of FN is much larger than FP, AUC may not be ideal metric. **Minimizing FN directly may be a better metric.** F1 Measure is recommended for highly imbalanced datasets.\n", "\n", "\n", "## Dropouts\n", "\n", "Dropout is a technique to prevent over fitting during training phase. Srivastava, et. al (2014) present the technique. In modern scheme of neural network training, use of dropout is a standard approach to prevent over fitting in deep neural network designs. [[4]](#References)\n", " \n", "In drop out, the nodes in the neural network are removed from network randomly in every weight training iteration. This effectively means that in every iteration a sample of full network (or a thinned network) is used and trained. Hence, a collection of different thinned networks with extensive weight sharing is achieved. Conceptually the dropout breaks-up situations where network layers co-adapt to correct mistakes from prior layers, in turn making the model more robust. \n", " \n", "In the paper, drop out feature during training algorithm is used in the paper for the ‘top hidden layer with 50% probability during training’. \n", " \n", "A priori, it cannot be typically said what dropout rate would be optimal, i.e. give best performance. \n", " \n", "**The proposal** is to **use different dropout rate percentages over different training/validation set size** to determine best model performance.\n", "\n", "\n" ] }, { "cell_type": "markdown", "id": "organic-friend", "metadata": {}, "source": [ "# Conclusion\n", "\n", "In the case study, were successfully able to replicate the neural network design to detect Higgs Boson. The replicated model matched the performance metric (AUC) mentioned in the paper (~0.88), when all the features are included in modeling. \n", " \n", "This was a deep neural network, with 5 layers, and 4 hidden layers of 300 nodes each. The paper uses tanh activation function, and uses subset of the simulation generated data set to train the model. Weights were initialized from a normal distribution with zero mean and standard deviation 0.1 in the first layer, 0.001 in the output layer, and 0.05 all other hidden layers. Gradient computations were made on mini-batches of size 100, and drop out technique was used for top hidden layer at 50% probability rate. \n", " \n", "As part of the case study, we were successfully able to run the model on same data set size, and replicate the results. Adjusting the batch size to 1000 helped running the model faster. This is different from paper, which uses batch size of 100. Additionally, modified models were developed using RelU, and ELU activation functions, and with different dropout schemes and compared to AUC performance metric mentioned in the paper. \n", " \n", "In our observations, we don’t see a marked jump in accuracy or loss function reduction when different techniques are deployed. It is recommended that further tuning of model be considered by choosing different dropout schemes with more training data,different learning rates, momentum,decay rate etc. \n" ] }, { "cell_type": "markdown", "id": "processed-civilian", "metadata": {}, "source": [ "# References\n", "\n", "1. [HIGGS DataSet - UCI- Website](https://archive.ics.uci.edu/ml/datasets/HIGGS)\n", "2. P. Onyisi, Higgs boson FAQ, University of Texas ATLAS group, 2013.\n", "3. Baldi, P., Sadowski, P. & Whiteson, D. Searching for exotic particles in high-energy physics with deep learning. Nat Commun 5, 4308 (2014). https://doi.org/10.1038/ncomms5308\n", "4. Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov; 15(56):1929−1958, 2014.\n", "\n" ] }, { "cell_type": "markdown", "id": "vocal-blair", "metadata": {}, "source": [ "# Appendix-I - Python Code\n", "\n", "This section contains code that was used to build different models. Following models were tried\n", "\n", "1. Replica Model - Replica of model from the paper\n", "2. RELU activation functions with dropout 0.5 in top hidden layer\n", "3. RELU activation functions with dropout 0.4 in all hidden layers\n", "4. ELU activation functions with dropout 0.4 in all hidden layers." ] }, { "cell_type": "markdown", "id": "african-fireplace", "metadata": {}, "source": [ "## Replica Model \n", "\n", "This is code for model replicated from the paper with exact similar configuration.\n" ] }, { "cell_type": "markdown", "id": "fundamental-consensus", "metadata": {}, "source": [ "\n", "warnings.filterwarnings('ignore')\n", "print(' Store Model : ',sys.argv[1])\n", "store_model = sys.argv[1]\n", "\n", "if(path.exists(store_model)):\n", " model = keras.models.load_model(store_model)\n", "else:\n", " model = tf.keras.Sequential()\n", " model.add(tf.keras.Input(shape=(28,)))\n", " model.add(layers.Dense(300, activation='tanh',name=\"h0\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.1)))\n", " model.add(layers.Dense(300, activation='tanh',name=\"h1\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(layers.Dense(300, activation='tanh',name=\"h2\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(layers.Dense(300, activation='tanh',name=\"h3\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(tf.keras.layers.Dropout(0.5))\n", " model.add(layers.Dense(1, activation='sigmoid',name=\"y\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev= 0.001)))\n", "\n", "\n", "warnings.filterwarnings('ignore')\n", "\n", "print(' Store history : ',sys.argv[2])\n", "\n", "model_fit_history = sys.argv[2]\n", "\n", "if (not path.exists(store_model)):\n", "\n", " # Replica model\n", " # initial_learning_rate=.000001,\n", " # decay_steps=10000,\n", " # decay_rate=1.0000002\n", " # momentum=0.9\n", " # batch_size=100\n", "\n", " lr_schedule = keras.optimizers.schedules.ExponentialDecay(\n", " initial_learning_rate=.000001,\n", " decay_steps=10000,\n", " decay_rate=1.0000002)\n", "\n", " #opt = tf.keras.optimizers.Adam(learning_rate=lr_schedule)\n", " opt = tf.keras.optimizers.SGD(learning_rate=0.05, momentum=0.9)\n", " model.compile( optimizer=opt,\n", " loss='binary_crossentropy',\n", " metrics=['accuracy','AUC'])\n", " history= model.fit(X_train, y_train, epochs=200, validation_data=(X_test,y_test), batch_size=1000)\n", " model.save(store_model)\n", " pickle.dump( history.history, open( model_fit_history, \"wb\" ) )\n", "" ] }, { "cell_type": "markdown", "id": "mobile-organization", "metadata": {}, "source": [ "## RELU top hidden layer with Dropout 0.5 " ] }, { "cell_type": "markdown", "id": "general-lithuania", "metadata": {}, "source": [ "\n", "warnings.filterwarnings('ignore')\n", "store_model = \"data/model.p\"\n", "\n", "if(path.exists(store_model)):\n", " model = keras.models.load_model(store_model)\n", "else:\n", " model = tf.keras.Sequential()\n", " model.add(tf.keras.Input(shape=(28,)))\n", " model.add(layers.Dense(300, activation='relu',name=\"h0\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.1)))\n", " model.add(layers.Dense(300, activation='relu',name=\"h1\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(layers.Dense(300, activation='relu',name=\"h2\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(layers.Dense(300, activation='relu',name=\"h3\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(tf.keras.layers.Dropout(0.5))\n", " model.add(layers.Dense(1, activation='sigmoid',name=\"y\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev= 0.001)))\n", " \n", "warnings.filterwarnings('ignore')\n", "\n", "model_fit_history = \"data/model.p_history\"\n", "\n", "if (not path.exists(store_model)):\n", " lr_schedule = keras.optimizers.schedules.ExponentialDecay(\n", " initial_learning_rate=0.05,\n", " decay_steps=10000,\n", " decay_rate=1.0000002)\n", "\n", " #opt = tf.keras.optimizers.Adam(learning_rate=lr_schedule)\n", " opt = tf.keras.optimizers.SGD(learning_rate=0.05, momentum=0.9)\n", " model.compile( optimizer=opt,\n", " loss='binary_crossentropy',\n", " metrics=['accuracy','AUC'])\n", " history= model.fit(X_train, y_train, epochs=200, validation_data=(X_test,y_test), batch_size=1000)\n", " pickle.dump( history.history, open( model_fit_history, \"wb\" ) ) \n", " \n", " " ] }, { "cell_type": "markdown", "id": "starting-version", "metadata": {}, "source": [ "## RELU with all hidden layers with Dropout 0.4" ] }, { "cell_type": "markdown", "id": "reliable-bedroom", "metadata": {}, "source": [ "\n", "warnings.filterwarnings('ignore')\n", "print(' Store Model : ',sys.argv[1])\n", "store_model = sys.argv[1]\n", "\n", "if(path.exists(store_model)):\n", " model = keras.models.load_model(store_model)\n", "else:\n", " model = tf.keras.Sequential()\n", " model.add(tf.keras.Input(shape=(28,)))\n", " model.add(layers.Dense(300, activation='relu',name=\"h0\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.1)))\n", " model.add(tf.keras.layers.Dropout(0.4))\n", " model.add(layers.Dense(300, activation='relu',name=\"h1\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(tf.keras.layers.Dropout(0.4))\n", " model.add(layers.Dense(300, activation='relu',name=\"h2\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(tf.keras.layers.Dropout(0.4))\n", " model.add(layers.Dense(300, activation='relu',name=\"h3\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(tf.keras.layers.Dropout(0.4))\n", " model.add(layers.Dense(1, activation='sigmoid',name=\"y\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev= 0.001)))\n", "\n", "\n", "\n", "warnings.filterwarnings('ignore')\n", "\n", "print(' Store history : ',sys.argv[2])\n", "\n", "model_fit_history = sys.argv[2]\n", "\n", "if (not path.exists(store_model)):\n", "\n", " # New model\n", " # initial_learning_rate=0.05,\n", " # decay_steps=10000,\n", " # decay_rate=0.96\n", " # momentum=0.9\n", " # batch_size=100\n", "\n", " lr_schedule = keras.optimizers.schedules.ExponentialDecay(\n", " initial_learning_rate=0.05,\n", " decay_steps=10000,\n", " decay_rate=0.96)\n", "\n", "\n", " opt = tf.keras.optimizers.SGD(learning_rate=0.05, momentum=0.9)\n", " model.compile( optimizer=opt,\n", " loss='binary_crossentropy',\n", " metrics=['accuracy','AUC'])\n", " history= model.fit(X_train, y_train, epochs=200, validation_data=(X_test,y_test), batch_size=1000)\n", "\n", " model.save(store_model)\n", " pickle.dump( history.history, open( model_fit_history, \"wb\" ) )\n", "" ] }, { "cell_type": "markdown", "id": "universal-maryland", "metadata": {}, "source": [ "## ELU with all hidden layers with Dropout 0.4" ] }, { "cell_type": "markdown", "id": "imposed-population", "metadata": {}, "source": [ "\n", "warnings.filterwarnings('ignore')\n", "print(' Store Model : ',sys.argv[1])\n", "store_model = sys.argv[1]\n", "\n", "if(path.exists(store_model)):\n", " model = keras.models.load_model(store_model)\n", "else:\n", " model = tf.keras.Sequential()\n", " model.add(tf.keras.Input(shape=(28,)))\n", " model.add(layers.Dense(300, activation='elu',name=\"h0\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.1)))\n", " model.add(tf.keras.layers.Dropout(0.5))\n", " model.add(layers.Dense(300, activation='elu',name=\"h1\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(tf.keras.layers.Dropout(0.5))\n", " model.add(layers.Dense(300, activation='elu',name=\"h2\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(tf.keras.layers.Dropout(0.5))\n", " model.add(layers.Dense(300, activation='elu',name=\"h3\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev=.05)))\n", " model.add(tf.keras.layers.Dropout(0.5))\n", " model.add(layers.Dense(1, activation='sigmoid',name=\"y\",\n", " kernel_initializer=tf.keras.initializers.RandomNormal(mean=0., stddev= 0.001)))\n", "\n", "warnings.filterwarnings('ignore')\n", "\n", "print(' Store history : ',sys.argv[2])\n", "\n", "model_fit_history = sys.argv[2]\n", "\n", "if (not path.exists(store_model)):\n", "\n", " # New model\n", " # initial_learning_rate=0.05,\n", " # decay_steps=10000,\n", " # decay_rate=0.96\n", " # momentum=0.9\n", " # batch_size=100\n", "\n", " lr_schedule = keras.optimizers.schedules.ExponentialDecay(\n", " initial_learning_rate=0.05,\n", " decay_steps=10000,\n", " decay_rate=0.96)\n", "\n", "\n", " opt = tf.keras.optimizers.SGD(learning_rate=lr_schedule, momentum=0.9)\n", " model.compile( optimizer=opt,\n", " loss='binary_crossentropy',\n", " metrics=['accuracy','AUC'])\n", " history= model.fit(X_train, y_train, epochs=200, validation_data=(X_test,y_test), batch_size=1000)\n", "\n", " model.save(store_model)\n", " pickle.dump( history.history, open( model_fit_history, \"wb\" ) )\n", "" ] }, { "cell_type": "markdown", "id": "parental-feedback", "metadata": {}, "source": [ "# Appendix-II - Job logs " ] }, { "cell_type": "markdown", "id": "native-collapse", "metadata": {}, "source": [ "## Replica Model" ] }, { "cell_type": "code", "execution_count": 27, "id": "accompanied-luxembourg", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1: 2160000/2160000 [==============================] - 51s 24us/sample - loss: 0.6580 - acc: 0.6012 - auc: 0.6389 - val_loss: 0.6435 - val_acc: 0.6262 - val_auc: 0.6695\n", "Epoch 2: 2160000/2160000 [==============================] - 47s 22us/sample - loss: 0.6441 - acc: 0.6261 - auc: 0.6684 - val_loss: 0.6388 - val_acc: 0.6357 - val_auc: 0.6787\n", "Epoch 3: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.6405 - acc: 0.6314 - auc: 0.6743 - val_loss: 0.6350 - val_acc: 0.6396 - val_auc: 0.6839\n", "Epoch 4: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.6293 - acc: 0.6427 - auc: 0.6942 - val_loss: 0.6269 - val_acc: 0.6517 - val_auc: 0.7130\n", "Epoch 5: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.6130 - acc: 0.6619 - auc: 0.7202 - val_loss: 0.6157 - val_acc: 0.6593 - val_auc: 0.7184\n", "Epoch 6: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.6043 - acc: 0.6704 - auc: 0.7322 - val_loss: 0.5993 - val_acc: 0.6768 - val_auc: 0.7411\n", "Epoch 7: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.5991 - acc: 0.6758 - auc: 0.7388 - val_loss: 0.5954 - val_acc: 0.6830 - val_auc: 0.7481\n", "Epoch 8: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.5938 - acc: 0.6810 - auc: 0.7451 - val_loss: 0.5874 - val_acc: 0.6870 - val_auc: 0.7535\n", "Epoch 9: 2160000/2160000 [==============================] - 47s 22us/sample - loss: 0.5902 - acc: 0.6840 - auc: 0.7492 - val_loss: 0.5830 - val_acc: 0.6904 - val_auc: 0.7584\n", "Epoch 10: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.5854 - acc: 0.6872 - auc: 0.7545 - val_loss: 0.5829 - val_acc: 0.6889 - val_auc: 0.7578\n", "Epoch 11: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.5809 - acc: 0.6912 - auc: 0.7592 - val_loss: 0.5864 - val_acc: 0.6855 - val_auc: 0.7540\n", "Epoch 12: 2160000/2160000 [==============================] - 49s 23us/sample - loss: 0.5768 - acc: 0.6951 - auc: 0.7637 - val_loss: 0.5825 - val_acc: 0.6899 - val_auc: 0.7615\n", "Epoch 13: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.5724 - acc: 0.6986 - auc: 0.7682 - val_loss: 0.5801 - val_acc: 0.6907 - val_auc: 0.7631\n", "Epoch 14: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.5686 - acc: 0.7013 - auc: 0.7721 - val_loss: 0.5736 - val_acc: 0.6963 - val_auc: 0.7690\n", "Epoch 15: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.5669 - acc: 0.7026 - auc: 0.7739 - val_loss: 0.5602 - val_acc: 0.7073 - val_auc: 0.7815\n", "Epoch 16: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.5634 - acc: 0.7052 - auc: 0.7774 - val_loss: 0.5592 - val_acc: 0.7073 - val_auc: 0.7823\n", "Epoch 17: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.5617 - acc: 0.7068 - auc: 0.7792 - val_loss: 0.5552 - val_acc: 0.7114 - val_auc: 0.7863\n", "Epoch 18: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.5596 - acc: 0.7083 - auc: 0.7813 - val_loss: 0.5559 - val_acc: 0.7107 - val_auc: 0.7849\n", "Epoch 19: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.5577 - acc: 0.7101 - auc: 0.7832 - val_loss: 0.5614 - val_acc: 0.7070 - val_auc: 0.7821\n", "Epoch 20: 2160000/2160000 [==============================] - 50s 23us/sample - loss: 0.5552 - acc: 0.7122 - auc: 0.7857 - val_loss: 0.5515 - val_acc: 0.7156 - val_auc: 0.7916\n", "Epoch 21: 2160000/2160000 [==============================] - 48s 22us/sample - loss: 0.5534 - acc: 0.7137 - auc: 0.7874 - val_loss: 0.5503 - val_acc: 0.7153 - val_auc: 0.7910\n", "Epoch 22: 2160000/2160000 [==============================] - 54s 25us/sample - loss: 0.5521 - acc: 0.7145 - auc: 0.7886 - val_loss: 0.5480 - val_acc: 0.7168 - val_auc: 0.7935\n", "Epoch 23: 2160000/2160000 [==============================] - 54s 25us/sample - loss: 0.5500 - acc: 0.7162 - auc: 0.7906 - val_loss: 0.5466 - val_acc: 0.7182 - val_auc: 0.7940\n", "Epoch 24: 2160000/2160000 [==============================] - 53s 25us/sample - loss: 0.5488 - acc: 0.7169 - auc: 0.7917 - val_loss: 0.5538 - val_acc: 0.7114 - val_auc: 0.7877\n", "Epoch 25: 2160000/2160000 [==============================] - 60s 28us/sample - loss: 0.5477 - acc: 0.7177 - auc: 0.7927 - val_loss: 0.5436 - val_acc: 0.7200 - val_auc: 0.7963\n", "Epoch 26: 2160000/2160000 [==============================] - 47s 22us/sample - loss: 0.5461 - acc: 0.7190 - auc: 0.7942 - val_loss: 0.5480 - val_acc: 0.7173 - val_auc: 0.7926\n", "Epoch 27: 2160000/2160000 [==============================] - 48s 22us/sample - loss: 0.5454 - acc: 0.7196 - auc: 0.7948 - val_loss: 0.5436 - val_acc: 0.7195 - val_auc: 0.7963\n", "Epoch 28: 2160000/2160000 [==============================] - 47s 22us/sample - loss: 0.5435 - acc: 0.7210 - auc: 0.7967 - val_loss: 0.5395 - val_acc: 0.7232 - val_auc: 0.8004\n", "Epoch 29: 2160000/2160000 [==============================] - 47s 22us/sample - loss: 0.5422 - acc: 0.7221 - auc: 0.7978 - val_loss: 0.5409 - val_acc: 0.7223 - val_auc: 0.7991\n", "Epoch 30: 2160000/2160000 [==============================] - 47s 22us/sample - loss: 0.5419 - acc: 0.7224 - auc: 0.7981 - val_loss: 0.5385 - val_acc: 0.7243 - val_auc: 0.8011\n", "Epoch 31: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.5398 - acc: 0.7241 - auc: 0.8001 - val_loss: 0.5367 - val_acc: 0.7254 - val_auc: 0.8038\n", "Epoch 32: 2160000/2160000 [==============================] - 50s 23us/sample - loss: 0.5388 - acc: 0.7248 - auc: 0.8011 - val_loss: 0.5379 - val_acc: 0.7253 - val_auc: 0.8032\n", "Epoch 33: 2160000/2160000 [==============================] - 47s 22us/sample - loss: 0.5373 - acc: 0.7260 - auc: 0.8024 - val_loss: 0.5369 - val_acc: 0.7256 - val_auc: 0.8038\n", "Epoch 34: 2160000/2160000 [==============================] - 51s 24us/sample - loss: 0.5355 - acc: 0.7273 - auc: 0.8040 - val_loss: 0.5361 - val_acc: 0.7263 - val_auc: 0.8042\n", "Epoch 35: 2160000/2160000 [==============================] - 48s 22us/sample - loss: 0.5351 - acc: 0.7275 - auc: 0.8043 - val_loss: 0.5343 - val_acc: 0.7279 - val_auc: 0.8049\n", "Epoch 36: 2160000/2160000 [==============================] - 54s 25us/sample - loss: 0.5338 - acc: 0.7286 - auc: 0.8056 - val_loss: 0.5369 - val_acc: 0.7264 - val_auc: 0.8030\n", "Epoch 37: 2160000/2160000 [==============================] - 56s 26us/sample - loss: 0.5330 - acc: 0.7290 - auc: 0.8062 - val_loss: 0.5344 - val_acc: 0.7277 - val_auc: 0.8055\n", "Epoch 38: 2160000/2160000 [==============================] - 48s 22us/sample - loss: 0.5318 - acc: 0.7300 - auc: 0.8073 - val_loss: 0.5304 - val_acc: 0.7311 - val_auc: 0.8091\n", "Epoch 39: 2160000/2160000 [==============================] - 50s 23us/sample - loss: 0.5312 - acc: 0.7306 - auc: 0.8078 - val_loss: 0.5300 - val_acc: 0.7312 - val_auc: 0.8091\n", "Epoch 40: 2160000/2160000 [==============================] - 49s 23us/sample - loss: 0.5301 - acc: 0.7310 - auc: 0.8087 - val_loss: 0.5282 - val_acc: 0.7311 - val_auc: 0.8100\n", "Epoch 41: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.5291 - acc: 0.7320 - auc: 0.8096 - val_loss: 0.5321 - val_acc: 0.7291 - val_auc: 0.8084\n", "Epoch 42: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.5288 - acc: 0.7319 - auc: 0.8099 - val_loss: 0.5338 - val_acc: 0.7275 - val_auc: 0.8059\n", "Epoch 43: 2160000/2160000 [==============================] - 51s 23us/sample - loss: 0.5285 - acc: 0.7326 - auc: 0.8101 - val_loss: 0.5281 - val_acc: 0.7322 - val_auc: 0.8106\n", "Epoch 44: 2160000/2160000 [==============================] - 48s 22us/sample - loss: 0.5272 - acc: 0.7333 - auc: 0.8113 - val_loss: 0.5323 - val_acc: 0.7302 - val_auc: 0.8081\n", "Epoch 45: 2160000/2160000 [==============================] - 59s 27us/sample - loss: 0.5267 - acc: 0.7339 - auc: 0.8117 - val_loss: 0.5256 - val_acc: 0.7346 - val_auc: 0.8127\n", "Epoch 46: 2160000/2160000 [==============================] - 53s 25us/sample - loss: 0.5257 - acc: 0.7344 - auc: 0.8125 - val_loss: 0.5237 - val_acc: 0.7354 - val_auc: 0.8145\n", "Epoch 47: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.5252 - acc: 0.7349 - auc: 0.8130 - val_loss: 0.5330 - val_acc: 0.7281 - val_auc: 0.8065\n", "Epoch 48: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.5236 - acc: 0.7358 - auc: 0.8143 - val_loss: 0.5253 - val_acc: 0.7335 - val_auc: 0.8129\n", "Epoch 49: 2160000/2160000 [==============================] - 52s 24us/sample - loss: 0.5229 - acc: 0.7365 - auc: 0.8150 - val_loss: 0.5262 - val_acc: 0.7326 - val_auc: 0.8142\n", "Epoch 50: 2160000/2160000 [==============================] - 53s 24us/sample - loss: 0.5215 - acc: 0.7372 - auc: 0.8161 - val_loss: 0.5208 - val_acc: 0.7369 - val_auc: 0.8168\n", "Epoch 51: 2160000/2160000 [==============================] - 49s 23us/sample - loss: 0.5213 - acc: 0.7378 - auc: 0.8163 - val_loss: 0.5227 - val_acc: 0.7355 - val_auc: 0.8150\n", "Epoch 52: 2160000/2160000 [==============================] - 48s 22us/sample - loss: 0.5199 - acc: 0.7384 - auc: 0.8175 - val_loss: 0.5209 - val_acc: 0.7375 - val_auc: 0.8176\n", "Epoch 53: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.5188 - acc: 0.7395 - auc: 0.8184 - val_loss: 0.5224 - val_acc: 0.7363 - val_auc: 0.8159\n", "Epoch 54: 2160000/2160000 [==============================] - 50s 23us/sample - loss: 0.5179 - acc: 0.7401 - auc: 0.8191 - val_loss: 0.5231 - val_acc: 0.7348 - val_auc: 0.8177\n", "Epoch 55: 2160000/2160000 [==============================] - 48s 22us/sample - loss: 0.5171 - acc: 0.7404 - auc: 0.8197 - val_loss: 0.5179 - val_acc: 0.7384 - val_auc: 0.8193\n", "Epoch 56: 2160000/2160000 [==============================] - 51s 24us/sample - loss: 0.5159 - acc: 0.7411 - auc: 0.8207 - val_loss: 0.5168 - val_acc: 0.7392 - val_auc: 0.8196\n", "Epoch 57: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.5153 - acc: 0.7419 - auc: 0.8212 - val_loss: 0.5171 - val_acc: 0.7393 - val_auc: 0.8206\n", "Epoch 58: 2160000/2160000 [==============================] - 56s 26us/sample - loss: 0.5144 - acc: 0.7422 - auc: 0.8219 - val_loss: 0.5148 - val_acc: 0.7414 - val_auc: 0.8223\n", "Epoch 59: 2160000/2160000 [==============================] - 54s 25us/sample - loss: 0.5138 - acc: 0.7428 - auc: 0.8224 - val_loss: 0.5166 - val_acc: 0.7399 - val_auc: 0.8223\n", "Epoch 60: 2160000/2160000 [==============================] - 60s 28us/sample - loss: 0.5128 - acc: 0.7434 - auc: 0.8232 - val_loss: 0.5182 - val_acc: 0.7387 - val_auc: 0.8189\n", "Epoch 61: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5121 - acc: 0.7440 - auc: 0.8237 - val_loss: 0.5163 - val_acc: 0.7398 - val_auc: 0.8229\n", "Epoch 62: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5119 - acc: 0.7441 - auc: 0.8239 - val_loss: 0.5150 - val_acc: 0.7410 - val_auc: 0.8235\n", "Epoch 63: 2160000/2160000 [==============================] - 59s 27us/sample - loss: 0.5110 - acc: 0.7445 - auc: 0.8246 - val_loss: 0.5149 - val_acc: 0.7417 - val_auc: 0.8215\n", "Epoch 64: 2160000/2160000 [==============================] - 79s 36us/sample - loss: 0.5100 - acc: 0.7452 - auc: 0.8254 - val_loss: 0.5142 - val_acc: 0.7417 - val_auc: 0.8223\n", "Epoch 65: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5097 - acc: 0.7453 - auc: 0.8256 - val_loss: 0.5155 - val_acc: 0.7406 - val_auc: 0.8210\n", "Epoch 66: 2160000/2160000 [==============================] - 82s 38us/sample - loss: 0.5092 - acc: 0.7459 - auc: 0.8260 - val_loss: 0.5110 - val_acc: 0.7438 - val_auc: 0.8247\n", "Epoch 67: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5091 - acc: 0.7463 - auc: 0.8261 - val_loss: 0.5081 - val_acc: 0.7458 - val_auc: 0.8266\n", "Epoch 68: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5082 - acc: 0.7465 - auc: 0.8268 - val_loss: 0.5108 - val_acc: 0.7437 - val_auc: 0.8256\n", "Epoch 69: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5076 - acc: 0.7470 - auc: 0.8273 - val_loss: 0.5083 - val_acc: 0.7453 - val_auc: 0.8271\n", "Epoch 70: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5071 - acc: 0.7470 - auc: 0.8276 - val_loss: 0.5063 - val_acc: 0.7472 - val_auc: 0.8286\n", "Epoch 71: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5070 - acc: 0.7473 - auc: 0.8277 - val_loss: 0.5092 - val_acc: 0.7453 - val_auc: 0.8267\n", "Epoch 72: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5064 - acc: 0.7475 - auc: 0.8282 - val_loss: 0.5111 - val_acc: 0.7442 - val_auc: 0.8255\n", "Epoch 73: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5061 - acc: 0.7479 - auc: 0.8284 - val_loss: 0.5083 - val_acc: 0.7462 - val_auc: 0.8284\n", "Epoch 74: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5057 - acc: 0.7482 - auc: 0.8288 - val_loss: 0.5082 - val_acc: 0.7460 - val_auc: 0.8273\n", "Epoch 75: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5050 - acc: 0.7486 - auc: 0.8294 - val_loss: 0.5070 - val_acc: 0.7465 - val_auc: 0.8285\n", "Epoch 76: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5051 - acc: 0.7485 - auc: 0.8293 - val_loss: 0.5042 - val_acc: 0.7481 - val_auc: 0.8304\n", "Epoch 77: 2160000/2160000 [==============================] - 89s 41us/sample - loss: 0.5043 - acc: 0.7491 - auc: 0.8298 - val_loss: 0.5069 - val_acc: 0.7463 - val_auc: 0.8286\n", "Epoch 78: 2160000/2160000 [==============================] - 89s 41us/sample - loss: 0.5041 - acc: 0.7493 - auc: 0.8301 - val_loss: 0.5052 - val_acc: 0.7470 - val_auc: 0.8293\n", "Epoch 79: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5039 - acc: 0.7492 - auc: 0.8302 - val_loss: 0.5063 - val_acc: 0.7479 - val_auc: 0.8282\n", "Epoch 80: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5035 - acc: 0.7497 - auc: 0.8305 - val_loss: 0.5056 - val_acc: 0.7473 - val_auc: 0.8303\n", "Epoch 81: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5031 - acc: 0.7499 - auc: 0.8308 - val_loss: 0.5042 - val_acc: 0.7486 - val_auc: 0.8300\n", "Epoch 82: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5022 - acc: 0.7503 - auc: 0.8315 - val_loss: 0.5118 - val_acc: 0.7439 - val_auc: 0.8238\n", "Epoch 83: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5025 - acc: 0.7505 - auc: 0.8313 - val_loss: 0.5090 - val_acc: 0.7456 - val_auc: 0.8259\n", "Epoch 84: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5017 - acc: 0.7506 - auc: 0.8318 - val_loss: 0.5044 - val_acc: 0.7483 - val_auc: 0.8305\n", "Epoch 85: 2160000/2160000 [==============================] - 76s 35us/sample - loss: 0.5007 - acc: 0.7515 - auc: 0.8326 - val_loss: 0.5024 - val_acc: 0.7493 - val_auc: 0.8321\n", "Epoch 86: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.5010 - acc: 0.7511 - auc: 0.8324 - val_loss: 0.5062 - val_acc: 0.7468 - val_auc: 0.8283\n", "Epoch 87: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.5004 - acc: 0.7516 - auc: 0.8329 - val_loss: 0.5022 - val_acc: 0.7496 - val_auc: 0.8318\n", "Epoch 88: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.5003 - acc: 0.7518 - auc: 0.8329 - val_loss: 0.5080 - val_acc: 0.7473 - val_auc: 0.8281\n", "Epoch 89: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.5001 - acc: 0.7517 - auc: 0.8331 - val_loss: 0.5044 - val_acc: 0.7483 - val_auc: 0.8296\n", "Epoch 90: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4996 - acc: 0.7523 - auc: 0.8336 - val_loss: 0.5003 - val_acc: 0.7515 - val_auc: 0.8335\n", "Epoch 91: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4993 - acc: 0.7523 - auc: 0.8337 - val_loss: 0.5005 - val_acc: 0.7511 - val_auc: 0.8327\n", "Epoch 92: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4983 - acc: 0.7528 - auc: 0.8345 - val_loss: 0.5043 - val_acc: 0.7484 - val_auc: 0.8299\n", "Epoch 93: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4986 - acc: 0.7527 - auc: 0.8343 - val_loss: 0.5014 - val_acc: 0.7502 - val_auc: 0.8327\n", "Epoch 94: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4983 - acc: 0.7528 - auc: 0.8344 - val_loss: 0.5013 - val_acc: 0.7507 - val_auc: 0.8325\n", "Epoch 95: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4980 - acc: 0.7531 - auc: 0.8347 - val_loss: 0.5038 - val_acc: 0.7497 - val_auc: 0.8323\n", "Epoch 96: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4976 - acc: 0.7534 - auc: 0.8350 - val_loss: 0.4978 - val_acc: 0.7522 - val_auc: 0.8352\n", "Epoch 97: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.4971 - acc: 0.7538 - auc: 0.8354 - val_loss: 0.4975 - val_acc: 0.7531 - val_auc: 0.8353\n", "Epoch 98: 2160000/2160000 [==============================] - 47s 22us/sample - loss: 0.4967 - acc: 0.7542 - auc: 0.8357 - val_loss: 0.5036 - val_acc: 0.7498 - val_auc: 0.8311\n", "Epoch 99: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4960 - acc: 0.7544 - auc: 0.8362 - val_loss: 0.4993 - val_acc: 0.7514 - val_auc: 0.8335\n", "Epoch 100: 2160000/2160000 [==============================] - 50s 23us/sample - loss: 0.4965 - acc: 0.7542 - auc: 0.8358 - val_loss: 0.4967 - val_acc: 0.7534 - val_auc: 0.8356\n", "Epoch 101: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4957 - acc: 0.7545 - auc: 0.8364 - val_loss: 0.4992 - val_acc: 0.7522 - val_auc: 0.8342\n", "Epoch 102: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4956 - acc: 0.7547 - auc: 0.8365 - val_loss: 0.5021 - val_acc: 0.7495 - val_auc: 0.8332\n", "Epoch 103: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4954 - acc: 0.7547 - auc: 0.8366 - val_loss: 0.4965 - val_acc: 0.7529 - val_auc: 0.8363\n", "Epoch 104: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4946 - acc: 0.7554 - auc: 0.8373 - val_loss: 0.4984 - val_acc: 0.7524 - val_auc: 0.8360\n", "Epoch 105: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4944 - acc: 0.7556 - auc: 0.8374 - val_loss: 0.4995 - val_acc: 0.7516 - val_auc: 0.8338\n", "Epoch 106: 2160000/2160000 [==============================] - 50s 23us/sample - loss: 0.4944 - acc: 0.7554 - auc: 0.8374 - val_loss: 0.5028 - val_acc: 0.7491 - val_auc: 0.8315\n", "Epoch 107: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4941 - acc: 0.7556 - auc: 0.8376 - val_loss: 0.4958 - val_acc: 0.7544 - val_auc: 0.8367\n", "Epoch 108: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4940 - acc: 0.7556 - auc: 0.8377 - val_loss: 0.4954 - val_acc: 0.7548 - val_auc: 0.8368\n", "Epoch 109: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4933 - acc: 0.7563 - auc: 0.8382 - val_loss: 0.5003 - val_acc: 0.7509 - val_auc: 0.8328\n", "Epoch 110: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.4933 - acc: 0.7563 - auc: 0.8382 - val_loss: 0.4962 - val_acc: 0.7541 - val_auc: 0.8366\n", "Epoch 111: 2160000/2160000 [==============================] - 47s 22us/sample - loss: 0.4929 - acc: 0.7562 - auc: 0.8385 - val_loss: 0.4947 - val_acc: 0.7543 - val_auc: 0.8383\n", "Epoch 112: 2160000/2160000 [==============================] - 49s 23us/sample - loss: 0.4925 - acc: 0.7567 - auc: 0.8388 - val_loss: 0.4927 - val_acc: 0.7561 - val_auc: 0.8384\n", "Epoch 113: 2160000/2160000 [==============================] - 44s 21us/sample - loss: 0.4924 - acc: 0.7567 - auc: 0.8389 - val_loss: 0.4963 - val_acc: 0.7536 - val_auc: 0.8363\n", "Epoch 114: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4921 - acc: 0.7571 - auc: 0.8391 - val_loss: 0.4927 - val_acc: 0.7558 - val_auc: 0.8387\n", "Epoch 115: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.4920 - acc: 0.7569 - auc: 0.8392 - val_loss: 0.4972 - val_acc: 0.7529 - val_auc: 0.8361\n", "Epoch 116: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4914 - acc: 0.7572 - auc: 0.8396 - val_loss: 0.4974 - val_acc: 0.7530 - val_auc: 0.8351\n", "Epoch 117: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4917 - acc: 0.7574 - auc: 0.8395 - val_loss: 0.4987 - val_acc: 0.7524 - val_auc: 0.8350\n", "Epoch 118: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4912 - acc: 0.7574 - auc: 0.8398 - val_loss: 0.4957 - val_acc: 0.7543 - val_auc: 0.8366\n", "Epoch 119: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4914 - acc: 0.7572 - auc: 0.8397 - val_loss: 0.4936 - val_acc: 0.7551 - val_auc: 0.8391\n", "Epoch 120: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4911 - acc: 0.7578 - auc: 0.8398 - val_loss: 0.4992 - val_acc: 0.7518 - val_auc: 0.8359\n", "Epoch 121: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4908 - acc: 0.7577 - auc: 0.8401 - val_loss: 0.4945 - val_acc: 0.7550 - val_auc: 0.8372\n", "Epoch 122: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4902 - acc: 0.7583 - auc: 0.8406 - val_loss: 0.4920 - val_acc: 0.7564 - val_auc: 0.8391\n", "Epoch 123: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4897 - acc: 0.7585 - auc: 0.8409 - val_loss: 0.5028 - val_acc: 0.7502 - val_auc: 0.8319\n", "Epoch 124: 2160000/2160000 [==============================] - 48s 22us/sample - loss: 0.4898 - acc: 0.7587 - auc: 0.8408 - val_loss: 0.4962 - val_acc: 0.7532 - val_auc: 0.8390\n", "Epoch 125: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4896 - acc: 0.7587 - auc: 0.8410 - val_loss: 0.4898 - val_acc: 0.7578 - val_auc: 0.8407\n", "Epoch 126: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.4893 - acc: 0.7588 - auc: 0.8412 - val_loss: 0.4954 - val_acc: 0.7540 - val_auc: 0.8369\n", "Epoch 127: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4894 - acc: 0.7587 - auc: 0.8411 - val_loss: 0.4909 - val_acc: 0.7570 - val_auc: 0.8403\n", "Epoch 128: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4888 - acc: 0.7590 - auc: 0.8416 - val_loss: 0.4970 - val_acc: 0.7530 - val_auc: 0.8373\n", "Epoch 129: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4886 - acc: 0.7592 - auc: 0.8417 - val_loss: 0.4920 - val_acc: 0.7564 - val_auc: 0.8390\n", "Epoch 130: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4884 - acc: 0.7592 - auc: 0.8418 - val_loss: 0.4945 - val_acc: 0.7546 - val_auc: 0.8374\n", "Epoch 131: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4880 - acc: 0.7597 - auc: 0.8422 - val_loss: 0.4933 - val_acc: 0.7554 - val_auc: 0.8385\n", "Epoch 132: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4883 - acc: 0.7592 - auc: 0.8419 - val_loss: 0.4910 - val_acc: 0.7569 - val_auc: 0.8396\n", "Epoch 133: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.4881 - acc: 0.7594 - auc: 0.8421 - val_loss: 0.4969 - val_acc: 0.7529 - val_auc: 0.8360\n", "Epoch 134: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4877 - acc: 0.7599 - auc: 0.8424 - val_loss: 0.4906 - val_acc: 0.7576 - val_auc: 0.8400\n", "Epoch 135: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4876 - acc: 0.7597 - auc: 0.8424 - val_loss: 0.4931 - val_acc: 0.7557 - val_auc: 0.8389\n", "Epoch 136: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4878 - acc: 0.7597 - auc: 0.8423 - val_loss: 0.4913 - val_acc: 0.7571 - val_auc: 0.8396\n", "Epoch 137: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.4878 - acc: 0.7598 - auc: 0.8423 - val_loss: 0.4973 - val_acc: 0.7529 - val_auc: 0.8373\n", "Epoch 138: 2160000/2160000 [==============================] - 48s 22us/sample - loss: 0.4869 - acc: 0.7601 - auc: 0.8429 - val_loss: 0.4934 - val_acc: 0.7550 - val_auc: 0.8389\n", "Epoch 139: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4869 - acc: 0.7604 - auc: 0.8430 - val_loss: 0.4952 - val_acc: 0.7542 - val_auc: 0.8367\n", "Epoch 140: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4864 - acc: 0.7609 - auc: 0.8433 - val_loss: 0.4895 - val_acc: 0.7585 - val_auc: 0.8411\n", "Epoch 141: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4863 - acc: 0.7608 - auc: 0.8434 - val_loss: 0.4915 - val_acc: 0.7564 - val_auc: 0.8393\n", "Epoch 142: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4860 - acc: 0.7607 - auc: 0.8436 - val_loss: 0.4898 - val_acc: 0.7581 - val_auc: 0.8411\n", "Epoch 143: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4861 - acc: 0.7607 - auc: 0.8436 - val_loss: 0.4920 - val_acc: 0.7570 - val_auc: 0.8392\n", "Epoch 144: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4863 - acc: 0.7608 - auc: 0.8435 - val_loss: 0.4930 - val_acc: 0.7558 - val_auc: 0.8381\n", "Epoch 145: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4859 - acc: 0.7608 - auc: 0.8436 - val_loss: 0.4884 - val_acc: 0.7585 - val_auc: 0.8416\n", "Epoch 146: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4854 - acc: 0.7612 - auc: 0.8441 - val_loss: 0.4919 - val_acc: 0.7566 - val_auc: 0.8396\n", "Epoch 147: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4853 - acc: 0.7613 - auc: 0.8441 - val_loss: 0.4897 - val_acc: 0.7583 - val_auc: 0.8410\n", "Epoch 148: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4851 - acc: 0.7615 - auc: 0.8442 - val_loss: 0.4899 - val_acc: 0.7580 - val_auc: 0.8407\n", "Epoch 149: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4846 - acc: 0.7619 - auc: 0.8446 - val_loss: 0.4915 - val_acc: 0.7570 - val_auc: 0.8398\n", "Epoch 150: 2160000/2160000 [==============================] - 50s 23us/sample - loss: 0.4847 - acc: 0.7618 - auc: 0.8446 - val_loss: 0.4943 - val_acc: 0.7560 - val_auc: 0.8384\n", "Epoch 151: 2160000/2160000 [==============================] - 49s 23us/sample - loss: 0.4847 - acc: 0.7617 - auc: 0.8445 - val_loss: 0.4979 - val_acc: 0.7532 - val_auc: 0.8351\n", "Epoch 152: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4845 - acc: 0.7619 - auc: 0.8447 - val_loss: 0.4878 - val_acc: 0.7591 - val_auc: 0.8421\n", "Epoch 153: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4841 - acc: 0.7622 - auc: 0.8450 - val_loss: 0.4871 - val_acc: 0.7596 - val_auc: 0.8425\n", "Epoch 154: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.4840 - acc: 0.7622 - auc: 0.8451 - val_loss: 0.4961 - val_acc: 0.7540 - val_auc: 0.8360\n", "Epoch 155: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4838 - acc: 0.7623 - auc: 0.8452 - val_loss: 0.4883 - val_acc: 0.7593 - val_auc: 0.8430\n", "Epoch 156: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4838 - acc: 0.7621 - auc: 0.8452 - val_loss: 0.4890 - val_acc: 0.7587 - val_auc: 0.8419\n", "Epoch 157: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4833 - acc: 0.7626 - auc: 0.8456 - val_loss: 0.4883 - val_acc: 0.7586 - val_auc: 0.8417\n", "Epoch 158: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.4830 - acc: 0.7627 - auc: 0.8458 - val_loss: 0.4898 - val_acc: 0.7575 - val_auc: 0.8409\n", "Epoch 159: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4830 - acc: 0.7628 - auc: 0.8458 - val_loss: 0.4906 - val_acc: 0.7573 - val_auc: 0.8404\n", "Epoch 160: 2160000/2160000 [==============================] - 42s 19us/sample - loss: 0.4831 - acc: 0.7627 - auc: 0.8457 - val_loss: 0.4963 - val_acc: 0.7551 - val_auc: 0.8364\n", "Epoch 161: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4830 - acc: 0.7627 - auc: 0.8458 - val_loss: 0.4902 - val_acc: 0.7585 - val_auc: 0.8416\n", "Epoch 162: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.4827 - acc: 0.7629 - auc: 0.8460 - val_loss: 0.4876 - val_acc: 0.7594 - val_auc: 0.8426\n", "Epoch 163: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.4824 - acc: 0.7633 - auc: 0.8462 - val_loss: 0.4888 - val_acc: 0.7593 - val_auc: 0.8419\n", "Epoch 164: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.4825 - acc: 0.7631 - auc: 0.8461 - val_loss: 0.4882 - val_acc: 0.7589 - val_auc: 0.8419\n", "Epoch 165: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4821 - acc: 0.7633 - auc: 0.8465 - val_loss: 0.4897 - val_acc: 0.7576 - val_auc: 0.8409\n", "Epoch 166: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4821 - acc: 0.7633 - auc: 0.8464 - val_loss: 0.4908 - val_acc: 0.7568 - val_auc: 0.8421\n", "Epoch 167: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4818 - acc: 0.7635 - auc: 0.8466 - val_loss: 0.4886 - val_acc: 0.7583 - val_auc: 0.8421\n", "Epoch 168: 2160000/2160000 [==============================] - 42s 19us/sample - loss: 0.4814 - acc: 0.7639 - auc: 0.8469 - val_loss: 0.4879 - val_acc: 0.7587 - val_auc: 0.8425\n", "Epoch 169: 2160000/2160000 [==============================] - 42s 19us/sample - loss: 0.4813 - acc: 0.7637 - auc: 0.8470 - val_loss: 0.4896 - val_acc: 0.7581 - val_auc: 0.8411\n", "Epoch 170: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4814 - acc: 0.7639 - auc: 0.8469 - val_loss: 0.4889 - val_acc: 0.7587 - val_auc: 0.8414\n", "Epoch 171: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.4813 - acc: 0.7640 - auc: 0.8470 - val_loss: 0.4889 - val_acc: 0.7582 - val_auc: 0.8423\n", "Epoch 172: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.4811 - acc: 0.7641 - auc: 0.8472 - val_loss: 0.4884 - val_acc: 0.7585 - val_auc: 0.8417\n", "Epoch 173: 2160000/2160000 [==============================] - 44s 21us/sample - loss: 0.4809 - acc: 0.7642 - auc: 0.8473 - val_loss: 0.4857 - val_acc: 0.7606 - val_auc: 0.8441\n", "Epoch 174: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.4810 - acc: 0.7639 - auc: 0.8473 - val_loss: 0.4868 - val_acc: 0.7593 - val_auc: 0.8429\n", "Epoch 175: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4804 - acc: 0.7645 - auc: 0.8476 - val_loss: 0.4871 - val_acc: 0.7601 - val_auc: 0.8427\n", "Epoch 176: 2160000/2160000 [==============================] - 42s 19us/sample - loss: 0.4803 - acc: 0.7645 - auc: 0.8477 - val_loss: 0.4899 - val_acc: 0.7576 - val_auc: 0.8421\n", "Epoch 177: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4805 - acc: 0.7645 - auc: 0.8476 - val_loss: 0.4898 - val_acc: 0.7594 - val_auc: 0.8429\n", "Epoch 178: 2160000/2160000 [==============================] - 45s 21us/sample - loss: 0.4800 - acc: 0.7646 - auc: 0.8479 - val_loss: 0.4858 - val_acc: 0.7605 - val_auc: 0.8437\n", "Epoch 179: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4802 - acc: 0.7645 - auc: 0.8478 - val_loss: 0.4892 - val_acc: 0.7582 - val_auc: 0.8414\n", "Epoch 180: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4799 - acc: 0.7648 - auc: 0.8480 - val_loss: 0.4869 - val_acc: 0.7594 - val_auc: 0.8433\n", "Epoch 181: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4798 - acc: 0.7648 - auc: 0.8481 - val_loss: 0.4863 - val_acc: 0.7602 - val_auc: 0.8433\n", "Epoch 182: 2160000/2160000 [==============================] - 42s 19us/sample - loss: 0.4797 - acc: 0.7648 - auc: 0.8482 - val_loss: 0.4857 - val_acc: 0.7607 - val_auc: 0.8440\n", "Epoch 183: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4799 - acc: 0.7650 - auc: 0.8480 - val_loss: 0.4890 - val_acc: 0.7584 - val_auc: 0.8411\n", "Epoch 184: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4791 - acc: 0.7652 - auc: 0.8486 - val_loss: 0.4862 - val_acc: 0.7608 - val_auc: 0.8441\n", "Epoch 185: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4792 - acc: 0.7654 - auc: 0.8485 - val_loss: 0.4875 - val_acc: 0.7587 - val_auc: 0.8427\n", "Epoch 186: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4788 - acc: 0.7655 - auc: 0.8488 - val_loss: 0.4923 - val_acc: 0.7565 - val_auc: 0.8406\n", "Epoch 187: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4788 - acc: 0.7656 - auc: 0.8488 - val_loss: 0.4859 - val_acc: 0.7596 - val_auc: 0.8434\n", "Epoch 188: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4785 - acc: 0.7656 - auc: 0.8490 - val_loss: 0.4863 - val_acc: 0.7601 - val_auc: 0.8432\n", "Epoch 189: 2160000/2160000 [==============================] - 42s 19us/sample - loss: 0.4788 - acc: 0.7655 - auc: 0.8488 - val_loss: 0.4872 - val_acc: 0.7589 - val_auc: 0.8439\n", "Epoch 190: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4782 - acc: 0.7659 - auc: 0.8492 - val_loss: 0.4914 - val_acc: 0.7566 - val_auc: 0.8409\n", "Epoch 191: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4784 - acc: 0.7658 - auc: 0.8491 - val_loss: 0.4862 - val_acc: 0.7607 - val_auc: 0.8436\n", "Epoch 192: 2160000/2160000 [==============================] - 44s 21us/sample - loss: 0.4781 - acc: 0.7660 - auc: 0.8493 - val_loss: 0.4874 - val_acc: 0.7595 - val_auc: 0.8428\n", "Epoch 193: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4780 - acc: 0.7662 - auc: 0.8494 - val_loss: 0.4854 - val_acc: 0.7608 - val_auc: 0.8440\n", "Epoch 194: 2160000/2160000 [==============================] - 47s 22us/sample - loss: 0.4778 - acc: 0.7660 - auc: 0.8495 - val_loss: 0.4886 - val_acc: 0.7591 - val_auc: 0.8419\n", "Epoch 195: 2160000/2160000 [==============================] - 46s 21us/sample - loss: 0.4780 - acc: 0.7660 - auc: 0.8494 - val_loss: 0.4841 - val_acc: 0.7616 - val_auc: 0.8450\n", "Epoch 196: 2160000/2160000 [==============================] - 44s 20us/sample - loss: 0.4777 - acc: 0.7663 - auc: 0.8495 - val_loss: 0.4876 - val_acc: 0.7596 - val_auc: 0.8425\n", "Epoch 197: 2160000/2160000 [==============================] - 43s 20us/sample - loss: 0.4776 - acc: 0.7663 - auc: 0.8497 - val_loss: 0.4889 - val_acc: 0.7582 - val_auc: 0.8412\n", "Epoch 198: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4776 - acc: 0.7664 - auc: 0.8497 - val_loss: 0.4874 - val_acc: 0.7594 - val_auc: 0.8424\n", "Epoch 199: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4773 - acc: 0.7665 - auc: 0.8499 - val_loss: 0.4902 - val_acc: 0.7575 - val_auc: 0.8416\n", "Epoch 200: 2160000/2160000 [==============================] - 42s 20us/sample - loss: 0.4771 - acc: 0.7666 - auc: 0.8500 - val_loss: 0.4850 - val_acc: 0.7614 - val_auc: 0.8451\n" ] } ], "source": [ "print_logs('replica_model.log')" ] }, { "cell_type": "markdown", "id": "agricultural-particle", "metadata": {}, "source": [ "## RELU top hidden layer with Dropout 0.5 " ] }, { "cell_type": "code", "execution_count": 29, "id": "related-conditioning", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.6819 - acc: 0.5553 - auc: 0.5714 - val_loss: 0.6479 - val_acc: 0.6248 - val_auc: 0.6675\n", "Epoch 2: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.6496 - acc: 0.6169 - auc: 0.6585 - val_loss: 0.6334 - val_acc: 0.6414 - val_auc: 0.6930\n", "Epoch 3: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.6439 - acc: 0.6239 - auc: 0.6695 - val_loss: 0.6316 - val_acc: 0.6366 - val_auc: 0.6983\n", "Epoch 4: 2160000/2160000 [==============================] - 70s 33us/sample - loss: 0.6398 - acc: 0.6299 - auc: 0.6770 - val_loss: 0.6361 - val_acc: 0.6335 - val_auc: 0.6939\n", "Epoch 5: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.6385 - acc: 0.6314 - auc: 0.6785 - val_loss: 0.6275 - val_acc: 0.6452 - val_auc: 0.7002\n", "Epoch 6: 2160000/2160000 [==============================] - 64s 29us/sample - loss: 0.6343 - acc: 0.6365 - auc: 0.6861 - val_loss: 0.6197 - val_acc: 0.6493 - val_auc: 0.7154\n", "Epoch 7: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.6307 - acc: 0.6413 - auc: 0.6925 - val_loss: 0.6254 - val_acc: 0.6419 - val_auc: 0.7137\n", "Epoch 8: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.6280 - acc: 0.6447 - auc: 0.6971 - val_loss: 0.6163 - val_acc: 0.6571 - val_auc: 0.7177\n", "Epoch 9: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.6246 - acc: 0.6486 - auc: 0.7024 - val_loss: 0.6134 - val_acc: 0.6600 - val_auc: 0.7226\n", "Epoch 10: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.6234 - acc: 0.6501 - auc: 0.7040 - val_loss: 0.6130 - val_acc: 0.6617 - val_auc: 0.7259\n", "Epoch 11: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.6211 - acc: 0.6534 - auc: 0.7076 - val_loss: 0.6092 - val_acc: 0.6743 - val_auc: 0.7356\n", "Epoch 12: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.6205 - acc: 0.6545 - auc: 0.7080 - val_loss: 0.6105 - val_acc: 0.6686 - val_auc: 0.7286\n", "Epoch 13: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.6186 - acc: 0.6563 - auc: 0.7111 - val_loss: 0.6062 - val_acc: 0.6702 - val_auc: 0.7364\n", "Epoch 14: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.6173 - acc: 0.6573 - auc: 0.7130 - val_loss: 0.5966 - val_acc: 0.6798 - val_auc: 0.7442\n", "Epoch 15: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.6153 - acc: 0.6582 - auc: 0.7155 - val_loss: 0.6061 - val_acc: 0.6729 - val_auc: 0.7412\n", "Epoch 16: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.6163 - acc: 0.6561 - auc: 0.7136 - val_loss: 0.6043 - val_acc: 0.6689 - val_auc: 0.7413\n", "Epoch 17: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.6130 - acc: 0.6609 - auc: 0.7188 - val_loss: 0.6010 - val_acc: 0.6772 - val_auc: 0.7455\n", "Epoch 18: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.6128 - acc: 0.6598 - auc: 0.7190 - val_loss: 0.6014 - val_acc: 0.6806 - val_auc: 0.7453\n", "Epoch 19: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.6093 - acc: 0.6640 - auc: 0.7241 - val_loss: 0.6144 - val_acc: 0.6576 - val_auc: 0.7500\n", "Epoch 20: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.6056 - acc: 0.6681 - auc: 0.7292 - val_loss: 0.5986 - val_acc: 0.6779 - val_auc: 0.7580\n", "Epoch 21: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.6045 - acc: 0.6683 - auc: 0.7304 - val_loss: 0.5913 - val_acc: 0.6853 - val_auc: 0.7563\n", "Epoch 22: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.6032 - acc: 0.6704 - auc: 0.7323 - val_loss: 0.6089 - val_acc: 0.6636 - val_auc: 0.7526\n", "Epoch 23: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.6000 - acc: 0.6738 - auc: 0.7366 - val_loss: 0.5973 - val_acc: 0.6762 - val_auc: 0.7614\n", "Epoch 24: 2160000/2160000 [==============================] - 64s 29us/sample - loss: 0.5970 - acc: 0.6763 - auc: 0.7402 - val_loss: 0.5919 - val_acc: 0.6862 - val_auc: 0.7637\n", "Epoch 25: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5964 - acc: 0.6769 - auc: 0.7409 - val_loss: 0.6032 - val_acc: 0.6704 - val_auc: 0.7587\n", "Epoch 26: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5947 - acc: 0.6789 - auc: 0.7432 - val_loss: 0.5944 - val_acc: 0.6785 - val_auc: 0.7627\n", "Epoch 27: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5960 - acc: 0.6775 - auc: 0.7413 - val_loss: 0.5893 - val_acc: 0.6887 - val_auc: 0.7626\n", "Epoch 28: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5943 - acc: 0.6790 - auc: 0.7434 - val_loss: 0.5995 - val_acc: 0.6720 - val_auc: 0.7621\n", "Epoch 29: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5935 - acc: 0.6799 - auc: 0.7444 - val_loss: 0.5964 - val_acc: 0.6803 - val_auc: 0.7648\n", "Epoch 30: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5914 - acc: 0.6824 - auc: 0.7472 - val_loss: 0.5917 - val_acc: 0.6806 - val_auc: 0.7656\n", "Epoch 31: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5920 - acc: 0.6812 - auc: 0.7461 - val_loss: 0.5952 - val_acc: 0.6795 - val_auc: 0.7594\n", "Epoch 32: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5881 - acc: 0.6850 - auc: 0.7511 - val_loss: 0.5857 - val_acc: 0.6902 - val_auc: 0.7700\n", "Epoch 33: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5881 - acc: 0.6849 - auc: 0.7509 - val_loss: 0.5965 - val_acc: 0.6762 - val_auc: 0.7705\n", "Epoch 34: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5870 - acc: 0.6857 - auc: 0.7522 - val_loss: 0.5987 - val_acc: 0.6766 - val_auc: 0.7659\n", "Epoch 35: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5840 - acc: 0.6886 - auc: 0.7557 - val_loss: 0.5946 - val_acc: 0.6738 - val_auc: 0.7709\n", "Epoch 36: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5825 - acc: 0.6898 - auc: 0.7574 - val_loss: 0.5850 - val_acc: 0.6878 - val_auc: 0.7769\n", "Epoch 37: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5821 - acc: 0.6900 - auc: 0.7578 - val_loss: 0.5995 - val_acc: 0.6738 - val_auc: 0.7693\n", "Epoch 38: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5807 - acc: 0.6916 - auc: 0.7595 - val_loss: 0.6048 - val_acc: 0.6691 - val_auc: 0.7720\n", "Epoch 39: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5814 - acc: 0.6909 - auc: 0.7585 - val_loss: 0.5941 - val_acc: 0.6780 - val_auc: 0.7723\n", "Epoch 40: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5792 - acc: 0.6929 - auc: 0.7611 - val_loss: 0.5867 - val_acc: 0.6886 - val_auc: 0.7744\n", "Epoch 41: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5788 - acc: 0.6930 - auc: 0.7615 - val_loss: 0.5947 - val_acc: 0.6797 - val_auc: 0.7759\n", "Epoch 42: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5778 - acc: 0.6940 - auc: 0.7627 - val_loss: 0.5959 - val_acc: 0.6801 - val_auc: 0.7741\n", "Epoch 43: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5767 - acc: 0.6949 - auc: 0.7638 - val_loss: 0.5815 - val_acc: 0.6906 - val_auc: 0.7795\n", "Epoch 44: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5761 - acc: 0.6957 - auc: 0.7645 - val_loss: 0.6173 - val_acc: 0.6599 - val_auc: 0.7739\n", "Epoch 45: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5759 - acc: 0.6958 - auc: 0.7647 - val_loss: 0.5775 - val_acc: 0.6955 - val_auc: 0.7796\n", "Epoch 46: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5754 - acc: 0.6963 - auc: 0.7652 - val_loss: 0.5873 - val_acc: 0.6857 - val_auc: 0.7796\n", "Epoch 47: 2160000/2160000 [==============================] - 64s 29us/sample - loss: 0.5744 - acc: 0.6974 - auc: 0.7663 - val_loss: 0.5943 - val_acc: 0.6796 - val_auc: 0.7759\n", "Epoch 48: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5741 - acc: 0.6973 - auc: 0.7666 - val_loss: 0.5875 - val_acc: 0.6882 - val_auc: 0.7779\n", "Epoch 49: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5730 - acc: 0.6984 - auc: 0.7678 - val_loss: 0.6156 - val_acc: 0.6527 - val_auc: 0.7779\n", "Epoch 50: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5726 - acc: 0.6985 - auc: 0.7682 - val_loss: 0.5898 - val_acc: 0.6815 - val_auc: 0.7802\n", "Epoch 51: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5722 - acc: 0.6993 - auc: 0.7688 - val_loss: 0.5762 - val_acc: 0.6963 - val_auc: 0.7830\n", "Epoch 52: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5713 - acc: 0.6999 - auc: 0.7696 - val_loss: 0.5676 - val_acc: 0.7032 - val_auc: 0.7830\n", "Epoch 53: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5710 - acc: 0.7002 - auc: 0.7700 - val_loss: 0.5835 - val_acc: 0.6878 - val_auc: 0.7794\n", "Epoch 54: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5698 - acc: 0.7013 - auc: 0.7713 - val_loss: 0.5792 - val_acc: 0.6938 - val_auc: 0.7844\n", "Epoch 55: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5696 - acc: 0.7014 - auc: 0.7715 - val_loss: 0.5835 - val_acc: 0.6884 - val_auc: 0.7826\n", "Epoch 56: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5694 - acc: 0.7014 - auc: 0.7716 - val_loss: 0.5750 - val_acc: 0.6941 - val_auc: 0.7854\n", "Epoch 57: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5697 - acc: 0.7011 - auc: 0.7713 - val_loss: 0.5778 - val_acc: 0.6917 - val_auc: 0.7867\n", "Epoch 58: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.5692 - acc: 0.7017 - auc: 0.7719 - val_loss: 0.5753 - val_acc: 0.6953 - val_auc: 0.7848\n", "Epoch 59: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5691 - acc: 0.7016 - auc: 0.7720 - val_loss: 0.5896 - val_acc: 0.6790 - val_auc: 0.7847\n", "Epoch 60: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5678 - acc: 0.7029 - auc: 0.7733 - val_loss: 0.5818 - val_acc: 0.6923 - val_auc: 0.7831\n", "Epoch 61: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5682 - acc: 0.7022 - auc: 0.7729 - val_loss: 0.5809 - val_acc: 0.6918 - val_auc: 0.7830\n", "Epoch 62: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5669 - acc: 0.7036 - auc: 0.7742 - val_loss: 0.5700 - val_acc: 0.7002 - val_auc: 0.7866\n", "Epoch 63: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5671 - acc: 0.7033 - auc: 0.7740 - val_loss: 0.5705 - val_acc: 0.7013 - val_auc: 0.7875\n", "Epoch 64: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5681 - acc: 0.7028 - auc: 0.7731 - val_loss: 0.5754 - val_acc: 0.6962 - val_auc: 0.7858\n", "Epoch 65: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5677 - acc: 0.7028 - auc: 0.7734 - val_loss: 0.5787 - val_acc: 0.6946 - val_auc: 0.7839\n", "Epoch 66: 2160000/2160000 [==============================] - 64s 29us/sample - loss: 0.5659 - acc: 0.7042 - auc: 0.7752 - val_loss: 0.5848 - val_acc: 0.6878 - val_auc: 0.7853\n", "Epoch 67: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5654 - acc: 0.7049 - auc: 0.7757 - val_loss: 0.5820 - val_acc: 0.6923 - val_auc: 0.7876\n", "Epoch 68: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5643 - acc: 0.7054 - auc: 0.7769 - val_loss: 0.5717 - val_acc: 0.6985 - val_auc: 0.7888\n", "Epoch 69: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5643 - acc: 0.7059 - auc: 0.7770 - val_loss: 0.5673 - val_acc: 0.7032 - val_auc: 0.7897\n", "Epoch 70: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5641 - acc: 0.7061 - auc: 0.7772 - val_loss: 0.5914 - val_acc: 0.6796 - val_auc: 0.7848\n", "Epoch 71: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5637 - acc: 0.7060 - auc: 0.7775 - val_loss: 0.5751 - val_acc: 0.6934 - val_auc: 0.7872\n", "Epoch 72: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5640 - acc: 0.7060 - auc: 0.7772 - val_loss: 0.5724 - val_acc: 0.7003 - val_auc: 0.7870\n", "Epoch 73: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5642 - acc: 0.7057 - auc: 0.7770 - val_loss: 0.5748 - val_acc: 0.6964 - val_auc: 0.7875\n", "Epoch 74: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5638 - acc: 0.7062 - auc: 0.7775 - val_loss: 0.5778 - val_acc: 0.6908 - val_auc: 0.7893\n", "Epoch 75: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5632 - acc: 0.7062 - auc: 0.7779 - val_loss: 0.5680 - val_acc: 0.7025 - val_auc: 0.7898\n", "Epoch 76: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5631 - acc: 0.7070 - auc: 0.7783 - val_loss: 0.5767 - val_acc: 0.6947 - val_auc: 0.7905\n", "Epoch 77: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5630 - acc: 0.7065 - auc: 0.7782 - val_loss: 0.5786 - val_acc: 0.6973 - val_auc: 0.7825\n", "Epoch 78: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5627 - acc: 0.7069 - auc: 0.7786 - val_loss: 0.5805 - val_acc: 0.6886 - val_auc: 0.7888\n", "Epoch 79: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5622 - acc: 0.7072 - auc: 0.7790 - val_loss: 0.5650 - val_acc: 0.7044 - val_auc: 0.7892\n", "Epoch 80: 2160000/2160000 [==============================] - 88s 41us/sample - loss: 0.5618 - acc: 0.7075 - auc: 0.7794 - val_loss: 0.5838 - val_acc: 0.6898 - val_auc: 0.7880\n", "Epoch 81: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5616 - acc: 0.7078 - auc: 0.7796 - val_loss: 0.5832 - val_acc: 0.6898 - val_auc: 0.7894\n", "Epoch 82: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5615 - acc: 0.7080 - auc: 0.7798 - val_loss: 0.5807 - val_acc: 0.6905 - val_auc: 0.7902\n", "Epoch 83: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5604 - acc: 0.7089 - auc: 0.7809 - val_loss: 0.5672 - val_acc: 0.7022 - val_auc: 0.7922\n", "Epoch 84: 2160000/2160000 [==============================] - 72s 34us/sample - loss: 0.5599 - acc: 0.7090 - auc: 0.7813 - val_loss: 0.5658 - val_acc: 0.7043 - val_auc: 0.7934\n", "Epoch 85: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5600 - acc: 0.7092 - auc: 0.7813 - val_loss: 0.5729 - val_acc: 0.6957 - val_auc: 0.7932\n", "Epoch 86: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5597 - acc: 0.7095 - auc: 0.7815 - val_loss: 0.5692 - val_acc: 0.7001 - val_auc: 0.7926\n", "Epoch 87: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5599 - acc: 0.7090 - auc: 0.7813 - val_loss: 0.5741 - val_acc: 0.6965 - val_auc: 0.7845\n", "Epoch 88: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5603 - acc: 0.7087 - auc: 0.7809 - val_loss: 0.5634 - val_acc: 0.7056 - val_auc: 0.7885\n", "Epoch 89: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5596 - acc: 0.7093 - auc: 0.7816 - val_loss: 0.5709 - val_acc: 0.7017 - val_auc: 0.7930\n", "Epoch 90: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5589 - acc: 0.7099 - auc: 0.7822 - val_loss: 0.5696 - val_acc: 0.7019 - val_auc: 0.7899\n", "Epoch 91: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5596 - acc: 0.7095 - auc: 0.7816 - val_loss: 0.5673 - val_acc: 0.7010 - val_auc: 0.7926\n", "Epoch 92: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5589 - acc: 0.7098 - auc: 0.7822 - val_loss: 0.5757 - val_acc: 0.6945 - val_auc: 0.7912\n", "Epoch 93: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5589 - acc: 0.7099 - auc: 0.7822 - val_loss: 0.5703 - val_acc: 0.6980 - val_auc: 0.7924\n", "Epoch 94: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5584 - acc: 0.7102 - auc: 0.7828 - val_loss: 0.5681 - val_acc: 0.7004 - val_auc: 0.7961\n", "Epoch 95: 2160000/2160000 [==============================] - 70s 33us/sample - loss: 0.5583 - acc: 0.7105 - auc: 0.7828 - val_loss: 0.5716 - val_acc: 0.7015 - val_auc: 0.7936\n", "Epoch 96: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5580 - acc: 0.7103 - auc: 0.7831 - val_loss: 0.5760 - val_acc: 0.6963 - val_auc: 0.7931\n", "Epoch 97: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5577 - acc: 0.7110 - auc: 0.7835 - val_loss: 0.5800 - val_acc: 0.6904 - val_auc: 0.7898\n", "Epoch 98: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5572 - acc: 0.7116 - auc: 0.7840 - val_loss: 0.5727 - val_acc: 0.6969 - val_auc: 0.7952\n", "Epoch 99: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5572 - acc: 0.7113 - auc: 0.7840 - val_loss: 0.5671 - val_acc: 0.7021 - val_auc: 0.7930\n", "Epoch 100: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5568 - acc: 0.7115 - auc: 0.7844 - val_loss: 0.5655 - val_acc: 0.7034 - val_auc: 0.7948\n", "Epoch 101: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5566 - acc: 0.7119 - auc: 0.7846 - val_loss: 0.5691 - val_acc: 0.6996 - val_auc: 0.7944\n", "Epoch 102: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5571 - acc: 0.7113 - auc: 0.7841 - val_loss: 0.5620 - val_acc: 0.7072 - val_auc: 0.7958\n", "Epoch 103: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5563 - acc: 0.7120 - auc: 0.7849 - val_loss: 0.5553 - val_acc: 0.7136 - val_auc: 0.7956\n", "Epoch 104: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5559 - acc: 0.7118 - auc: 0.7852 - val_loss: 0.5717 - val_acc: 0.6966 - val_auc: 0.7949\n", "Epoch 105: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5555 - acc: 0.7127 - auc: 0.7856 - val_loss: 0.5737 - val_acc: 0.6960 - val_auc: 0.7915\n", "Epoch 106: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5553 - acc: 0.7120 - auc: 0.7857 - val_loss: 0.5659 - val_acc: 0.7012 - val_auc: 0.7958\n", "Epoch 107: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5548 - acc: 0.7130 - auc: 0.7863 - val_loss: 0.5630 - val_acc: 0.7072 - val_auc: 0.7934\n", "Epoch 108: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5546 - acc: 0.7132 - auc: 0.7865 - val_loss: 0.5730 - val_acc: 0.6966 - val_auc: 0.7944\n", "Epoch 109: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5549 - acc: 0.7129 - auc: 0.7861 - val_loss: 0.5617 - val_acc: 0.7063 - val_auc: 0.7977\n", "Epoch 110: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5542 - acc: 0.7133 - auc: 0.7868 - val_loss: 0.5703 - val_acc: 0.6982 - val_auc: 0.7959\n", "Epoch 111: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5539 - acc: 0.7137 - auc: 0.7871 - val_loss: 0.5690 - val_acc: 0.7013 - val_auc: 0.7964\n", "Epoch 112: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5544 - acc: 0.7135 - auc: 0.7867 - val_loss: 0.5674 - val_acc: 0.7034 - val_auc: 0.7954\n", "Epoch 113: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5545 - acc: 0.7133 - auc: 0.7866 - val_loss: 0.5635 - val_acc: 0.7061 - val_auc: 0.7936\n", "Epoch 114: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5541 - acc: 0.7138 - auc: 0.7870 - val_loss: 0.5642 - val_acc: 0.7045 - val_auc: 0.7965\n", "Epoch 115: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5538 - acc: 0.7139 - auc: 0.7872 - val_loss: 0.5622 - val_acc: 0.7078 - val_auc: 0.7954\n", "Epoch 116: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5534 - acc: 0.7141 - auc: 0.7876 - val_loss: 0.5656 - val_acc: 0.7033 - val_auc: 0.7965\n", "Epoch 117: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5536 - acc: 0.7141 - auc: 0.7875 - val_loss: 0.5617 - val_acc: 0.7077 - val_auc: 0.7962\n", "Epoch 118: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5532 - acc: 0.7144 - auc: 0.7878 - val_loss: 0.5602 - val_acc: 0.7071 - val_auc: 0.7996\n", "Epoch 119: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5532 - acc: 0.7145 - auc: 0.7878 - val_loss: 0.5640 - val_acc: 0.7065 - val_auc: 0.7971\n", "Epoch 120: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5531 - acc: 0.7147 - auc: 0.7880 - val_loss: 0.5568 - val_acc: 0.7116 - val_auc: 0.7992\n", "Epoch 121: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5528 - acc: 0.7146 - auc: 0.7882 - val_loss: 0.5656 - val_acc: 0.7027 - val_auc: 0.7972\n", "Epoch 122: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5527 - acc: 0.7147 - auc: 0.7883 - val_loss: 0.5635 - val_acc: 0.7058 - val_auc: 0.7983\n", "Epoch 123: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5523 - acc: 0.7150 - auc: 0.7887 - val_loss: 0.5729 - val_acc: 0.6972 - val_auc: 0.7960\n", "Epoch 124: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5522 - acc: 0.7151 - auc: 0.7887 - val_loss: 0.5655 - val_acc: 0.7041 - val_auc: 0.7949\n", "Epoch 125: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5524 - acc: 0.7148 - auc: 0.7886 - val_loss: 0.5630 - val_acc: 0.7051 - val_auc: 0.7966\n", "Epoch 126: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5517 - acc: 0.7152 - auc: 0.7892 - val_loss: 0.5617 - val_acc: 0.7070 - val_auc: 0.7990\n", "Epoch 127: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5517 - acc: 0.7152 - auc: 0.7893 - val_loss: 0.5574 - val_acc: 0.7125 - val_auc: 0.7953\n", "Epoch 128: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5515 - acc: 0.7157 - auc: 0.7895 - val_loss: 0.5693 - val_acc: 0.6999 - val_auc: 0.7975\n", "Epoch 129: 2160000/2160000 [==============================] - 76s 35us/sample - loss: 0.5514 - acc: 0.7158 - auc: 0.7896 - val_loss: 0.5665 - val_acc: 0.7057 - val_auc: 0.7975\n", "Epoch 130: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5514 - acc: 0.7159 - auc: 0.7896 - val_loss: 0.5575 - val_acc: 0.7123 - val_auc: 0.7955\n", "Epoch 131: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5513 - acc: 0.7157 - auc: 0.7897 - val_loss: 0.5753 - val_acc: 0.6954 - val_auc: 0.7954\n", "Epoch 132: 2160000/2160000 [==============================] - 76s 35us/sample - loss: 0.5510 - acc: 0.7162 - auc: 0.7900 - val_loss: 0.5599 - val_acc: 0.7071 - val_auc: 0.7996\n", "Epoch 133: 2160000/2160000 [==============================] - 76s 35us/sample - loss: 0.5509 - acc: 0.7160 - auc: 0.7900 - val_loss: 0.5713 - val_acc: 0.6983 - val_auc: 0.7968\n", "Epoch 134: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5505 - acc: 0.7164 - auc: 0.7904 - val_loss: 0.5649 - val_acc: 0.7048 - val_auc: 0.7958\n", "Epoch 135: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5504 - acc: 0.7164 - auc: 0.7904 - val_loss: 0.5581 - val_acc: 0.7102 - val_auc: 0.7989\n", "Epoch 136: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5502 - acc: 0.7166 - auc: 0.7907 - val_loss: 0.5599 - val_acc: 0.7090 - val_auc: 0.7974\n", "Epoch 137: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5504 - acc: 0.7164 - auc: 0.7905 - val_loss: 0.5608 - val_acc: 0.7065 - val_auc: 0.7992\n", "Epoch 138: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5503 - acc: 0.7166 - auc: 0.7907 - val_loss: 0.5681 - val_acc: 0.7046 - val_auc: 0.7988\n", "Epoch 139: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5501 - acc: 0.7166 - auc: 0.7908 - val_loss: 0.5714 - val_acc: 0.6956 - val_auc: 0.7997\n", "Epoch 140: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5500 - acc: 0.7166 - auc: 0.7907 - val_loss: 0.5706 - val_acc: 0.6998 - val_auc: 0.7997\n", "Epoch 141: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5497 - acc: 0.7167 - auc: 0.7911 - val_loss: 0.5672 - val_acc: 0.7012 - val_auc: 0.7989\n", "Epoch 142: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5496 - acc: 0.7170 - auc: 0.7912 - val_loss: 0.5592 - val_acc: 0.7086 - val_auc: 0.7995\n", "Epoch 143: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5493 - acc: 0.7171 - auc: 0.7915 - val_loss: 0.5639 - val_acc: 0.7055 - val_auc: 0.7991\n", "Epoch 144: 2160000/2160000 [==============================] - 79s 36us/sample - loss: 0.5494 - acc: 0.7169 - auc: 0.7914 - val_loss: 0.5550 - val_acc: 0.7132 - val_auc: 0.8021\n", "Epoch 145: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5492 - acc: 0.7172 - auc: 0.7916 - val_loss: 0.5624 - val_acc: 0.7054 - val_auc: 0.8002\n", "Epoch 146: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5488 - acc: 0.7174 - auc: 0.7919 - val_loss: 0.5612 - val_acc: 0.7066 - val_auc: 0.8017\n", "Epoch 147: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5491 - acc: 0.7173 - auc: 0.7917 - val_loss: 0.5546 - val_acc: 0.7131 - val_auc: 0.8007\n", "Epoch 148: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5484 - acc: 0.7177 - auc: 0.7923 - val_loss: 0.5566 - val_acc: 0.7134 - val_auc: 0.7995\n", "Epoch 149: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5486 - acc: 0.7179 - auc: 0.7921 - val_loss: 0.5648 - val_acc: 0.7043 - val_auc: 0.7993\n", "Epoch 150: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5486 - acc: 0.7177 - auc: 0.7922 - val_loss: 0.5612 - val_acc: 0.7043 - val_auc: 0.8029\n", "Epoch 151: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5484 - acc: 0.7177 - auc: 0.7924 - val_loss: 0.5693 - val_acc: 0.7023 - val_auc: 0.7976\n", "Epoch 152: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5481 - acc: 0.7178 - auc: 0.7926 - val_loss: 0.5689 - val_acc: 0.7003 - val_auc: 0.7986\n", "Epoch 153: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5482 - acc: 0.7180 - auc: 0.7926 - val_loss: 0.5627 - val_acc: 0.7085 - val_auc: 0.7998\n", "Epoch 154: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5479 - acc: 0.7184 - auc: 0.7929 - val_loss: 0.5695 - val_acc: 0.7027 - val_auc: 0.7988\n", "Epoch 155: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5477 - acc: 0.7184 - auc: 0.7930 - val_loss: 0.5621 - val_acc: 0.7058 - val_auc: 0.8010\n", "Epoch 156: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5475 - acc: 0.7185 - auc: 0.7932 - val_loss: 0.5646 - val_acc: 0.7037 - val_auc: 0.7993\n", "Epoch 157: 2160000/2160000 [==============================] - 84s 39us/sample - loss: 0.5475 - acc: 0.7184 - auc: 0.7932 - val_loss: 0.5653 - val_acc: 0.7071 - val_auc: 0.7977\n", "Epoch 158: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5474 - acc: 0.7183 - auc: 0.7933 - val_loss: 0.5615 - val_acc: 0.7065 - val_auc: 0.8030\n", "Epoch 159: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5475 - acc: 0.7184 - auc: 0.7932 - val_loss: 0.5615 - val_acc: 0.7076 - val_auc: 0.8008\n", "Epoch 160: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5478 - acc: 0.7179 - auc: 0.7928 - val_loss: 0.5592 - val_acc: 0.7107 - val_auc: 0.7995\n", "Epoch 161: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5476 - acc: 0.7186 - auc: 0.7931 - val_loss: 0.5651 - val_acc: 0.7063 - val_auc: 0.7989\n", "Epoch 162: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5473 - acc: 0.7187 - auc: 0.7934 - val_loss: 0.5633 - val_acc: 0.7074 - val_auc: 0.7989\n", "Epoch 163: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5467 - acc: 0.7191 - auc: 0.7940 - val_loss: 0.5583 - val_acc: 0.7108 - val_auc: 0.8016\n", "Epoch 164: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5464 - acc: 0.7193 - auc: 0.7941 - val_loss: 0.5604 - val_acc: 0.7089 - val_auc: 0.8004\n", "Epoch 165: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5466 - acc: 0.7193 - auc: 0.7941 - val_loss: 0.5585 - val_acc: 0.7101 - val_auc: 0.7985\n", "Epoch 166: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5464 - acc: 0.7195 - auc: 0.7942 - val_loss: 0.5564 - val_acc: 0.7111 - val_auc: 0.8018\n", "Epoch 167: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5465 - acc: 0.7191 - auc: 0.7941 - val_loss: 0.5582 - val_acc: 0.7121 - val_auc: 0.8021\n", "Epoch 168: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5463 - acc: 0.7195 - auc: 0.7944 - val_loss: 0.5572 - val_acc: 0.7130 - val_auc: 0.8011\n", "Epoch 169: 2160000/2160000 [==============================] - 76s 35us/sample - loss: 0.5462 - acc: 0.7197 - auc: 0.7944 - val_loss: 0.5678 - val_acc: 0.7042 - val_auc: 0.7989\n", "Epoch 170: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5461 - acc: 0.7192 - auc: 0.7945 - val_loss: 0.5628 - val_acc: 0.7077 - val_auc: 0.8016\n", "Epoch 171: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5459 - acc: 0.7195 - auc: 0.7947 - val_loss: 0.5597 - val_acc: 0.7108 - val_auc: 0.7987\n", "Epoch 172: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5459 - acc: 0.7195 - auc: 0.7947 - val_loss: 0.5558 - val_acc: 0.7130 - val_auc: 0.8015\n", "Epoch 173: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5455 - acc: 0.7199 - auc: 0.7950 - val_loss: 0.5666 - val_acc: 0.7035 - val_auc: 0.8022\n", "Epoch 174: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5452 - acc: 0.7201 - auc: 0.7954 - val_loss: 0.5583 - val_acc: 0.7107 - val_auc: 0.8021\n", "Epoch 175: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5452 - acc: 0.7201 - auc: 0.7953 - val_loss: 0.5549 - val_acc: 0.7117 - val_auc: 0.8031\n", "Epoch 176: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5450 - acc: 0.7202 - auc: 0.7954 - val_loss: 0.5606 - val_acc: 0.7071 - val_auc: 0.8027\n", "Epoch 177: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5450 - acc: 0.7201 - auc: 0.7954 - val_loss: 0.5596 - val_acc: 0.7086 - val_auc: 0.8009\n", "Epoch 178: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5451 - acc: 0.7202 - auc: 0.7954 - val_loss: 0.5658 - val_acc: 0.7041 - val_auc: 0.8031\n", "Epoch 179: 2160000/2160000 [==============================] - 70s 33us/sample - loss: 0.5448 - acc: 0.7205 - auc: 0.7956 - val_loss: 0.5593 - val_acc: 0.7098 - val_auc: 0.8020\n", "Epoch 180: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5447 - acc: 0.7202 - auc: 0.7957 - val_loss: 0.5516 - val_acc: 0.7149 - val_auc: 0.8044\n", "Epoch 181: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5445 - acc: 0.7203 - auc: 0.7959 - val_loss: 0.5593 - val_acc: 0.7111 - val_auc: 0.7996\n", "Epoch 182: 2160000/2160000 [==============================] - 64s 29us/sample - loss: 0.5445 - acc: 0.7206 - auc: 0.7959 - val_loss: 0.5535 - val_acc: 0.7135 - val_auc: 0.8036\n", "Epoch 183: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5445 - acc: 0.7206 - auc: 0.7960 - val_loss: 0.5575 - val_acc: 0.7097 - val_auc: 0.8024\n", "Epoch 184: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5442 - acc: 0.7208 - auc: 0.7962 - val_loss: 0.5574 - val_acc: 0.7122 - val_auc: 0.8026\n", "Epoch 185: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5442 - acc: 0.7209 - auc: 0.7962 - val_loss: 0.5553 - val_acc: 0.7132 - val_auc: 0.8033\n", "Epoch 186: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5441 - acc: 0.7207 - auc: 0.7963 - val_loss: 0.5543 - val_acc: 0.7140 - val_auc: 0.8020\n", "Epoch 187: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5438 - acc: 0.7210 - auc: 0.7966 - val_loss: 0.5701 - val_acc: 0.7010 - val_auc: 0.8024\n", "Epoch 188: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5441 - acc: 0.7208 - auc: 0.7963 - val_loss: 0.5577 - val_acc: 0.7103 - val_auc: 0.8026\n", "Epoch 189: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5439 - acc: 0.7210 - auc: 0.7965 - val_loss: 0.5621 - val_acc: 0.7070 - val_auc: 0.8017\n", "Epoch 190: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5437 - acc: 0.7209 - auc: 0.7966 - val_loss: 0.5586 - val_acc: 0.7109 - val_auc: 0.8038\n", "Epoch 191: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5437 - acc: 0.7210 - auc: 0.7966 - val_loss: 0.5564 - val_acc: 0.7125 - val_auc: 0.8040\n", "Epoch 192: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5435 - acc: 0.7216 - auc: 0.7970 - val_loss: 0.5601 - val_acc: 0.7093 - val_auc: 0.8034\n", "Epoch 193: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.5436 - acc: 0.7210 - auc: 0.7968 - val_loss: 0.5594 - val_acc: 0.7096 - val_auc: 0.8043\n", "Epoch 194: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.5434 - acc: 0.7216 - auc: 0.7970 - val_loss: 0.5592 - val_acc: 0.7092 - val_auc: 0.8033\n", "Epoch 195: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5433 - acc: 0.7215 - auc: 0.7970 - val_loss: 0.5542 - val_acc: 0.7125 - val_auc: 0.8059\n", "Epoch 196: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5433 - acc: 0.7213 - auc: 0.7971 - val_loss: 0.5583 - val_acc: 0.7093 - val_auc: 0.8035\n", "Epoch 197: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.5432 - acc: 0.7217 - auc: 0.7972 - val_loss: 0.5535 - val_acc: 0.7140 - val_auc: 0.8040\n", "Epoch 198: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5433 - acc: 0.7215 - auc: 0.7971 - val_loss: 0.5515 - val_acc: 0.7146 - val_auc: 0.8038\n", "Epoch 199: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.5430 - acc: 0.7217 - auc: 0.7973 - val_loss: 0.5614 - val_acc: 0.7072 - val_auc: 0.8028\n", "Epoch 200: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5430 - acc: 0.7217 - auc: 0.7974 - val_loss: 0.5584 - val_acc: 0.7077 - val_auc: 0.8030\n" ] } ], "source": [ "print_logs('keras_model.log')" ] }, { "cell_type": "markdown", "id": "executive-pontiac", "metadata": {}, "source": [ "## RELU with all hidden layers with Dropout 0.4" ] }, { "cell_type": "code", "execution_count": 31, "id": "brazilian-reminder", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.6833 - acc: 0.5522 - auc: 0.5657 - val_loss: 0.6479 - val_acc: 0.6227 - val_auc: 0.6637\n", "Epoch 2: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.6496 - acc: 0.6173 - auc: 0.6584 - val_loss: 0.6307 - val_acc: 0.6418 - val_auc: 0.6931\n", "Epoch 3: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.6428 - acc: 0.6251 - auc: 0.6710 - val_loss: 0.6256 - val_acc: 0.6462 - val_auc: 0.7055\n", "Epoch 4: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.6413 - acc: 0.6275 - auc: 0.6739 - val_loss: 0.6295 - val_acc: 0.6455 - val_auc: 0.7017\n", "Epoch 5: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.6403 - acc: 0.6297 - auc: 0.6767 - val_loss: 0.6312 - val_acc: 0.6412 - val_auc: 0.7024\n", "Epoch 6: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.6359 - acc: 0.6357 - auc: 0.6836 - val_loss: 0.6216 - val_acc: 0.6532 - val_auc: 0.7083\n", "Epoch 7: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.6341 - acc: 0.6378 - auc: 0.6866 - val_loss: 0.6168 - val_acc: 0.6546 - val_auc: 0.7217\n", "Epoch 8: 2160000/2160000 [==============================] - 77s 35us/sample - loss: 0.6308 - acc: 0.6422 - auc: 0.6927 - val_loss: 0.6144 - val_acc: 0.6576 - val_auc: 0.7249\n", "Epoch 9: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.6319 - acc: 0.6410 - auc: 0.6906 - val_loss: 0.6139 - val_acc: 0.6640 - val_auc: 0.7237\n", "Epoch 10: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.6284 - acc: 0.6454 - auc: 0.6966 - val_loss: 0.6247 - val_acc: 0.6513 - val_auc: 0.7129\n", "Epoch 11: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.6283 - acc: 0.6450 - auc: 0.6965 - val_loss: 0.6123 - val_acc: 0.6643 - val_auc: 0.7333\n", "Epoch 12: 2160000/2160000 [==============================] - 64s 29us/sample - loss: 0.6276 - acc: 0.6444 - auc: 0.6970 - val_loss: 0.6327 - val_acc: 0.6385 - val_auc: 0.7214\n", "Epoch 13: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.6236 - acc: 0.6496 - auc: 0.7035 - val_loss: 0.6083 - val_acc: 0.6703 - val_auc: 0.7336\n", "Epoch 14: 2160000/2160000 [==============================] - 82s 38us/sample - loss: 0.6226 - acc: 0.6497 - auc: 0.7044 - val_loss: 0.6186 - val_acc: 0.6585 - val_auc: 0.7181\n", "Epoch 15: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.6229 - acc: 0.6489 - auc: 0.7035 - val_loss: 0.6090 - val_acc: 0.6686 - val_auc: 0.7360\n", "Epoch 16: 2160000/2160000 [==============================] - 83s 38us/sample - loss: 0.6191 - acc: 0.6540 - auc: 0.7099 - val_loss: 0.6095 - val_acc: 0.6644 - val_auc: 0.7335\n", "Epoch 17: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.6174 - acc: 0.6562 - auc: 0.7123 - val_loss: 0.6094 - val_acc: 0.6708 - val_auc: 0.7375\n", "Epoch 18: 2160000/2160000 [==============================] - 60s 28us/sample - loss: 0.6134 - acc: 0.6604 - auc: 0.7184 - val_loss: 0.5988 - val_acc: 0.6820 - val_auc: 0.7462\n", "Epoch 19: 2160000/2160000 [==============================] - 60s 28us/sample - loss: 0.6127 - acc: 0.6607 - auc: 0.7194 - val_loss: 0.6076 - val_acc: 0.6689 - val_auc: 0.7457\n", "Epoch 20: 2160000/2160000 [==============================] - 60s 28us/sample - loss: 0.6106 - acc: 0.6627 - auc: 0.7222 - val_loss: 0.6012 - val_acc: 0.6796 - val_auc: 0.7474\n", "Epoch 21: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.6069 - acc: 0.6669 - auc: 0.7274 - val_loss: 0.5977 - val_acc: 0.6838 - val_auc: 0.7542\n", "Epoch 22: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.6053 - acc: 0.6681 - auc: 0.7294 - val_loss: 0.5963 - val_acc: 0.6852 - val_auc: 0.7519\n", "Epoch 23: 2160000/2160000 [==============================] - 60s 28us/sample - loss: 0.6042 - acc: 0.6694 - auc: 0.7309 - val_loss: 0.5977 - val_acc: 0.6785 - val_auc: 0.7551\n", "Epoch 24: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.6031 - acc: 0.6704 - auc: 0.7324 - val_loss: 0.6035 - val_acc: 0.6720 - val_auc: 0.7553\n", "Epoch 25: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.5999 - acc: 0.6743 - auc: 0.7368 - val_loss: 0.6139 - val_acc: 0.6546 - val_auc: 0.7598\n", "Epoch 26: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5968 - acc: 0.6770 - auc: 0.7407 - val_loss: 0.5885 - val_acc: 0.6892 - val_auc: 0.7624\n", "Epoch 27: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5950 - acc: 0.6786 - auc: 0.7429 - val_loss: 0.5988 - val_acc: 0.6739 - val_auc: 0.7602\n", "Epoch 28: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5944 - acc: 0.6797 - auc: 0.7438 - val_loss: 0.6002 - val_acc: 0.6701 - val_auc: 0.7662\n", "Epoch 29: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5940 - acc: 0.6801 - auc: 0.7441 - val_loss: 0.6058 - val_acc: 0.6618 - val_auc: 0.7653\n", "Epoch 30: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.5923 - acc: 0.6815 - auc: 0.7462 - val_loss: 0.5964 - val_acc: 0.6794 - val_auc: 0.7548\n", "Epoch 31: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5911 - acc: 0.6821 - auc: 0.7476 - val_loss: 0.5904 - val_acc: 0.6840 - val_auc: 0.7687\n", "Epoch 32: 2160000/2160000 [==============================] - 61s 28us/sample - loss: 0.5910 - acc: 0.6826 - auc: 0.7476 - val_loss: 0.6013 - val_acc: 0.6702 - val_auc: 0.7677\n", "Epoch 33: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5912 - acc: 0.6822 - auc: 0.7473 - val_loss: 0.5927 - val_acc: 0.6821 - val_auc: 0.7641\n", "Epoch 34: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5897 - acc: 0.6837 - auc: 0.7491 - val_loss: 0.5936 - val_acc: 0.6805 - val_auc: 0.7648\n", "Epoch 35: 2160000/2160000 [==============================] - 66s 31us/sample - loss: 0.5877 - acc: 0.6853 - auc: 0.7514 - val_loss: 0.5888 - val_acc: 0.6879 - val_auc: 0.7700\n", "Epoch 36: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5881 - acc: 0.6852 - auc: 0.7510 - val_loss: 0.5862 - val_acc: 0.6854 - val_auc: 0.7712\n", "Epoch 37: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5890 - acc: 0.6845 - auc: 0.7500 - val_loss: 0.5945 - val_acc: 0.6811 - val_auc: 0.7706\n", "Epoch 38: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5852 - acc: 0.6875 - auc: 0.7544 - val_loss: 0.5839 - val_acc: 0.6902 - val_auc: 0.7721\n", "Epoch 39: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5847 - acc: 0.6882 - auc: 0.7549 - val_loss: 0.5969 - val_acc: 0.6741 - val_auc: 0.7623\n", "Epoch 40: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5842 - acc: 0.6883 - auc: 0.7554 - val_loss: 0.5856 - val_acc: 0.6890 - val_auc: 0.7707\n", "Epoch 41: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5812 - acc: 0.6918 - auc: 0.7591 - val_loss: 0.5778 - val_acc: 0.6964 - val_auc: 0.7713\n", "Epoch 42: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5816 - acc: 0.6913 - auc: 0.7586 - val_loss: 0.5891 - val_acc: 0.6824 - val_auc: 0.7741\n", "Epoch 43: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5804 - acc: 0.6918 - auc: 0.7598 - val_loss: 0.5895 - val_acc: 0.6848 - val_auc: 0.7733\n", "Epoch 44: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5793 - acc: 0.6932 - auc: 0.7611 - val_loss: 0.5788 - val_acc: 0.6942 - val_auc: 0.7745\n", "Epoch 45: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5791 - acc: 0.6933 - auc: 0.7612 - val_loss: 0.5805 - val_acc: 0.6920 - val_auc: 0.7726\n", "Epoch 46: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5781 - acc: 0.6942 - auc: 0.7624 - val_loss: 0.5779 - val_acc: 0.6933 - val_auc: 0.7771\n", "Epoch 47: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5772 - acc: 0.6949 - auc: 0.7634 - val_loss: 0.5853 - val_acc: 0.6863 - val_auc: 0.7729\n", "Epoch 48: 2160000/2160000 [==============================] - 70s 33us/sample - loss: 0.5764 - acc: 0.6955 - auc: 0.7642 - val_loss: 0.5893 - val_acc: 0.6839 - val_auc: 0.7695\n", "Epoch 49: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5761 - acc: 0.6957 - auc: 0.7645 - val_loss: 0.5753 - val_acc: 0.6976 - val_auc: 0.7772\n", "Epoch 50: 2160000/2160000 [==============================] - 70s 33us/sample - loss: 0.5750 - acc: 0.6969 - auc: 0.7657 - val_loss: 0.5764 - val_acc: 0.6954 - val_auc: 0.7759\n", "Epoch 51: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5741 - acc: 0.6977 - auc: 0.7667 - val_loss: 0.5839 - val_acc: 0.6852 - val_auc: 0.7791\n", "Epoch 52: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5746 - acc: 0.6971 - auc: 0.7661 - val_loss: 0.5734 - val_acc: 0.6978 - val_auc: 0.7828\n", "Epoch 53: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5729 - acc: 0.6987 - auc: 0.7681 - val_loss: 0.5733 - val_acc: 0.6976 - val_auc: 0.7788\n", "Epoch 54: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5729 - acc: 0.6987 - auc: 0.7681 - val_loss: 0.5748 - val_acc: 0.6953 - val_auc: 0.7810\n", "Epoch 55: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5723 - acc: 0.6990 - auc: 0.7687 - val_loss: 0.5761 - val_acc: 0.6923 - val_auc: 0.7841\n", "Epoch 56: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5722 - acc: 0.6995 - auc: 0.7688 - val_loss: 0.5823 - val_acc: 0.6896 - val_auc: 0.7761\n", "Epoch 57: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5715 - acc: 0.6999 - auc: 0.7695 - val_loss: 0.5814 - val_acc: 0.6902 - val_auc: 0.7790\n", "Epoch 58: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5711 - acc: 0.7002 - auc: 0.7700 - val_loss: 0.5788 - val_acc: 0.6903 - val_auc: 0.7833\n", "Epoch 59: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5704 - acc: 0.7008 - auc: 0.7707 - val_loss: 0.5858 - val_acc: 0.6859 - val_auc: 0.7781\n", "Epoch 60: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5701 - acc: 0.7011 - auc: 0.7709 - val_loss: 0.5848 - val_acc: 0.6892 - val_auc: 0.7809\n", "Epoch 61: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5695 - acc: 0.7016 - auc: 0.7716 - val_loss: 0.5708 - val_acc: 0.7003 - val_auc: 0.7882\n", "Epoch 62: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5691 - acc: 0.7016 - auc: 0.7720 - val_loss: 0.5791 - val_acc: 0.6914 - val_auc: 0.7820\n", "Epoch 63: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5687 - acc: 0.7022 - auc: 0.7724 - val_loss: 0.5701 - val_acc: 0.7027 - val_auc: 0.7816\n", "Epoch 64: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5681 - acc: 0.7029 - auc: 0.7730 - val_loss: 0.5826 - val_acc: 0.6885 - val_auc: 0.7825\n", "Epoch 65: 2160000/2160000 [==============================] - 88s 41us/sample - loss: 0.5675 - acc: 0.7031 - auc: 0.7737 - val_loss: 0.5809 - val_acc: 0.6917 - val_auc: 0.7846\n", "Epoch 66: 2160000/2160000 [==============================] - 94s 43us/sample - loss: 0.5675 - acc: 0.7032 - auc: 0.7737 - val_loss: 0.5994 - val_acc: 0.6777 - val_auc: 0.7785\n", "Epoch 67: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5675 - acc: 0.7031 - auc: 0.7737 - val_loss: 0.5758 - val_acc: 0.6929 - val_auc: 0.7881\n", "Epoch 68: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5668 - acc: 0.7039 - auc: 0.7744 - val_loss: 0.5704 - val_acc: 0.7001 - val_auc: 0.7867\n", "Epoch 69: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5662 - acc: 0.7043 - auc: 0.7750 - val_loss: 0.5687 - val_acc: 0.7005 - val_auc: 0.7886\n", "Epoch 70: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5653 - acc: 0.7050 - auc: 0.7759 - val_loss: 0.5799 - val_acc: 0.6908 - val_auc: 0.7849\n", "Epoch 71: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5661 - acc: 0.7044 - auc: 0.7750 - val_loss: 0.5770 - val_acc: 0.6937 - val_auc: 0.7814\n", "Epoch 72: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5657 - acc: 0.7047 - auc: 0.7755 - val_loss: 0.5763 - val_acc: 0.6945 - val_auc: 0.7827\n", "Epoch 73: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5646 - acc: 0.7055 - auc: 0.7765 - val_loss: 0.5730 - val_acc: 0.6953 - val_auc: 0.7865\n", "Epoch 74: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5648 - acc: 0.7052 - auc: 0.7764 - val_loss: 0.5666 - val_acc: 0.7050 - val_auc: 0.7867\n", "Epoch 75: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5646 - acc: 0.7055 - auc: 0.7766 - val_loss: 0.5807 - val_acc: 0.6879 - val_auc: 0.7875\n", "Epoch 76: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5632 - acc: 0.7064 - auc: 0.7780 - val_loss: 0.5689 - val_acc: 0.6987 - val_auc: 0.7905\n", "Epoch 77: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5637 - acc: 0.7061 - auc: 0.7775 - val_loss: 0.5666 - val_acc: 0.7020 - val_auc: 0.7899\n", "Epoch 78: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5632 - acc: 0.7066 - auc: 0.7779 - val_loss: 0.5775 - val_acc: 0.6926 - val_auc: 0.7857\n", "Epoch 79: 2160000/2160000 [==============================] - 64s 29us/sample - loss: 0.5630 - acc: 0.7067 - auc: 0.7781 - val_loss: 0.5667 - val_acc: 0.7034 - val_auc: 0.7900\n", "Epoch 80: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5627 - acc: 0.7066 - auc: 0.7785 - val_loss: 0.5697 - val_acc: 0.7009 - val_auc: 0.7868\n", "Epoch 81: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5626 - acc: 0.7070 - auc: 0.7785 - val_loss: 0.5681 - val_acc: 0.7005 - val_auc: 0.7890\n", "Epoch 82: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5625 - acc: 0.7068 - auc: 0.7786 - val_loss: 0.5764 - val_acc: 0.6956 - val_auc: 0.7869\n", "Epoch 83: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5618 - acc: 0.7079 - auc: 0.7794 - val_loss: 0.5669 - val_acc: 0.7033 - val_auc: 0.7906\n", "Epoch 84: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5613 - acc: 0.7080 - auc: 0.7799 - val_loss: 0.5736 - val_acc: 0.6955 - val_auc: 0.7896\n", "Epoch 85: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5610 - acc: 0.7083 - auc: 0.7802 - val_loss: 0.5658 - val_acc: 0.7033 - val_auc: 0.7905\n", "Epoch 86: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5605 - acc: 0.7084 - auc: 0.7807 - val_loss: 0.5710 - val_acc: 0.6993 - val_auc: 0.7858\n", "Epoch 87: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5602 - acc: 0.7087 - auc: 0.7810 - val_loss: 0.5772 - val_acc: 0.6932 - val_auc: 0.7910\n", "Epoch 88: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5595 - acc: 0.7095 - auc: 0.7817 - val_loss: 0.5777 - val_acc: 0.6944 - val_auc: 0.7864\n", "Epoch 89: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5596 - acc: 0.7093 - auc: 0.7816 - val_loss: 0.5702 - val_acc: 0.6991 - val_auc: 0.7908\n", "Epoch 90: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5594 - acc: 0.7093 - auc: 0.7818 - val_loss: 0.5713 - val_acc: 0.6966 - val_auc: 0.7942\n", "Epoch 91: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5589 - acc: 0.7099 - auc: 0.7822 - val_loss: 0.5750 - val_acc: 0.6934 - val_auc: 0.7897\n", "Epoch 92: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5590 - acc: 0.7097 - auc: 0.7822 - val_loss: 0.5622 - val_acc: 0.7046 - val_auc: 0.7942\n", "Epoch 93: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5584 - acc: 0.7100 - auc: 0.7827 - val_loss: 0.5743 - val_acc: 0.6938 - val_auc: 0.7874\n", "Epoch 94: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5595 - acc: 0.7091 - auc: 0.7816 - val_loss: 0.5741 - val_acc: 0.6944 - val_auc: 0.7912\n", "Epoch 95: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5588 - acc: 0.7098 - auc: 0.7823 - val_loss: 0.5786 - val_acc: 0.6920 - val_auc: 0.7906\n", "Epoch 96: 2160000/2160000 [==============================] - 66s 31us/sample - loss: 0.5582 - acc: 0.7103 - auc: 0.7830 - val_loss: 0.5653 - val_acc: 0.7036 - val_auc: 0.7921\n", "Epoch 97: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5580 - acc: 0.7104 - auc: 0.7831 - val_loss: 0.5709 - val_acc: 0.6968 - val_auc: 0.7934\n", "Epoch 98: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5572 - acc: 0.7109 - auc: 0.7839 - val_loss: 0.5668 - val_acc: 0.7014 - val_auc: 0.7931\n", "Epoch 99: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5573 - acc: 0.7109 - auc: 0.7838 - val_loss: 0.5680 - val_acc: 0.7006 - val_auc: 0.7946\n", "Epoch 100: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5577 - acc: 0.7106 - auc: 0.7835 - val_loss: 0.5624 - val_acc: 0.7039 - val_auc: 0.7939\n", "Epoch 101: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5567 - acc: 0.7115 - auc: 0.7844 - val_loss: 0.5613 - val_acc: 0.7062 - val_auc: 0.7966\n", "Epoch 102: 2160000/2160000 [==============================] - 64s 29us/sample - loss: 0.5567 - acc: 0.7115 - auc: 0.7844 - val_loss: 0.5671 - val_acc: 0.7002 - val_auc: 0.7935\n", "Epoch 103: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5564 - acc: 0.7118 - auc: 0.7847 - val_loss: 0.5663 - val_acc: 0.6999 - val_auc: 0.7926\n", "Epoch 104: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5570 - acc: 0.7114 - auc: 0.7842 - val_loss: 0.5586 - val_acc: 0.7107 - val_auc: 0.7970\n", "Epoch 105: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5561 - acc: 0.7117 - auc: 0.7849 - val_loss: 0.5675 - val_acc: 0.7015 - val_auc: 0.7925\n", "Epoch 106: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5567 - acc: 0.7114 - auc: 0.7845 - val_loss: 0.5618 - val_acc: 0.7076 - val_auc: 0.7944\n", "Epoch 107: 2160000/2160000 [==============================] - 62s 29us/sample - loss: 0.5555 - acc: 0.7124 - auc: 0.7856 - val_loss: 0.5616 - val_acc: 0.7058 - val_auc: 0.7944\n", "Epoch 108: 2160000/2160000 [==============================] - 63s 29us/sample - loss: 0.5557 - acc: 0.7120 - auc: 0.7854 - val_loss: 0.5635 - val_acc: 0.7035 - val_auc: 0.7962\n", "Epoch 109: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5556 - acc: 0.7123 - auc: 0.7855 - val_loss: 0.5683 - val_acc: 0.7000 - val_auc: 0.7963\n", "Epoch 110: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5557 - acc: 0.7122 - auc: 0.7854 - val_loss: 0.5700 - val_acc: 0.6956 - val_auc: 0.7964\n", "Epoch 111: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5551 - acc: 0.7126 - auc: 0.7858 - val_loss: 0.5648 - val_acc: 0.7043 - val_auc: 0.7925\n", "Epoch 112: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5548 - acc: 0.7128 - auc: 0.7862 - val_loss: 0.5652 - val_acc: 0.7026 - val_auc: 0.7973\n", "Epoch 113: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5550 - acc: 0.7130 - auc: 0.7861 - val_loss: 0.5687 - val_acc: 0.6989 - val_auc: 0.7942\n", "Epoch 114: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5554 - acc: 0.7124 - auc: 0.7856 - val_loss: 0.5674 - val_acc: 0.6999 - val_auc: 0.7950\n", "Epoch 115: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5545 - acc: 0.7133 - auc: 0.7866 - val_loss: 0.5630 - val_acc: 0.7038 - val_auc: 0.7954\n", "Epoch 116: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5538 - acc: 0.7139 - auc: 0.7873 - val_loss: 0.5627 - val_acc: 0.7074 - val_auc: 0.7946\n", "Epoch 117: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5537 - acc: 0.7137 - auc: 0.7874 - val_loss: 0.5617 - val_acc: 0.7070 - val_auc: 0.7951\n", "Epoch 118: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5549 - acc: 0.7127 - auc: 0.7861 - val_loss: 0.5668 - val_acc: 0.7030 - val_auc: 0.7921\n", "Epoch 119: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5541 - acc: 0.7135 - auc: 0.7869 - val_loss: 0.5668 - val_acc: 0.7014 - val_auc: 0.7972\n", "Epoch 120: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5538 - acc: 0.7135 - auc: 0.7871 - val_loss: 0.5761 - val_acc: 0.6890 - val_auc: 0.7955\n", "Epoch 121: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5534 - acc: 0.7139 - auc: 0.7875 - val_loss: 0.5682 - val_acc: 0.7000 - val_auc: 0.7971\n", "Epoch 122: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5533 - acc: 0.7144 - auc: 0.7878 - val_loss: 0.5679 - val_acc: 0.6989 - val_auc: 0.7981\n", "Epoch 123: 2160000/2160000 [==============================] - 84s 39us/sample - loss: 0.5530 - acc: 0.7144 - auc: 0.7881 - val_loss: 0.5732 - val_acc: 0.6970 - val_auc: 0.7919\n", "Epoch 124: 2160000/2160000 [==============================] - 82s 38us/sample - loss: 0.5528 - acc: 0.7142 - auc: 0.7882 - val_loss: 0.5804 - val_acc: 0.6910 - val_auc: 0.7930\n", "Epoch 125: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5529 - acc: 0.7146 - auc: 0.7881 - val_loss: 0.5640 - val_acc: 0.7020 - val_auc: 0.7969\n", "Epoch 126: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5532 - acc: 0.7143 - auc: 0.7878 - val_loss: 0.5677 - val_acc: 0.7000 - val_auc: 0.7953\n", "Epoch 127: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5524 - acc: 0.7149 - auc: 0.7885 - val_loss: 0.5634 - val_acc: 0.7024 - val_auc: 0.7979\n", "Epoch 128: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5523 - acc: 0.7146 - auc: 0.7886 - val_loss: 0.5779 - val_acc: 0.6918 - val_auc: 0.7957\n", "Epoch 129: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5523 - acc: 0.7150 - auc: 0.7887 - val_loss: 0.5691 - val_acc: 0.6977 - val_auc: 0.7971\n", "Epoch 130: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5518 - acc: 0.7153 - auc: 0.7892 - val_loss: 0.5633 - val_acc: 0.7034 - val_auc: 0.7971\n", "Epoch 131: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5523 - acc: 0.7150 - auc: 0.7886 - val_loss: 0.5683 - val_acc: 0.6967 - val_auc: 0.7966\n", "Epoch 132: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5516 - acc: 0.7155 - auc: 0.7893 - val_loss: 0.5626 - val_acc: 0.7060 - val_auc: 0.7984\n", "Epoch 133: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5514 - acc: 0.7155 - auc: 0.7894 - val_loss: 0.5631 - val_acc: 0.7043 - val_auc: 0.8009\n", "Epoch 134: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5515 - acc: 0.7156 - auc: 0.7893 - val_loss: 0.5627 - val_acc: 0.7048 - val_auc: 0.7985\n", "Epoch 135: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5515 - acc: 0.7153 - auc: 0.7894 - val_loss: 0.5643 - val_acc: 0.7046 - val_auc: 0.7964\n", "Epoch 136: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5518 - acc: 0.7153 - auc: 0.7892 - val_loss: 0.5646 - val_acc: 0.7032 - val_auc: 0.7967\n", "Epoch 137: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5517 - acc: 0.7152 - auc: 0.7892 - val_loss: 0.5581 - val_acc: 0.7092 - val_auc: 0.8001\n", "Epoch 138: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5507 - acc: 0.7158 - auc: 0.7902 - val_loss: 0.5632 - val_acc: 0.7051 - val_auc: 0.7963\n", "Epoch 139: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5516 - acc: 0.7153 - auc: 0.7893 - val_loss: 0.5644 - val_acc: 0.7055 - val_auc: 0.7948\n", "Epoch 140: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5509 - acc: 0.7161 - auc: 0.7900 - val_loss: 0.5619 - val_acc: 0.7066 - val_auc: 0.7990\n", "Epoch 141: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5506 - acc: 0.7162 - auc: 0.7903 - val_loss: 0.5720 - val_acc: 0.6926 - val_auc: 0.7989\n", "Epoch 142: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5500 - acc: 0.7167 - auc: 0.7909 - val_loss: 0.5670 - val_acc: 0.7019 - val_auc: 0.7987\n", "Epoch 143: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5502 - acc: 0.7167 - auc: 0.7906 - val_loss: 0.5530 - val_acc: 0.7125 - val_auc: 0.8017\n", "Epoch 144: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5498 - acc: 0.7166 - auc: 0.7910 - val_loss: 0.5754 - val_acc: 0.6940 - val_auc: 0.7963\n", "Epoch 145: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5503 - acc: 0.7163 - auc: 0.7905 - val_loss: 0.5638 - val_acc: 0.7026 - val_auc: 0.8008\n", "Epoch 146: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5499 - acc: 0.7168 - auc: 0.7909 - val_loss: 0.5698 - val_acc: 0.6993 - val_auc: 0.7931\n", "Epoch 147: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5496 - acc: 0.7167 - auc: 0.7912 - val_loss: 0.5644 - val_acc: 0.7019 - val_auc: 0.7978\n", "Epoch 148: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5496 - acc: 0.7169 - auc: 0.7912 - val_loss: 0.5647 - val_acc: 0.7008 - val_auc: 0.8038\n", "Epoch 149: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5496 - acc: 0.7170 - auc: 0.7912 - val_loss: 0.5636 - val_acc: 0.7062 - val_auc: 0.7961\n", "Epoch 150: 2160000/2160000 [==============================] - 70s 33us/sample - loss: 0.5494 - acc: 0.7169 - auc: 0.7914 - val_loss: 0.5548 - val_acc: 0.7117 - val_auc: 0.7991\n", "Epoch 151: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5493 - acc: 0.7169 - auc: 0.7915 - val_loss: 0.5627 - val_acc: 0.7028 - val_auc: 0.8009\n", "Epoch 152: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5486 - acc: 0.7173 - auc: 0.7920 - val_loss: 0.5666 - val_acc: 0.7028 - val_auc: 0.8022\n", "Epoch 153: 2160000/2160000 [==============================] - 83s 39us/sample - loss: 0.5487 - acc: 0.7177 - auc: 0.7921 - val_loss: 0.5583 - val_acc: 0.7089 - val_auc: 0.8017\n", "Epoch 154: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5488 - acc: 0.7174 - auc: 0.7921 - val_loss: 0.5589 - val_acc: 0.7082 - val_auc: 0.8003\n", "Epoch 155: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5478 - acc: 0.7184 - auc: 0.7929 - val_loss: 0.5587 - val_acc: 0.7072 - val_auc: 0.8022\n", "Epoch 156: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5479 - acc: 0.7184 - auc: 0.7928 - val_loss: 0.5680 - val_acc: 0.7020 - val_auc: 0.8001\n", "Epoch 157: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5488 - acc: 0.7176 - auc: 0.7920 - val_loss: 0.5609 - val_acc: 0.7056 - val_auc: 0.8010\n", "Epoch 158: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5484 - acc: 0.7179 - auc: 0.7923 - val_loss: 0.5727 - val_acc: 0.6974 - val_auc: 0.7966\n", "Epoch 159: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5482 - acc: 0.7181 - auc: 0.7926 - val_loss: 0.5739 - val_acc: 0.6967 - val_auc: 0.7947\n", "Epoch 160: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5495 - acc: 0.7168 - auc: 0.7913 - val_loss: 0.5664 - val_acc: 0.7038 - val_auc: 0.7957\n", "Epoch 161: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5484 - acc: 0.7177 - auc: 0.7923 - val_loss: 0.5640 - val_acc: 0.7041 - val_auc: 0.7957\n", "Epoch 162: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5486 - acc: 0.7173 - auc: 0.7921 - val_loss: 0.5661 - val_acc: 0.6998 - val_auc: 0.8022\n", "Epoch 163: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5476 - acc: 0.7182 - auc: 0.7930 - val_loss: 0.5641 - val_acc: 0.7019 - val_auc: 0.7990\n", "Epoch 164: 2160000/2160000 [==============================] - 89s 41us/sample - loss: 0.5476 - acc: 0.7187 - auc: 0.7931 - val_loss: 0.5731 - val_acc: 0.6949 - val_auc: 0.8001\n", "Epoch 165: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5474 - acc: 0.7185 - auc: 0.7933 - val_loss: 0.5689 - val_acc: 0.6980 - val_auc: 0.8018\n", "Epoch 166: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5474 - acc: 0.7186 - auc: 0.7933 - val_loss: 0.5568 - val_acc: 0.7097 - val_auc: 0.8013\n", "Epoch 167: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5476 - acc: 0.7186 - auc: 0.7931 - val_loss: 0.5541 - val_acc: 0.7129 - val_auc: 0.8026\n", "Epoch 168: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5471 - acc: 0.7189 - auc: 0.7936 - val_loss: 0.5566 - val_acc: 0.7098 - val_auc: 0.8000\n", "Epoch 169: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5474 - acc: 0.7184 - auc: 0.7933 - val_loss: 0.5614 - val_acc: 0.7055 - val_auc: 0.8002\n", "Epoch 170: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5466 - acc: 0.7194 - auc: 0.7940 - val_loss: 0.5573 - val_acc: 0.7116 - val_auc: 0.7998\n", "Epoch 171: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5470 - acc: 0.7187 - auc: 0.7936 - val_loss: 0.5584 - val_acc: 0.7080 - val_auc: 0.8007\n", "Epoch 172: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5460 - acc: 0.7195 - auc: 0.7945 - val_loss: 0.5747 - val_acc: 0.6916 - val_auc: 0.8005\n", "Epoch 173: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5464 - acc: 0.7193 - auc: 0.7942 - val_loss: 0.5640 - val_acc: 0.7045 - val_auc: 0.8004\n", "Epoch 174: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5465 - acc: 0.7190 - auc: 0.7940 - val_loss: 0.5533 - val_acc: 0.7137 - val_auc: 0.7999\n", "Epoch 175: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5466 - acc: 0.7191 - auc: 0.7940 - val_loss: 0.5628 - val_acc: 0.7072 - val_auc: 0.7984\n", "Epoch 176: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5462 - acc: 0.7197 - auc: 0.7945 - val_loss: 0.5654 - val_acc: 0.7037 - val_auc: 0.7990\n", "Epoch 177: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5467 - acc: 0.7188 - auc: 0.7939 - val_loss: 0.5566 - val_acc: 0.7106 - val_auc: 0.8007\n", "Epoch 178: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5465 - acc: 0.7189 - auc: 0.7941 - val_loss: 0.5738 - val_acc: 0.6931 - val_auc: 0.8014\n", "Epoch 179: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5463 - acc: 0.7191 - auc: 0.7942 - val_loss: 0.5642 - val_acc: 0.7061 - val_auc: 0.8020\n", "Epoch 180: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5460 - acc: 0.7193 - auc: 0.7946 - val_loss: 0.5600 - val_acc: 0.7066 - val_auc: 0.8057\n", "Epoch 181: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5458 - acc: 0.7197 - auc: 0.7947 - val_loss: 0.5569 - val_acc: 0.7104 - val_auc: 0.8009\n", "Epoch 182: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5455 - acc: 0.7199 - auc: 0.7950 - val_loss: 0.5654 - val_acc: 0.7023 - val_auc: 0.8018\n", "Epoch 183: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5461 - acc: 0.7191 - auc: 0.7944 - val_loss: 0.5610 - val_acc: 0.7076 - val_auc: 0.7999\n", "Epoch 184: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5460 - acc: 0.7196 - auc: 0.7946 - val_loss: 0.5610 - val_acc: 0.7042 - val_auc: 0.8014\n", "Epoch 185: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5466 - acc: 0.7188 - auc: 0.7939 - val_loss: 0.5661 - val_acc: 0.7036 - val_auc: 0.7989\n", "Epoch 186: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5467 - acc: 0.7190 - auc: 0.7939 - val_loss: 0.5585 - val_acc: 0.7090 - val_auc: 0.8012\n", "Epoch 187: 2160000/2160000 [==============================] - 76s 35us/sample - loss: 0.5457 - acc: 0.7197 - auc: 0.7948 - val_loss: 0.5594 - val_acc: 0.7086 - val_auc: 0.7999\n", "Epoch 188: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5454 - acc: 0.7202 - auc: 0.7952 - val_loss: 0.5540 - val_acc: 0.7148 - val_auc: 0.8042\n", "Epoch 189: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5451 - acc: 0.7200 - auc: 0.7954 - val_loss: 0.5689 - val_acc: 0.6991 - val_auc: 0.8004\n", "Epoch 190: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5452 - acc: 0.7202 - auc: 0.7953 - val_loss: 0.5685 - val_acc: 0.7016 - val_auc: 0.8004\n", "Epoch 191: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5448 - acc: 0.7205 - auc: 0.7957 - val_loss: 0.5622 - val_acc: 0.7047 - val_auc: 0.8040\n", "Epoch 192: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5441 - acc: 0.7212 - auc: 0.7964 - val_loss: 0.5568 - val_acc: 0.7105 - val_auc: 0.8040\n", "Epoch 193: 2160000/2160000 [==============================] - 76s 35us/sample - loss: 0.5451 - acc: 0.7200 - auc: 0.7954 - val_loss: 0.5576 - val_acc: 0.7095 - val_auc: 0.8026\n", "Epoch 194: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5446 - acc: 0.7205 - auc: 0.7958 - val_loss: 0.5536 - val_acc: 0.7133 - val_auc: 0.8064\n", "Epoch 195: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5438 - acc: 0.7210 - auc: 0.7966 - val_loss: 0.5514 - val_acc: 0.7150 - val_auc: 0.8015\n", "Epoch 196: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5448 - acc: 0.7199 - auc: 0.7956 - val_loss: 0.5652 - val_acc: 0.7044 - val_auc: 0.8007\n", "Epoch 197: 2160000/2160000 [==============================] - 82s 38us/sample - loss: 0.5457 - acc: 0.7197 - auc: 0.7949 - val_loss: 0.5620 - val_acc: 0.7045 - val_auc: 0.8019\n", "Epoch 198: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5458 - acc: 0.7195 - auc: 0.7948 - val_loss: 0.5614 - val_acc: 0.7066 - val_auc: 0.8012\n", "Epoch 199: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5445 - acc: 0.7205 - auc: 0.7960 - val_loss: 0.5696 - val_acc: 0.7012 - val_auc: 0.8019\n", "Epoch 200: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5450 - acc: 0.7200 - auc: 0.7954 - val_loss: 0.5561 - val_acc: 0.7108 - val_auc: 0.8000\n" ] } ], "source": [ "print_logs('keras_model-kera_lr005.log')" ] }, { "cell_type": "markdown", "id": "broke-basket", "metadata": {}, "source": [ "## ELU with all hidden layers with Dropout 0.4" ] }, { "cell_type": "code", "execution_count": 32, "id": "novel-assets", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1: 2160000/2160000 [==============================] - 97s 45us/sample - loss: 0.6784 - acc: 0.5618 - auc: 0.5835 - val_loss: 0.6537 - val_acc: 0.6108 - val_auc: 0.6584\n", "Epoch 2: 2160000/2160000 [==============================] - 97s 45us/sample - loss: 0.6528 - acc: 0.6127 - auc: 0.6513 - val_loss: 0.6424 - val_acc: 0.6287 - val_auc: 0.6705\n", "Epoch 3: 2160000/2160000 [==============================] - 85s 39us/sample - loss: 0.6474 - acc: 0.6219 - auc: 0.6616 - val_loss: 0.6426 - val_acc: 0.6292 - val_auc: 0.6726\n", "Epoch 4: 2160000/2160000 [==============================] - 95s 44us/sample - loss: 0.6449 - acc: 0.6270 - auc: 0.6663 - val_loss: 0.6400 - val_acc: 0.6332 - val_auc: 0.6773\n", "Epoch 5: 2160000/2160000 [==============================] - 89s 41us/sample - loss: 0.6436 - acc: 0.6290 - auc: 0.6688 - val_loss: 0.6379 - val_acc: 0.6364 - val_auc: 0.6791\n", "Epoch 6: 2160000/2160000 [==============================] - 84s 39us/sample - loss: 0.6421 - acc: 0.6308 - auc: 0.6717 - val_loss: 0.6370 - val_acc: 0.6375 - val_auc: 0.6804\n", "Epoch 7: 2160000/2160000 [==============================] - 85s 39us/sample - loss: 0.6396 - acc: 0.6333 - auc: 0.6771 - val_loss: 0.6335 - val_acc: 0.6414 - val_auc: 0.6949\n", "Epoch 8: 2160000/2160000 [==============================] - 89s 41us/sample - loss: 0.6346 - acc: 0.6382 - auc: 0.6881 - val_loss: 0.6234 - val_acc: 0.6498 - val_auc: 0.7088\n", "Epoch 9: 2160000/2160000 [==============================] - 85s 39us/sample - loss: 0.6302 - acc: 0.6449 - auc: 0.6971 - val_loss: 0.6195 - val_acc: 0.6559 - val_auc: 0.7123\n", "Epoch 10: 2160000/2160000 [==============================] - 85s 39us/sample - loss: 0.6261 - acc: 0.6499 - auc: 0.7038 - val_loss: 0.6140 - val_acc: 0.6622 - val_auc: 0.7211\n", "Epoch 11: 2160000/2160000 [==============================] - 93s 43us/sample - loss: 0.6232 - acc: 0.6535 - auc: 0.7084 - val_loss: 0.6196 - val_acc: 0.6506 - val_auc: 0.7258\n", "Epoch 12: 2160000/2160000 [==============================] - 87s 40us/sample - loss: 0.6218 - acc: 0.6555 - auc: 0.7106 - val_loss: 0.6129 - val_acc: 0.6583 - val_auc: 0.7276\n", "Epoch 13: 2160000/2160000 [==============================] - 86s 40us/sample - loss: 0.6200 - acc: 0.6572 - auc: 0.7131 - val_loss: 0.6070 - val_acc: 0.6686 - val_auc: 0.7292\n", "Epoch 14: 2160000/2160000 [==============================] - 85s 39us/sample - loss: 0.6185 - acc: 0.6585 - auc: 0.7150 - val_loss: 0.6156 - val_acc: 0.6644 - val_auc: 0.7304\n", "Epoch 15: 2160000/2160000 [==============================] - 82s 38us/sample - loss: 0.6167 - acc: 0.6606 - auc: 0.7174 - val_loss: 0.6067 - val_acc: 0.6708 - val_auc: 0.7312\n", "Epoch 16: 2160000/2160000 [==============================] - 82s 38us/sample - loss: 0.6150 - acc: 0.6619 - auc: 0.7195 - val_loss: 0.6072 - val_acc: 0.6724 - val_auc: 0.7333\n", "Epoch 17: 2160000/2160000 [==============================] - 91s 42us/sample - loss: 0.6133 - acc: 0.6638 - auc: 0.7217 - val_loss: 0.6059 - val_acc: 0.6700 - val_auc: 0.7318\n", "Epoch 18: 2160000/2160000 [==============================] - 90s 42us/sample - loss: 0.6119 - acc: 0.6649 - auc: 0.7235 - val_loss: 0.6028 - val_acc: 0.6677 - val_auc: 0.7398\n", "Epoch 19: 2160000/2160000 [==============================] - 82s 38us/sample - loss: 0.6110 - acc: 0.6658 - auc: 0.7247 - val_loss: 0.6027 - val_acc: 0.6752 - val_auc: 0.7387\n", "Epoch 20: 2160000/2160000 [==============================] - 86s 40us/sample - loss: 0.6099 - acc: 0.6670 - auc: 0.7262 - val_loss: 0.6027 - val_acc: 0.6683 - val_auc: 0.7367\n", "Epoch 21: 2160000/2160000 [==============================] - 92s 43us/sample - loss: 0.6086 - acc: 0.6687 - auc: 0.7279 - val_loss: 0.5961 - val_acc: 0.6765 - val_auc: 0.7427\n", "Epoch 22: 2160000/2160000 [==============================] - 97s 45us/sample - loss: 0.6074 - acc: 0.6694 - auc: 0.7295 - val_loss: 0.5955 - val_acc: 0.6804 - val_auc: 0.7438\n", "Epoch 23: 2160000/2160000 [==============================] - 92s 42us/sample - loss: 0.6069 - acc: 0.6699 - auc: 0.7302 - val_loss: 0.5914 - val_acc: 0.6837 - val_auc: 0.7488\n", "Epoch 24: 2160000/2160000 [==============================] - 111s 51us/sample - loss: 0.6050 - acc: 0.6717 - auc: 0.7326 - val_loss: 0.5905 - val_acc: 0.6838 - val_auc: 0.7509\n", "Epoch 25: 2160000/2160000 [==============================] - 82s 38us/sample - loss: 0.6040 - acc: 0.6725 - auc: 0.7338 - val_loss: 0.5928 - val_acc: 0.6821 - val_auc: 0.7498\n", "Epoch 26: 2160000/2160000 [==============================] - 88s 41us/sample - loss: 0.6029 - acc: 0.6732 - auc: 0.7351 - val_loss: 0.5883 - val_acc: 0.6855 - val_auc: 0.7521\n", "Epoch 27: 2160000/2160000 [==============================] - 95s 44us/sample - loss: 0.6016 - acc: 0.6745 - auc: 0.7367 - val_loss: 0.5913 - val_acc: 0.6773 - val_auc: 0.7517\n", "Epoch 28: 2160000/2160000 [==============================] - 87s 40us/sample - loss: 0.6004 - acc: 0.6755 - auc: 0.7381 - val_loss: 0.5918 - val_acc: 0.6783 - val_auc: 0.7473\n", "Epoch 29: 2160000/2160000 [==============================] - 87s 40us/sample - loss: 0.5988 - acc: 0.6768 - auc: 0.7400 - val_loss: 0.5822 - val_acc: 0.6887 - val_auc: 0.7580\n", "Epoch 30: 2160000/2160000 [==============================] - 86s 40us/sample - loss: 0.5975 - acc: 0.6781 - auc: 0.7415 - val_loss: 0.5864 - val_acc: 0.6859 - val_auc: 0.7596\n", "Epoch 31: 2160000/2160000 [==============================] - 92s 42us/sample - loss: 0.5967 - acc: 0.6786 - auc: 0.7424 - val_loss: 0.5836 - val_acc: 0.6890 - val_auc: 0.7591\n", "Epoch 32: 2160000/2160000 [==============================] - 84s 39us/sample - loss: 0.5956 - acc: 0.6793 - auc: 0.7435 - val_loss: 0.5779 - val_acc: 0.6926 - val_auc: 0.7624\n", "Epoch 33: 2160000/2160000 [==============================] - 94s 44us/sample - loss: 0.5945 - acc: 0.6804 - auc: 0.7448 - val_loss: 0.5784 - val_acc: 0.6925 - val_auc: 0.7630\n", "Epoch 34: 2160000/2160000 [==============================] - 108s 50us/sample - loss: 0.5936 - acc: 0.6814 - auc: 0.7458 - val_loss: 0.5821 - val_acc: 0.6869 - val_auc: 0.7581\n", "Epoch 35: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5926 - acc: 0.6817 - auc: 0.7468 - val_loss: 0.5782 - val_acc: 0.6935 - val_auc: 0.7629\n", "Epoch 36: 2160000/2160000 [==============================] - 66s 31us/sample - loss: 0.5918 - acc: 0.6825 - auc: 0.7477 - val_loss: 0.5829 - val_acc: 0.6880 - val_auc: 0.7624\n", "Epoch 37: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5907 - acc: 0.6836 - auc: 0.7489 - val_loss: 0.5792 - val_acc: 0.6905 - val_auc: 0.7642\n", "Epoch 38: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5906 - acc: 0.6835 - auc: 0.7490 - val_loss: 0.5787 - val_acc: 0.6925 - val_auc: 0.7647\n", "Epoch 39: 2160000/2160000 [==============================] - 66s 31us/sample - loss: 0.5898 - acc: 0.6846 - auc: 0.7499 - val_loss: 0.5745 - val_acc: 0.6957 - val_auc: 0.7668\n", "Epoch 40: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5892 - acc: 0.6846 - auc: 0.7505 - val_loss: 0.5753 - val_acc: 0.6951 - val_auc: 0.7670\n", "Epoch 41: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5884 - acc: 0.6854 - auc: 0.7514 - val_loss: 0.5735 - val_acc: 0.6955 - val_auc: 0.7679\n", "Epoch 42: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5878 - acc: 0.6856 - auc: 0.7520 - val_loss: 0.5712 - val_acc: 0.6977 - val_auc: 0.7692\n", "Epoch 43: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5876 - acc: 0.6858 - auc: 0.7524 - val_loss: 0.5725 - val_acc: 0.6970 - val_auc: 0.7685\n", "Epoch 44: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5872 - acc: 0.6863 - auc: 0.7527 - val_loss: 0.5735 - val_acc: 0.6953 - val_auc: 0.7664\n", "Epoch 45: 2160000/2160000 [==============================] - 66s 31us/sample - loss: 0.5864 - acc: 0.6867 - auc: 0.7535 - val_loss: 0.5750 - val_acc: 0.6947 - val_auc: 0.7657\n", "Epoch 46: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5863 - acc: 0.6867 - auc: 0.7535 - val_loss: 0.5705 - val_acc: 0.6986 - val_auc: 0.7711\n", "Epoch 47: 2160000/2160000 [==============================] - 70s 33us/sample - loss: 0.5855 - acc: 0.6878 - auc: 0.7546 - val_loss: 0.5709 - val_acc: 0.6986 - val_auc: 0.7717\n", "Epoch 48: 2160000/2160000 [==============================] - 66s 31us/sample - loss: 0.5851 - acc: 0.6879 - auc: 0.7550 - val_loss: 0.5708 - val_acc: 0.6988 - val_auc: 0.7701\n", "Epoch 49: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5849 - acc: 0.6881 - auc: 0.7552 - val_loss: 0.5697 - val_acc: 0.6997 - val_auc: 0.7718\n", "Epoch 50: 2160000/2160000 [==============================] - 66s 31us/sample - loss: 0.5844 - acc: 0.6885 - auc: 0.7557 - val_loss: 0.5754 - val_acc: 0.6944 - val_auc: 0.7706\n", "Epoch 51: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5839 - acc: 0.6892 - auc: 0.7564 - val_loss: 0.5734 - val_acc: 0.6978 - val_auc: 0.7680\n", "Epoch 52: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5833 - acc: 0.6899 - auc: 0.7570 - val_loss: 0.5671 - val_acc: 0.7004 - val_auc: 0.7730\n", "Epoch 53: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5834 - acc: 0.6894 - auc: 0.7568 - val_loss: 0.5681 - val_acc: 0.7012 - val_auc: 0.7728\n", "Epoch 54: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5830 - acc: 0.6898 - auc: 0.7573 - val_loss: 0.5682 - val_acc: 0.6993 - val_auc: 0.7723\n", "Epoch 55: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5825 - acc: 0.6900 - auc: 0.7578 - val_loss: 0.5744 - val_acc: 0.6949 - val_auc: 0.7688\n", "Epoch 56: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5819 - acc: 0.6910 - auc: 0.7585 - val_loss: 0.5692 - val_acc: 0.6995 - val_auc: 0.7737\n", "Epoch 57: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5818 - acc: 0.6908 - auc: 0.7586 - val_loss: 0.5704 - val_acc: 0.7007 - val_auc: 0.7727\n", "Epoch 58: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5814 - acc: 0.6912 - auc: 0.7591 - val_loss: 0.5680 - val_acc: 0.7003 - val_auc: 0.7742\n", "Epoch 59: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5812 - acc: 0.6913 - auc: 0.7593 - val_loss: 0.5736 - val_acc: 0.6950 - val_auc: 0.7747\n", "Epoch 60: 2160000/2160000 [==============================] - 65s 30us/sample - loss: 0.5808 - acc: 0.6916 - auc: 0.7598 - val_loss: 0.5660 - val_acc: 0.7020 - val_auc: 0.7747\n", "Epoch 61: 2160000/2160000 [==============================] - 64s 30us/sample - loss: 0.5802 - acc: 0.6922 - auc: 0.7604 - val_loss: 0.5676 - val_acc: 0.7009 - val_auc: 0.7749\n", "Epoch 62: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5798 - acc: 0.6926 - auc: 0.7608 - val_loss: 0.5679 - val_acc: 0.6993 - val_auc: 0.7740\n", "Epoch 63: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5798 - acc: 0.6924 - auc: 0.7608 - val_loss: 0.5642 - val_acc: 0.7043 - val_auc: 0.7767\n", "Epoch 64: 2160000/2160000 [==============================] - 66s 30us/sample - loss: 0.5796 - acc: 0.6926 - auc: 0.7610 - val_loss: 0.5709 - val_acc: 0.6987 - val_auc: 0.7744\n", "Epoch 65: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5793 - acc: 0.6928 - auc: 0.7613 - val_loss: 0.5656 - val_acc: 0.7034 - val_auc: 0.7768\n", "Epoch 66: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5792 - acc: 0.6926 - auc: 0.7613 - val_loss: 0.5650 - val_acc: 0.7036 - val_auc: 0.7761\n", "Epoch 67: 2160000/2160000 [==============================] - 84s 39us/sample - loss: 0.5789 - acc: 0.6935 - auc: 0.7618 - val_loss: 0.5672 - val_acc: 0.7026 - val_auc: 0.7747\n", "Epoch 68: 2160000/2160000 [==============================] - 87s 40us/sample - loss: 0.5788 - acc: 0.6933 - auc: 0.7619 - val_loss: 0.5668 - val_acc: 0.7026 - val_auc: 0.7760\n", "Epoch 69: 2160000/2160000 [==============================] - 88s 41us/sample - loss: 0.5783 - acc: 0.6938 - auc: 0.7624 - val_loss: 0.5675 - val_acc: 0.7021 - val_auc: 0.7736\n", "Epoch 70: 2160000/2160000 [==============================] - 99s 46us/sample - loss: 0.5778 - acc: 0.6941 - auc: 0.7629 - val_loss: 0.5679 - val_acc: 0.7018 - val_auc: 0.7747\n", "Epoch 71: 2160000/2160000 [==============================] - 88s 41us/sample - loss: 0.5777 - acc: 0.6942 - auc: 0.7631 - val_loss: 0.5700 - val_acc: 0.7015 - val_auc: 0.7780\n", "Epoch 72: 2160000/2160000 [==============================] - 93s 43us/sample - loss: 0.5774 - acc: 0.6944 - auc: 0.7633 - val_loss: 0.5646 - val_acc: 0.7029 - val_auc: 0.7766\n", "Epoch 73: 2160000/2160000 [==============================] - 99s 46us/sample - loss: 0.5770 - acc: 0.6948 - auc: 0.7638 - val_loss: 0.5627 - val_acc: 0.7052 - val_auc: 0.7782\n", "Epoch 74: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5769 - acc: 0.6947 - auc: 0.7638 - val_loss: 0.5642 - val_acc: 0.7042 - val_auc: 0.7773\n", "Epoch 75: 2160000/2160000 [==============================] - 79s 36us/sample - loss: 0.5768 - acc: 0.6946 - auc: 0.7640 - val_loss: 0.5633 - val_acc: 0.7056 - val_auc: 0.7779\n", "Epoch 76: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5765 - acc: 0.6954 - auc: 0.7644 - val_loss: 0.5620 - val_acc: 0.7065 - val_auc: 0.7786\n", "Epoch 77: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5761 - acc: 0.6955 - auc: 0.7647 - val_loss: 0.5611 - val_acc: 0.7064 - val_auc: 0.7794\n", "Epoch 78: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5758 - acc: 0.6959 - auc: 0.7650 - val_loss: 0.5620 - val_acc: 0.7064 - val_auc: 0.7793\n", "Epoch 79: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5761 - acc: 0.6953 - auc: 0.7647 - val_loss: 0.5636 - val_acc: 0.7045 - val_auc: 0.7772\n", "Epoch 80: 2160000/2160000 [==============================] - 81s 38us/sample - loss: 0.5757 - acc: 0.6959 - auc: 0.7651 - val_loss: 0.5652 - val_acc: 0.7023 - val_auc: 0.7778\n", "Epoch 81: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5755 - acc: 0.6960 - auc: 0.7653 - val_loss: 0.5632 - val_acc: 0.7043 - val_auc: 0.7781\n", "Epoch 82: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5755 - acc: 0.6959 - auc: 0.7653 - val_loss: 0.5617 - val_acc: 0.7067 - val_auc: 0.7793\n", "Epoch 83: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5751 - acc: 0.6961 - auc: 0.7658 - val_loss: 0.5610 - val_acc: 0.7073 - val_auc: 0.7798\n", "Epoch 84: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5748 - acc: 0.6967 - auc: 0.7660 - val_loss: 0.5611 - val_acc: 0.7060 - val_auc: 0.7799\n", "Epoch 85: 2160000/2160000 [==============================] - 81s 38us/sample - loss: 0.5747 - acc: 0.6969 - auc: 0.7662 - val_loss: 0.5672 - val_acc: 0.7011 - val_auc: 0.7792\n", "Epoch 86: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5746 - acc: 0.6965 - auc: 0.7662 - val_loss: 0.5612 - val_acc: 0.7054 - val_auc: 0.7798\n", "Epoch 87: 2160000/2160000 [==============================] - 84s 39us/sample - loss: 0.5741 - acc: 0.6973 - auc: 0.7668 - val_loss: 0.5618 - val_acc: 0.7058 - val_auc: 0.7805\n", "Epoch 88: 2160000/2160000 [==============================] - 85s 39us/sample - loss: 0.5740 - acc: 0.6974 - auc: 0.7669 - val_loss: 0.5623 - val_acc: 0.7051 - val_auc: 0.7786\n", "Epoch 89: 2160000/2160000 [==============================] - 98s 45us/sample - loss: 0.5739 - acc: 0.6976 - auc: 0.7671 - val_loss: 0.5601 - val_acc: 0.7077 - val_auc: 0.7809\n", "Epoch 90: 2160000/2160000 [==============================] - 89s 41us/sample - loss: 0.5741 - acc: 0.6971 - auc: 0.7667 - val_loss: 0.5617 - val_acc: 0.7061 - val_auc: 0.7792\n", "Epoch 91: 2160000/2160000 [==============================] - 86s 40us/sample - loss: 0.5738 - acc: 0.6974 - auc: 0.7671 - val_loss: 0.5630 - val_acc: 0.7050 - val_auc: 0.7781\n", "Epoch 92: 2160000/2160000 [==============================] - 89s 41us/sample - loss: 0.5735 - acc: 0.6978 - auc: 0.7674 - val_loss: 0.5611 - val_acc: 0.7071 - val_auc: 0.7809\n", "Epoch 93: 2160000/2160000 [==============================] - 81s 37us/sample - loss: 0.5734 - acc: 0.6979 - auc: 0.7676 - val_loss: 0.5594 - val_acc: 0.7082 - val_auc: 0.7817\n", "Epoch 94: 2160000/2160000 [==============================] - 118s 54us/sample - loss: 0.5730 - acc: 0.6978 - auc: 0.7679 - val_loss: 0.5590 - val_acc: 0.7087 - val_auc: 0.7819\n", "Epoch 95: 2160000/2160000 [==============================] - 83s 39us/sample - loss: 0.5730 - acc: 0.6980 - auc: 0.7679 - val_loss: 0.5615 - val_acc: 0.7055 - val_auc: 0.7800\n", "Epoch 96: 2160000/2160000 [==============================] - 81s 37us/sample - loss: 0.5729 - acc: 0.6980 - auc: 0.7681 - val_loss: 0.5610 - val_acc: 0.7072 - val_auc: 0.7800\n", "Epoch 97: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5728 - acc: 0.6982 - auc: 0.7681 - val_loss: 0.5600 - val_acc: 0.7061 - val_auc: 0.7819\n", "Epoch 98: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5722 - acc: 0.6985 - auc: 0.7688 - val_loss: 0.5585 - val_acc: 0.7088 - val_auc: 0.7819\n", "Epoch 99: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5724 - acc: 0.6985 - auc: 0.7686 - val_loss: 0.5620 - val_acc: 0.7042 - val_auc: 0.7804\n", "Epoch 100: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5722 - acc: 0.6990 - auc: 0.7688 - val_loss: 0.5600 - val_acc: 0.7075 - val_auc: 0.7809\n", "Epoch 101: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5721 - acc: 0.6988 - auc: 0.7689 - val_loss: 0.5581 - val_acc: 0.7094 - val_auc: 0.7827\n", "Epoch 102: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5720 - acc: 0.6987 - auc: 0.7690 - val_loss: 0.5583 - val_acc: 0.7086 - val_auc: 0.7824\n", "Epoch 103: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5718 - acc: 0.6992 - auc: 0.7692 - val_loss: 0.5596 - val_acc: 0.7074 - val_auc: 0.7810\n", "Epoch 104: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5717 - acc: 0.6993 - auc: 0.7693 - val_loss: 0.5608 - val_acc: 0.7075 - val_auc: 0.7801\n", "Epoch 105: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5716 - acc: 0.6991 - auc: 0.7693 - val_loss: 0.5601 - val_acc: 0.7090 - val_auc: 0.7818\n", "Epoch 106: 2160000/2160000 [==============================] - 86s 40us/sample - loss: 0.5712 - acc: 0.6996 - auc: 0.7697 - val_loss: 0.5590 - val_acc: 0.7085 - val_auc: 0.7827\n", "Epoch 107: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5712 - acc: 0.6993 - auc: 0.7698 - val_loss: 0.5579 - val_acc: 0.7090 - val_auc: 0.7827\n", "Epoch 108: 2160000/2160000 [==============================] - 77s 35us/sample - loss: 0.5712 - acc: 0.6997 - auc: 0.7698 - val_loss: 0.5587 - val_acc: 0.7088 - val_auc: 0.7833\n", "Epoch 109: 2160000/2160000 [==============================] - 81s 38us/sample - loss: 0.5710 - acc: 0.7000 - auc: 0.7701 - val_loss: 0.5574 - val_acc: 0.7102 - val_auc: 0.7835\n", "Epoch 110: 2160000/2160000 [==============================] - 82s 38us/sample - loss: 0.5709 - acc: 0.6998 - auc: 0.7701 - val_loss: 0.5588 - val_acc: 0.7089 - val_auc: 0.7827\n", "Epoch 111: 2160000/2160000 [==============================] - 90s 42us/sample - loss: 0.5708 - acc: 0.6999 - auc: 0.7702 - val_loss: 0.5592 - val_acc: 0.7088 - val_auc: 0.7823\n", "Epoch 112: 2160000/2160000 [==============================] - 83s 39us/sample - loss: 0.5706 - acc: 0.7001 - auc: 0.7704 - val_loss: 0.5579 - val_acc: 0.7097 - val_auc: 0.7832\n", "Epoch 113: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5702 - acc: 0.7003 - auc: 0.7707 - val_loss: 0.5591 - val_acc: 0.7090 - val_auc: 0.7833\n", "Epoch 114: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5704 - acc: 0.7003 - auc: 0.7706 - val_loss: 0.5575 - val_acc: 0.7090 - val_auc: 0.7834\n", "Epoch 115: 2160000/2160000 [==============================] - 107s 50us/sample - loss: 0.5699 - acc: 0.7006 - auc: 0.7711 - val_loss: 0.5592 - val_acc: 0.7082 - val_auc: 0.7834\n", "Epoch 116: 2160000/2160000 [==============================] - 112s 52us/sample - loss: 0.5701 - acc: 0.7002 - auc: 0.7709 - val_loss: 0.5569 - val_acc: 0.7095 - val_auc: 0.7839\n", "Epoch 117: 2160000/2160000 [==============================] - 111s 51us/sample - loss: 0.5698 - acc: 0.7008 - auc: 0.7712 - val_loss: 0.5565 - val_acc: 0.7105 - val_auc: 0.7840\n", "Epoch 118: 2160000/2160000 [==============================] - 97s 45us/sample - loss: 0.5700 - acc: 0.7008 - auc: 0.7711 - val_loss: 0.5575 - val_acc: 0.7097 - val_auc: 0.7837\n", "Epoch 119: 2160000/2160000 [==============================] - 98s 46us/sample - loss: 0.5694 - acc: 0.7013 - auc: 0.7716 - val_loss: 0.5574 - val_acc: 0.7097 - val_auc: 0.7832\n", "Epoch 120: 2160000/2160000 [==============================] - 84s 39us/sample - loss: 0.5696 - acc: 0.7008 - auc: 0.7715 - val_loss: 0.5562 - val_acc: 0.7107 - val_auc: 0.7845\n", "Epoch 121: 2160000/2160000 [==============================] - 83s 39us/sample - loss: 0.5695 - acc: 0.7011 - auc: 0.7716 - val_loss: 0.5558 - val_acc: 0.7115 - val_auc: 0.7849\n", "Epoch 122: 2160000/2160000 [==============================] - 90s 42us/sample - loss: 0.5691 - acc: 0.7009 - auc: 0.7719 - val_loss: 0.5596 - val_acc: 0.7080 - val_auc: 0.7830\n", "Epoch 123: 2160000/2160000 [==============================] - 85s 39us/sample - loss: 0.5691 - acc: 0.7013 - auc: 0.7720 - val_loss: 0.5569 - val_acc: 0.7103 - val_auc: 0.7843\n", "Epoch 124: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5688 - acc: 0.7015 - auc: 0.7723 - val_loss: 0.5599 - val_acc: 0.7083 - val_auc: 0.7807\n", "Epoch 125: 2160000/2160000 [==============================] - 91s 42us/sample - loss: 0.5690 - acc: 0.7013 - auc: 0.7720 - val_loss: 0.5556 - val_acc: 0.7115 - val_auc: 0.7850\n", "Epoch 126: 2160000/2160000 [==============================] - 95s 44us/sample - loss: 0.5687 - acc: 0.7015 - auc: 0.7723 - val_loss: 0.5584 - val_acc: 0.7094 - val_auc: 0.7831\n", "Epoch 127: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5686 - acc: 0.7015 - auc: 0.7725 - val_loss: 0.5558 - val_acc: 0.7107 - val_auc: 0.7853\n", "Epoch 128: 2160000/2160000 [==============================] - 66s 31us/sample - loss: 0.5687 - acc: 0.7016 - auc: 0.7723 - val_loss: 0.5558 - val_acc: 0.7109 - val_auc: 0.7847\n", "Epoch 129: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5682 - acc: 0.7020 - auc: 0.7728 - val_loss: 0.5575 - val_acc: 0.7086 - val_auc: 0.7841\n", "Epoch 130: 2160000/2160000 [==============================] - 68s 31us/sample - loss: 0.5683 - acc: 0.7019 - auc: 0.7727 - val_loss: 0.5557 - val_acc: 0.7113 - val_auc: 0.7850\n", "Epoch 131: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5681 - acc: 0.7020 - auc: 0.7730 - val_loss: 0.5563 - val_acc: 0.7099 - val_auc: 0.7847\n", "Epoch 132: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5681 - acc: 0.7021 - auc: 0.7731 - val_loss: 0.5563 - val_acc: 0.7104 - val_auc: 0.7849\n", "Epoch 133: 2160000/2160000 [==============================] - 83s 38us/sample - loss: 0.5679 - acc: 0.7022 - auc: 0.7732 - val_loss: 0.5572 - val_acc: 0.7088 - val_auc: 0.7850\n", "Epoch 134: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5677 - acc: 0.7023 - auc: 0.7733 - val_loss: 0.5566 - val_acc: 0.7092 - val_auc: 0.7845\n", "Epoch 135: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5677 - acc: 0.7025 - auc: 0.7734 - val_loss: 0.5559 - val_acc: 0.7110 - val_auc: 0.7846\n", "Epoch 136: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5677 - acc: 0.7024 - auc: 0.7734 - val_loss: 0.5557 - val_acc: 0.7111 - val_auc: 0.7848\n", "Epoch 137: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5675 - acc: 0.7024 - auc: 0.7735 - val_loss: 0.5544 - val_acc: 0.7118 - val_auc: 0.7863\n", "Epoch 138: 2160000/2160000 [==============================] - 81s 38us/sample - loss: 0.5671 - acc: 0.7027 - auc: 0.7740 - val_loss: 0.5562 - val_acc: 0.7094 - val_auc: 0.7845\n", "Epoch 139: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5672 - acc: 0.7031 - auc: 0.7738 - val_loss: 0.5549 - val_acc: 0.7115 - val_auc: 0.7858\n", "Epoch 140: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5671 - acc: 0.7029 - auc: 0.7740 - val_loss: 0.5546 - val_acc: 0.7121 - val_auc: 0.7860\n", "Epoch 141: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5669 - acc: 0.7030 - auc: 0.7742 - val_loss: 0.5560 - val_acc: 0.7100 - val_auc: 0.7851\n", "Epoch 142: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5669 - acc: 0.7031 - auc: 0.7742 - val_loss: 0.5553 - val_acc: 0.7121 - val_auc: 0.7860\n", "Epoch 143: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5667 - acc: 0.7033 - auc: 0.7744 - val_loss: 0.5551 - val_acc: 0.7122 - val_auc: 0.7867\n", "Epoch 144: 2160000/2160000 [==============================] - 84s 39us/sample - loss: 0.5666 - acc: 0.7034 - auc: 0.7745 - val_loss: 0.5547 - val_acc: 0.7107 - val_auc: 0.7863\n", "Epoch 145: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5665 - acc: 0.7033 - auc: 0.7746 - val_loss: 0.5546 - val_acc: 0.7123 - val_auc: 0.7865\n", "Epoch 146: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5662 - acc: 0.7036 - auc: 0.7749 - val_loss: 0.5533 - val_acc: 0.7130 - val_auc: 0.7871\n", "Epoch 147: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5664 - acc: 0.7037 - auc: 0.7748 - val_loss: 0.5550 - val_acc: 0.7116 - val_auc: 0.7861\n", "Epoch 148: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5661 - acc: 0.7036 - auc: 0.7750 - val_loss: 0.5552 - val_acc: 0.7105 - val_auc: 0.7858\n", "Epoch 149: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5663 - acc: 0.7038 - auc: 0.7749 - val_loss: 0.5553 - val_acc: 0.7102 - val_auc: 0.7864\n", "Epoch 150: 2160000/2160000 [==============================] - 67s 31us/sample - loss: 0.5661 - acc: 0.7038 - auc: 0.7750 - val_loss: 0.5562 - val_acc: 0.7110 - val_auc: 0.7851\n", "Epoch 151: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5658 - acc: 0.7041 - auc: 0.7753 - val_loss: 0.5617 - val_acc: 0.7045 - val_auc: 0.7836\n", "Epoch 152: 2160000/2160000 [==============================] - 70s 33us/sample - loss: 0.5658 - acc: 0.7040 - auc: 0.7754 - val_loss: 0.5539 - val_acc: 0.7120 - val_auc: 0.7870\n", "Epoch 153: 2160000/2160000 [==============================] - 69s 32us/sample - loss: 0.5657 - acc: 0.7041 - auc: 0.7754 - val_loss: 0.5543 - val_acc: 0.7109 - val_auc: 0.7869\n", "Epoch 154: 2160000/2160000 [==============================] - 68s 32us/sample - loss: 0.5657 - acc: 0.7044 - auc: 0.7755 - val_loss: 0.5522 - val_acc: 0.7138 - val_auc: 0.7881\n", "Epoch 155: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5655 - acc: 0.7043 - auc: 0.7756 - val_loss: 0.5534 - val_acc: 0.7122 - val_auc: 0.7880\n", "Epoch 156: 2160000/2160000 [==============================] - 88s 41us/sample - loss: 0.5653 - acc: 0.7042 - auc: 0.7757 - val_loss: 0.5525 - val_acc: 0.7137 - val_auc: 0.7881\n", "Epoch 157: 2160000/2160000 [==============================] - 81s 38us/sample - loss: 0.5654 - acc: 0.7046 - auc: 0.7758 - val_loss: 0.5526 - val_acc: 0.7136 - val_auc: 0.7881\n", "Epoch 158: 2160000/2160000 [==============================] - 96s 45us/sample - loss: 0.5651 - acc: 0.7047 - auc: 0.7760 - val_loss: 0.5532 - val_acc: 0.7129 - val_auc: 0.7873\n", "Epoch 159: 2160000/2160000 [==============================] - 105s 49us/sample - loss: 0.5651 - acc: 0.7048 - auc: 0.7760 - val_loss: 0.5541 - val_acc: 0.7113 - val_auc: 0.7881\n", "Epoch 160: 2160000/2160000 [==============================] - 83s 38us/sample - loss: 0.5650 - acc: 0.7044 - auc: 0.7760 - val_loss: 0.5527 - val_acc: 0.7140 - val_auc: 0.7883\n", "Epoch 161: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5649 - acc: 0.7047 - auc: 0.7762 - val_loss: 0.5531 - val_acc: 0.7135 - val_auc: 0.7877\n", "Epoch 162: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5647 - acc: 0.7051 - auc: 0.7764 - val_loss: 0.5522 - val_acc: 0.7135 - val_auc: 0.7883\n", "Epoch 163: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5647 - acc: 0.7048 - auc: 0.7764 - val_loss: 0.5546 - val_acc: 0.7128 - val_auc: 0.7880\n", "Epoch 164: 2160000/2160000 [==============================] - 79s 36us/sample - loss: 0.5646 - acc: 0.7049 - auc: 0.7766 - val_loss: 0.5538 - val_acc: 0.7119 - val_auc: 0.7878\n", "Epoch 165: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5645 - acc: 0.7052 - auc: 0.7765 - val_loss: 0.5529 - val_acc: 0.7135 - val_auc: 0.7884\n", "Epoch 166: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5644 - acc: 0.7051 - auc: 0.7767 - val_loss: 0.5533 - val_acc: 0.7133 - val_auc: 0.7874\n", "Epoch 167: 2160000/2160000 [==============================] - 70s 33us/sample - loss: 0.5642 - acc: 0.7054 - auc: 0.7769 - val_loss: 0.5524 - val_acc: 0.7133 - val_auc: 0.7879\n", "Epoch 168: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5640 - acc: 0.7055 - auc: 0.7771 - val_loss: 0.5515 - val_acc: 0.7139 - val_auc: 0.7892\n", "Epoch 169: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5640 - acc: 0.7056 - auc: 0.7771 - val_loss: 0.5522 - val_acc: 0.7140 - val_auc: 0.7882\n", "Epoch 170: 2160000/2160000 [==============================] - 76s 35us/sample - loss: 0.5640 - acc: 0.7056 - auc: 0.7772 - val_loss: 0.5523 - val_acc: 0.7137 - val_auc: 0.7889\n", "Epoch 171: 2160000/2160000 [==============================] - 73s 34us/sample - loss: 0.5641 - acc: 0.7055 - auc: 0.7770 - val_loss: 0.5512 - val_acc: 0.7142 - val_auc: 0.7891\n", "Epoch 172: 2160000/2160000 [==============================] - 89s 41us/sample - loss: 0.5638 - acc: 0.7055 - auc: 0.7773 - val_loss: 0.5520 - val_acc: 0.7129 - val_auc: 0.7890\n", "Epoch 173: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5636 - acc: 0.7056 - auc: 0.7775 - val_loss: 0.5513 - val_acc: 0.7145 - val_auc: 0.7893\n", "Epoch 174: 2160000/2160000 [==============================] - 85s 39us/sample - loss: 0.5636 - acc: 0.7057 - auc: 0.7775 - val_loss: 0.5520 - val_acc: 0.7134 - val_auc: 0.7890\n", "Epoch 175: 2160000/2160000 [==============================] - 86s 40us/sample - loss: 0.5635 - acc: 0.7059 - auc: 0.7776 - val_loss: 0.5509 - val_acc: 0.7145 - val_auc: 0.7896\n", "Epoch 176: 2160000/2160000 [==============================] - 83s 39us/sample - loss: 0.5635 - acc: 0.7058 - auc: 0.7776 - val_loss: 0.5506 - val_acc: 0.7149 - val_auc: 0.7900\n", "Epoch 177: 2160000/2160000 [==============================] - 90s 42us/sample - loss: 0.5633 - acc: 0.7059 - auc: 0.7778 - val_loss: 0.5518 - val_acc: 0.7148 - val_auc: 0.7894\n", "Epoch 178: 2160000/2160000 [==============================] - 79s 37us/sample - loss: 0.5631 - acc: 0.7061 - auc: 0.7779 - val_loss: 0.5518 - val_acc: 0.7140 - val_auc: 0.7893\n", "Epoch 179: 2160000/2160000 [==============================] - 85s 39us/sample - loss: 0.5633 - acc: 0.7061 - auc: 0.7779 - val_loss: 0.5516 - val_acc: 0.7142 - val_auc: 0.7891\n", "Epoch 180: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5632 - acc: 0.7062 - auc: 0.7779 - val_loss: 0.5504 - val_acc: 0.7155 - val_auc: 0.7902\n", "Epoch 181: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5630 - acc: 0.7062 - auc: 0.7781 - val_loss: 0.5510 - val_acc: 0.7143 - val_auc: 0.7895\n", "Epoch 182: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5629 - acc: 0.7064 - auc: 0.7781 - val_loss: 0.5512 - val_acc: 0.7135 - val_auc: 0.7899\n", "Epoch 183: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5629 - acc: 0.7064 - auc: 0.7782 - val_loss: 0.5516 - val_acc: 0.7138 - val_auc: 0.7899\n", "Epoch 184: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5629 - acc: 0.7061 - auc: 0.7781 - val_loss: 0.5507 - val_acc: 0.7148 - val_auc: 0.7901\n", "Epoch 185: 2160000/2160000 [==============================] - 78s 36us/sample - loss: 0.5627 - acc: 0.7065 - auc: 0.7784 - val_loss: 0.5509 - val_acc: 0.7147 - val_auc: 0.7901\n", "Epoch 186: 2160000/2160000 [==============================] - 71s 33us/sample - loss: 0.5624 - acc: 0.7067 - auc: 0.7787 - val_loss: 0.5508 - val_acc: 0.7148 - val_auc: 0.7896\n", "Epoch 187: 2160000/2160000 [==============================] - 70s 32us/sample - loss: 0.5626 - acc: 0.7065 - auc: 0.7785 - val_loss: 0.5514 - val_acc: 0.7133 - val_auc: 0.7893\n", "Epoch 188: 2160000/2160000 [==============================] - 77s 35us/sample - loss: 0.5625 - acc: 0.7065 - auc: 0.7786 - val_loss: 0.5504 - val_acc: 0.7149 - val_auc: 0.7899\n", "Epoch 189: 2160000/2160000 [==============================] - 74s 34us/sample - loss: 0.5623 - acc: 0.7066 - auc: 0.7788 - val_loss: 0.5506 - val_acc: 0.7144 - val_auc: 0.7898\n", "Epoch 190: 2160000/2160000 [==============================] - 80s 37us/sample - loss: 0.5625 - acc: 0.7066 - auc: 0.7785 - val_loss: 0.5500 - val_acc: 0.7153 - val_auc: 0.7909\n", "Epoch 191: 2160000/2160000 [==============================] - 79s 36us/sample - loss: 0.5620 - acc: 0.7070 - auc: 0.7790 - val_loss: 0.5500 - val_acc: 0.7153 - val_auc: 0.7903\n", "Epoch 192: 2160000/2160000 [==============================] - 84s 39us/sample - loss: 0.5622 - acc: 0.7071 - auc: 0.7790 - val_loss: 0.5506 - val_acc: 0.7151 - val_auc: 0.7901\n", "Epoch 193: 2160000/2160000 [==============================] - 79s 36us/sample - loss: 0.5621 - acc: 0.7067 - auc: 0.7790 - val_loss: 0.5510 - val_acc: 0.7139 - val_auc: 0.7906\n", "Epoch 194: 2160000/2160000 [==============================] - 86s 40us/sample - loss: 0.5620 - acc: 0.7068 - auc: 0.7790 - val_loss: 0.5497 - val_acc: 0.7156 - val_auc: 0.7907\n", "Epoch 195: 2160000/2160000 [==============================] - 82s 38us/sample - loss: 0.5618 - acc: 0.7068 - auc: 0.7792 - val_loss: 0.5506 - val_acc: 0.7147 - val_auc: 0.7907\n", "Epoch 196: 2160000/2160000 [==============================] - 72s 33us/sample - loss: 0.5619 - acc: 0.7071 - auc: 0.7792 - val_loss: 0.5512 - val_acc: 0.7134 - val_auc: 0.7900\n", "Epoch 197: 2160000/2160000 [==============================] - 77s 36us/sample - loss: 0.5618 - acc: 0.7070 - auc: 0.7792 - val_loss: 0.5503 - val_acc: 0.7144 - val_auc: 0.7900\n", "Epoch 198: 2160000/2160000 [==============================] - 75s 35us/sample - loss: 0.5617 - acc: 0.7070 - auc: 0.7794 - val_loss: 0.5518 - val_acc: 0.7148 - val_auc: 0.7892\n", "Epoch 199: 2160000/2160000 [==============================] - 92s 43us/sample - loss: 0.5616 - acc: 0.7072 - auc: 0.7795 - val_loss: 0.5512 - val_acc: 0.7149 - val_auc: 0.7906\n", "Epoch 200: 2160000/2160000 [==============================] - 87s 40us/sample - loss: 0.5615 - acc: 0.7076 - auc: 0.7797 - val_loss: 0.5493 - val_acc: 0.7156 - val_auc: 0.7912\n" ] } ], "source": [ "print_logs('keras_model-keras_elu.log')" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.12" }, "toc": { "base_numbering": 1, "nav_menu": {}, "number_sections": false, "sideBar": true, "skip_h1_title": false, "title_cell": "Table of Contents", "title_sidebar": "Contents", "toc_cell": true, "toc_position": { "height": "calc(100% - 180px)", "left": "10px", "top": "150px", "width": "288px" }, "toc_section_display": true, "toc_window_display": false } }, "nbformat": 4, "nbformat_minor": 5 }