CPU info:
    CPU Model Name: Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz
    Hardware threads: 6
    Total Memory: 58719796 kB
-------------------------------------------------------------------
=== Running /cygdrive/c/jenkins/workspace/CNTK-Test-Windows-W1/x64/release/cntk.exe configFile=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining/cntk_dpt.cntk currentDirectory=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data RunDir=C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu DataDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data ConfigDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining OutputDir=C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu DeviceId=0 timestamping=true
CNTK 2.3.1+ (HEAD db192c, Jan 10 2018 22:59:43) at 2018/01/11 08:57:08

C:\jenkins\workspace\CNTK-Test-Windows-W1\x64\release\cntk.exe  configFile=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining/cntk_dpt.cntk  currentDirectory=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data  RunDir=C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu  DataDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data  ConfigDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining  OutputDir=C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu  DeviceId=0  timestamping=true
Changed current directory to C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data
-------------------------------------------------------------------
Build info: 

		Built time: Jan 10 2018 22:47:38
		Last modified date: Wed Jan 10 22:18:32 2018
		Build type: Release
		Build target: GPU
		With ASGD: yes
		Math lib: mkl
		CUDA version: 9.0.0
		CUDNN version: 7.0.5
		Build Branch: HEAD
		Build SHA1: db192cd3cb9ac688cae719c41e5930a4e3f628ea
		MPI distribution: Microsoft MPI
		MPI version: 7.0.12437.6
-------------------------------------------------------------------
-------------------------------------------------------------------
GPU info:

		Device[0]: cores = 3072; computeCapability = 5.2; type = "Tesla M60"; total memory = 8124 MB; free memory = 8001 MB
-------------------------------------------------------------------

Configuration After Processing and Variable Resolution:

configparameters: cntk_dpt.cntk:addLayer2=[    
    action = "edit"
    currLayer = 1
    newLayer = 2
    currModel = "C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/Pre1/cntkSpeech"
    newModel  = "C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/Pre2/cntkSpeech.0"
    editPath  = "C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining/add_layer.mel"
]

configparameters: cntk_dpt.cntk:addLayer3=[    
    action = "edit"
    currLayer = 2
    newLayer = 3
    currModel = "C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/Pre2/cntkSpeech"
    newModel  = "C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/cntkSpeech.0"
    editPath  = "C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining/add_layer.mel"
]

configparameters: cntk_dpt.cntk:command=dptPre1:addLayer2:dptPre2:addLayer3:speechTrain
configparameters: cntk_dpt.cntk:ConfigDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining
configparameters: cntk_dpt.cntk:currentDirectory=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data
configparameters: cntk_dpt.cntk:DataDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data
configparameters: cntk_dpt.cntk:deviceId=0
configparameters: cntk_dpt.cntk:dptPre1=[
    action = "train"
    modelPath = "C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/Pre1/cntkSpeech"
    NDLNetworkBuilder = [
        networkDescription = "C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining/dnn_1layer.txt"
    ]
]

configparameters: cntk_dpt.cntk:dptPre2=[
    action = "train"
    modelPath = "C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/Pre2/cntkSpeech"
    NDLNetworkBuilder = [
        networkDescription = "C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining/dnn_1layer.txt"
    ]
]

configparameters: cntk_dpt.cntk:globalInvStdPath=GlobalStats/var.363
configparameters: cntk_dpt.cntk:globalMeanPath=GlobalStats/mean.363
configparameters: cntk_dpt.cntk:globalPriorPath=GlobalStats/prior.132
configparameters: cntk_dpt.cntk:ndlMacros=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining/macros.txt
configparameters: cntk_dpt.cntk:OutputDir=C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu
configparameters: cntk_dpt.cntk:precision=float
configparameters: cntk_dpt.cntk:reader=[
    readerType = "HTKMLFReader"
    readMethod = "blockRandomize"
    miniBatchMode = "partial"
    randomize = "auto"
    verbosity = 0
    useMersenneTwisterRand=true
    features = [
        dim = 363
        type = "real"
        scpFile = "C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/glob_0000.scp"
    ]
    labels = [
        mlfFile = "C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/glob_0000.mlf"
        labelMappingFile = "C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/state.list"
        labelDim = 132
        labelType = "category"
    ]
]

configparameters: cntk_dpt.cntk:RunDir=C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu
configparameters: cntk_dpt.cntk:SGD=[
    epochSize = 81920
    minibatchSize = 256
    learningRatesPerMB = 0.8
    numMBsToShowResult = 10
    momentumPerMB = 0.9
    dropoutRate = 0.0
    maxEpochs = 2
]

configparameters: cntk_dpt.cntk:speechTrain=[
    action = "train"
    modelPath = "C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/cntkSpeech"
    deviceId = 0
    traceLevel = 1
    NDLNetworkBuilder = [
        networkDescription = "C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\DNN\DiscriminativePreTraining/dnn.txt"
    ]
    SGD = [
        epochSize = 81920
        minibatchSize = 256:512
        learningRatesPerMB = 0.8:1.6
        numMBsToShowResult = 10
        momentumPerSample = 0.999589
        dropoutRate = 0.0
        maxEpochs = 4
        gradUpdateType = "none"
        normWithAveMultiplier = true
        clippingThresholdPerSample = 1#INF
    ]
]

configparameters: cntk_dpt.cntk:timestamping=true
configparameters: cntk_dpt.cntk:traceLevel=1
01/11/2018 08:57:08: Commands: dptPre1 addLayer2 dptPre2 addLayer3 speechTrain
01/11/2018 08:57:08: precision = "float"

01/11/2018 08:57:08: ##############################################################################
01/11/2018 08:57:08: #                                                                            #
01/11/2018 08:57:08: # dptPre1 command (train action)                                             #
01/11/2018 08:57:08: #                                                                            #
01/11/2018 08:57:08: ##############################################################################

01/11/2018 08:57:08: 
Creating virgin network.
NDLBuilder Using GPU 0
Microsoft::MSR::CNTK::GPUMatrix<ElemType>::SetUniformRandomValue (GPU): creating curand object with seed 1, sizeof(ElemType)==4
reading script file C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/glob_0000.scp ... 948 entries
total 132 state names in state list C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/state.list
htkmlfreader: reading MLF file C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/glob_0000.mlf ... total 948 entries
...............................................................................................feature set 0: 252734 frames in 948 out of 948 utterances
label set 0: 129 classes
minibatchutterancesource: 948 utterances grouped into 3 chunks, av. chunk size: 316.0 utterances, 84244.7 frames
01/11/2018 08:57:09: 
Model has 19 nodes. Using GPU 0.

01/11/2018 08:57:09: Training criterion:   ce = CrossEntropyWithSoftmax
01/11/2018 08:57:09: Evaluation criterion: err = ClassificationError


Allocating matrices for forward and/or backward propagation.

Gradient Memory Aliasing: 2 are aliased.
	OL.t (gradient) reuses OL.z (gradient)

Memory Sharing: Out of 29 matrices, 11 are shared as 3, and 18 are not shared.

Here are the ones that share memory:
	{ HL1.W : [512 x 363] (gradient)
	  HL1.t : [512 x *]
	  HL1.y : [512 x 1 x *] }
	{ HL1.t : [512 x *] (gradient)
	  HL1.y : [512 x 1 x *] (gradient)
	  HL1.z : [512 x 1 x *]
	  OL.z : [132 x 1 x *] }
	{ HL1.z : [512 x 1 x *] (gradient)
	  OL.t : [132 x 1 x *]
	  OL.t : [132 x 1 x *] (gradient)
	  OL.z : [132 x 1 x *] (gradient) }

Here are the ones that don't share memory:
	{scaledLogLikelihood : [132 x 1 x *]}
	{features : [363 x *]}
	{globalMean : [363 x 1]}
	{OL.W : [132 x 512]}
	{HL1.b : [512 x 1]}
	{globalInvStd : [363 x 1]}
	{HL1.W : [512 x 363]}
	{OL.b : [132 x 1]}
	{globalPrior : [132 x 1]}
	{labels : [132 x *]}
	{featNorm : [363 x *]}
	{OL.b : [132 x 1] (gradient)}
	{logPrior : [132 x 1]}
	{HL1.b : [512 x 1] (gradient)}
	{ce : [1]}
	{OL.W : [132 x 512] (gradient)}
	{err : [1]}
	{ce : [1] (gradient)}


01/11/2018 08:57:09: Training 254084 parameters in 4 out of 4 parameter tensors and 10 nodes with gradient:

01/11/2018 08:57:09: 	Node 'HL1.W' (LearnableParameter operation) : [512 x 363]
01/11/2018 08:57:09: 	Node 'HL1.b' (LearnableParameter operation) : [512 x 1]
01/11/2018 08:57:09: 	Node 'OL.W' (LearnableParameter operation) : [132 x 512]
01/11/2018 08:57:09: 	Node 'OL.b' (LearnableParameter operation) : [132 x 1]

01/11/2018 08:57:09: No PreCompute nodes found, or all already computed. Skipping pre-computation step.

01/11/2018 08:57:09: Starting Epoch 1: learning rate per sample = 0.003125  effective momentum = 0.900000  momentum as time constant = 2429.8 samples
minibatchiterator: epoch 0: frames [0..81920] (first utterance at frame 0), data subset 0 of 1, with 1 datapasses
requiredata: determined feature kind as 33-dimensional 'USER' with frame shift 10.0 ms

01/11/2018 08:57:09: Starting minibatch loop.
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[   1-  10, 3.13%]: ce = 3.77545433 * 2560; err = 0.83984375 * 2560; time = 0.2028s; samplesPerSecond = 12620.3
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[  11-  20, 6.25%]: ce = 2.92129173 * 2560; err = 0.69921875 * 2560; time = 0.0086s; samplesPerSecond = 296949.3
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[  21-  30, 9.38%]: ce = 2.54243622 * 2560; err = 0.64882812 * 2560; time = 0.0084s; samplesPerSecond = 304537.1
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[  31-  40, 12.50%]: ce = 2.20117416 * 2560; err = 0.60156250 * 2560; time = 0.0084s; samplesPerSecond = 303684.5
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[  41-  50, 15.63%]: ce = 1.98474121 * 2560; err = 0.55273438 * 2560; time = 0.0081s; samplesPerSecond = 314620.0
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[  51-  60, 18.75%]: ce = 1.87129364 * 2560; err = 0.51562500 * 2560; time = 0.0087s; samplesPerSecond = 295933.2
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[  61-  70, 21.88%]: ce = 1.83400879 * 2560; err = 0.52812500 * 2560; time = 0.0082s; samplesPerSecond = 314068.0
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[  71-  80, 25.00%]: ce = 1.71646271 * 2560; err = 0.49335937 * 2560; time = 0.0083s; samplesPerSecond = 309399.2
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[  81-  90, 28.13%]: ce = 1.66541901 * 2560; err = 0.46328125 * 2560; time = 0.0085s; samplesPerSecond = 302944.2
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[  91- 100, 31.25%]: ce = 1.57725677 * 2560; err = 0.46054688 * 2560; time = 0.0082s; samplesPerSecond = 311367.3
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 101- 110, 34.38%]: ce = 1.61621246 * 2560; err = 0.45390625 * 2560; time = 0.0083s; samplesPerSecond = 309249.7
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 111- 120, 37.50%]: ce = 1.56063843 * 2560; err = 0.44140625 * 2560; time = 0.0080s; samplesPerSecond = 318289.2
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 121- 130, 40.63%]: ce = 1.52853241 * 2560; err = 0.44492188 * 2560; time = 0.0080s; samplesPerSecond = 318876.0
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 131- 140, 43.75%]: ce = 1.53461304 * 2560; err = 0.46210937 * 2560; time = 0.0080s; samplesPerSecond = 321345.6
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 141- 150, 46.88%]: ce = 1.46378479 * 2560; err = 0.44140625 * 2560; time = 0.0079s; samplesPerSecond = 322426.3
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 151- 160, 50.00%]: ce = 1.43345032 * 2560; err = 0.42617187 * 2560; time = 0.0079s; samplesPerSecond = 322999.9
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 161- 170, 53.13%]: ce = 1.43222961 * 2560; err = 0.42226562 * 2560; time = 0.0082s; samplesPerSecond = 313069.4
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 171- 180, 56.25%]: ce = 1.38003845 * 2560; err = 0.41250000 * 2560; time = 0.0079s; samplesPerSecond = 324305.2
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 181- 190, 59.38%]: ce = 1.35853271 * 2560; err = 0.40039063 * 2560; time = 0.0080s; samplesPerSecond = 321810.2
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 191- 200, 62.50%]: ce = 1.44864807 * 2560; err = 0.42656250 * 2560; time = 0.0079s; samplesPerSecond = 324313.4
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 201- 210, 65.63%]: ce = 1.43953552 * 2560; err = 0.42578125 * 2560; time = 0.0080s; samplesPerSecond = 320850.3
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 211- 220, 68.75%]: ce = 1.41762695 * 2560; err = 0.42617187 * 2560; time = 0.0079s; samplesPerSecond = 325401.7
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 221- 230, 71.88%]: ce = 1.33197937 * 2560; err = 0.40390625 * 2560; time = 0.0086s; samplesPerSecond = 296722.1
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 231- 240, 75.00%]: ce = 1.36100464 * 2560; err = 0.40429688 * 2560; time = 0.0079s; samplesPerSecond = 323105.9
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 241- 250, 78.13%]: ce = 1.30899048 * 2560; err = 0.39648438 * 2560; time = 0.0080s; samplesPerSecond = 320685.5
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 251- 260, 81.25%]: ce = 1.25351562 * 2560; err = 0.36953125 * 2560; time = 0.0079s; samplesPerSecond = 324601.2
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 261- 270, 84.38%]: ce = 1.30351257 * 2560; err = 0.39648438 * 2560; time = 0.0081s; samplesPerSecond = 315663.6
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 271- 280, 87.50%]: ce = 1.36050720 * 2560; err = 0.40898438 * 2560; time = 0.0079s; samplesPerSecond = 323673.7
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 281- 290, 90.63%]: ce = 1.29572754 * 2560; err = 0.39531250 * 2560; time = 0.0081s; samplesPerSecond = 317220.4
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 291- 300, 93.75%]: ce = 1.35762024 * 2560; err = 0.40898438 * 2560; time = 0.0079s; samplesPerSecond = 324251.8
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 301- 310, 96.88%]: ce = 1.32346802 * 2560; err = 0.39843750 * 2560; time = 0.0079s; samplesPerSecond = 322101.7
01/11/2018 08:57:09:  Epoch[ 1 of 2]-Minibatch[ 311- 320, 100.00%]: ce = 1.27053833 * 2560; err = 0.38203125 * 2560; time = 0.0076s; samplesPerSecond = 335021.5
01/11/2018 08:57:09: Finished Epoch[ 1 of 2]: [Training] ce = 1.65219517 * 81920; err = 0.46722412 * 81920; totalSamplesSeen = 81920; learningRatePerSample = 0.003125; epochTime=0.582083s
01/11/2018 08:57:09: SGD: Saving checkpoint model 'C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/Pre1/cntkSpeech.1'

01/11/2018 08:57:09: Starting Epoch 2: learning rate per sample = 0.003125  effective momentum = 0.900000  momentum as time constant = 2429.8 samples
minibatchiterator: epoch 1: frames [81920..163840] (first utterance at frame 81920), data subset 0 of 1, with 1 datapasses

01/11/2018 08:57:09: Starting minibatch loop.
01/11/2018 08:57:09:  Epoch[ 2 of 2]-Minibatch[   1-  10, 3.13%]: ce = 1.24904280 * 2560; err = 0.39492187 * 2560; time = 0.0105s; samplesPerSecond = 244543.2
01/11/2018 08:57:09:  Epoch[ 2 of 2]-Minibatch[  11-  20, 6.25%]: ce = 1.23917685 * 2560; err = 0.36992188 * 2560; time = 0.0081s; samplesPerSecond = 314825.1
01/11/2018 08:57:09:  Epoch[ 2 of 2]-Minibatch[  21-  30, 9.38%]: ce = 1.26081600 * 2560; err = 0.39531250 * 2560; time = 0.0080s; samplesPerSecond = 319820.1
01/11/2018 08:57:09:  Epoch[ 2 of 2]-Minibatch[  31-  40, 12.50%]: ce = 1.26097717 * 2560; err = 0.38281250 * 2560; time = 0.0083s; samplesPerSecond = 310246.6
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[  41-  50, 15.63%]: ce = 1.27839279 * 2560; err = 0.36953125 * 2560; time = 0.0080s; samplesPerSecond = 320569.0
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[  51-  60, 18.75%]: ce = 1.18358917 * 2560; err = 0.35742188 * 2560; time = 0.0080s; samplesPerSecond = 318772.7
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[  61-  70, 21.88%]: ce = 1.19746399 * 2560; err = 0.36992188 * 2560; time = 0.0079s; samplesPerSecond = 324584.8
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[  71-  80, 25.00%]: ce = 1.23055496 * 2560; err = 0.37070313 * 2560; time = 0.0079s; samplesPerSecond = 324914.3
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[  81-  90, 28.13%]: ce = 1.26867142 * 2560; err = 0.38828125 * 2560; time = 0.0078s; samplesPerSecond = 327566.8
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[  91- 100, 31.25%]: ce = 1.24915771 * 2560; err = 0.37500000 * 2560; time = 0.0078s; samplesPerSecond = 327969.7
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 101- 110, 34.38%]: ce = 1.20246201 * 2560; err = 0.36718750 * 2560; time = 0.0078s; samplesPerSecond = 329446.9
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 111- 120, 37.50%]: ce = 1.18079071 * 2560; err = 0.36289063 * 2560; time = 0.0094s; samplesPerSecond = 271307.1
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 121- 130, 40.63%]: ce = 1.16271973 * 2560; err = 0.36523438 * 2560; time = 0.0081s; samplesPerSecond = 317811.1
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 131- 140, 43.75%]: ce = 1.16420593 * 2560; err = 0.36484375 * 2560; time = 0.0080s; samplesPerSecond = 318511.0
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 141- 150, 46.88%]: ce = 1.14631195 * 2560; err = 0.34375000 * 2560; time = 0.0079s; samplesPerSecond = 323424.3
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 151- 160, 50.00%]: ce = 1.11735229 * 2560; err = 0.34609375 * 2560; time = 0.0081s; samplesPerSecond = 315243.8
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 161- 170, 53.13%]: ce = 1.17672577 * 2560; err = 0.35976562 * 2560; time = 0.0090s; samplesPerSecond = 283754.0
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 171- 180, 56.25%]: ce = 1.13726349 * 2560; err = 0.35312500 * 2560; time = 0.0084s; samplesPerSecond = 305372.7
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 181- 190, 59.38%]: ce = 1.14749298 * 2560; err = 0.35390625 * 2560; time = 0.0080s; samplesPerSecond = 320344.4
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 191- 200, 62.50%]: ce = 1.11475067 * 2560; err = 0.33515625 * 2560; time = 0.0080s; samplesPerSecond = 321943.7
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 201- 210, 65.63%]: ce = 1.16500397 * 2560; err = 0.35000000 * 2560; time = 0.0080s; samplesPerSecond = 318162.6
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 211- 220, 68.75%]: ce = 1.14435730 * 2560; err = 0.35234375 * 2560; time = 0.0079s; samplesPerSecond = 325546.5
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 221- 230, 71.88%]: ce = 1.09438171 * 2560; err = 0.34648438 * 2560; time = 0.0080s; samplesPerSecond = 319964.0
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 231- 240, 75.00%]: ce = 1.12633362 * 2560; err = 0.34531250 * 2560; time = 0.0078s; samplesPerSecond = 326638.9
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 241- 250, 78.13%]: ce = 1.09389648 * 2560; err = 0.33867188 * 2560; time = 0.0078s; samplesPerSecond = 326876.7
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 251- 260, 81.25%]: ce = 1.08799744 * 2560; err = 0.32968750 * 2560; time = 0.0078s; samplesPerSecond = 327001.9
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 261- 270, 84.38%]: ce = 1.12633667 * 2560; err = 0.33906250 * 2560; time = 0.0079s; samplesPerSecond = 325973.5
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 271- 280, 87.50%]: ce = 1.12987671 * 2560; err = 0.34375000 * 2560; time = 0.0083s; samplesPerSecond = 309186.2
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 281- 290, 90.63%]: ce = 1.11752319 * 2560; err = 0.34531250 * 2560; time = 0.0093s; samplesPerSecond = 275307.3
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 291- 300, 93.75%]: ce = 1.08401489 * 2560; err = 0.32695313 * 2560; time = 0.0080s; samplesPerSecond = 321705.0
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 301- 310, 96.88%]: ce = 1.08304138 * 2560; err = 0.34492187 * 2560; time = 0.0080s; samplesPerSecond = 321063.5
01/11/2018 08:57:10:  Epoch[ 2 of 2]-Minibatch[ 311- 320, 100.00%]: ce = 1.07171021 * 2560; err = 0.32734375 * 2560; time = 0.0076s; samplesPerSecond = 337962.7
01/11/2018 08:57:10: Finished Epoch[ 2 of 2]: [Training] ce = 1.16538725 * 81920; err = 0.35673828 * 81920; totalSamplesSeen = 163840; learningRatePerSample = 0.003125; epochTime=0.26542s
01/11/2018 08:57:10: SGD: Saving checkpoint model 'C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/Pre1/cntkSpeech'

01/11/2018 08:57:10: Action "train" complete.


01/11/2018 08:57:10: ##############################################################################
01/11/2018 08:57:10: #                                                                            #
01/11/2018 08:57:10: # addLayer2 command (edit action)                                            #
01/11/2018 08:57:10: #                                                                            #
01/11/2018 08:57:10: ##############################################################################


01/11/2018 08:57:10: Action "edit" complete.


01/11/2018 08:57:10: ##############################################################################
01/11/2018 08:57:10: #                                                                            #
01/11/2018 08:57:10: # dptPre2 command (train action)                                             #
01/11/2018 08:57:10: #                                                                            #
01/11/2018 08:57:10: ##############################################################################

01/11/2018 08:57:10: 
Starting from checkpoint. Loading network from 'C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/Pre2/cntkSpeech.0'.
NDLBuilder Using GPU 0
reading script file C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/glob_0000.scp ... 948 entries
total 132 state names in state list C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/state.list
htkmlfreader: reading MLF file C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/glob_0000.mlf ... total 948 entries
...............................................................................................feature set 0: 252734 frames in 948 out of 948 utterances
label set 0: 129 classes
minibatchutterancesource: 948 utterances grouped into 3 chunks, av. chunk size: 316.0 utterances, 84244.7 frames
01/11/2018 08:57:10: 
Model has 24 nodes. Using GPU 0.

01/11/2018 08:57:10: Training criterion:   ce = CrossEntropyWithSoftmax
01/11/2018 08:57:10: Evaluation criterion: err = ClassificationError

01/11/2018 08:57:10: Training 516740 parameters in 6 out of 6 parameter tensors and 15 nodes with gradient:

01/11/2018 08:57:10: 	Node 'HL1.W' (LearnableParameter operation) : [512 x 363]
01/11/2018 08:57:10: 	Node 'HL1.b' (LearnableParameter operation) : [512 x 1]
01/11/2018 08:57:10: 	Node 'HL2.W' (LearnableParameter operation) : [512 x 512]
01/11/2018 08:57:10: 	Node 'HL2.b' (LearnableParameter operation) : [512 x 1]
01/11/2018 08:57:10: 	Node 'OL.W' (LearnableParameter operation) : [132 x 512]
01/11/2018 08:57:10: 	Node 'OL.b' (LearnableParameter operation) : [132 x 1]

01/11/2018 08:57:10: No PreCompute nodes found, or all already computed. Skipping pre-computation step.

01/11/2018 08:57:10: Starting Epoch 1: learning rate per sample = 0.003125  effective momentum = 0.900000  momentum as time constant = 2429.8 samples
minibatchiterator: epoch 0: frames [0..81920] (first utterance at frame 0), data subset 0 of 1, with 1 datapasses
requiredata: determined feature kind as 33-dimensional 'USER' with frame shift 10.0 ms

01/11/2018 08:57:10: Starting minibatch loop.
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[   1-  10, 3.13%]: ce = 3.95232048 * 2560; err = 0.81835938 * 2560; time = 0.0178s; samplesPerSecond = 143523.5
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[  11-  20, 6.25%]: ce = 2.59509544 * 2560; err = 0.63632813 * 2560; time = 0.0093s; samplesPerSecond = 275363.6
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[  21-  30, 9.38%]: ce = 2.15305252 * 2560; err = 0.58046875 * 2560; time = 0.0094s; samplesPerSecond = 271569.1
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[  31-  40, 12.50%]: ce = 1.80730286 * 2560; err = 0.50039062 * 2560; time = 0.0092s; samplesPerSecond = 277065.3
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[  41-  50, 15.63%]: ce = 1.62435303 * 2560; err = 0.47460938 * 2560; time = 0.0092s; samplesPerSecond = 277236.3
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[  51-  60, 18.75%]: ce = 1.57792664 * 2560; err = 0.45468750 * 2560; time = 0.0094s; samplesPerSecond = 271646.9
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[  61-  70, 21.88%]: ce = 1.57253876 * 2560; err = 0.46523437 * 2560; time = 0.0092s; samplesPerSecond = 277323.4
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[  71-  80, 25.00%]: ce = 1.49025574 * 2560; err = 0.45156250 * 2560; time = 0.0092s; samplesPerSecond = 277988.9
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[  81-  90, 28.13%]: ce = 1.43519135 * 2560; err = 0.41289063 * 2560; time = 0.0092s; samplesPerSecond = 278164.1
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[  91- 100, 31.25%]: ce = 1.39548492 * 2560; err = 0.41093750 * 2560; time = 0.0094s; samplesPerSecond = 272363.6
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 101- 110, 34.38%]: ce = 1.40931549 * 2560; err = 0.40351562 * 2560; time = 0.0094s; samplesPerSecond = 273410.8
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 111- 120, 37.50%]: ce = 1.35583801 * 2560; err = 0.39492187 * 2560; time = 0.0092s; samplesPerSecond = 276900.4
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 121- 130, 40.63%]: ce = 1.31971741 * 2560; err = 0.38828125 * 2560; time = 0.0093s; samplesPerSecond = 276451.9
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 131- 140, 43.75%]: ce = 1.33088074 * 2560; err = 0.40664062 * 2560; time = 0.0092s; samplesPerSecond = 278052.3
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 141- 150, 46.88%]: ce = 1.27847748 * 2560; err = 0.38242188 * 2560; time = 0.0092s; samplesPerSecond = 277708.5
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 151- 160, 50.00%]: ce = 1.28628845 * 2560; err = 0.39296875 * 2560; time = 0.0094s; samplesPerSecond = 273235.7
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 161- 170, 53.13%]: ce = 1.29282837 * 2560; err = 0.37734375 * 2560; time = 0.0093s; samplesPerSecond = 276744.8
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 171- 180, 56.25%]: ce = 1.26449585 * 2560; err = 0.38867188 * 2560; time = 0.0092s; samplesPerSecond = 277979.9
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 181- 190, 59.38%]: ce = 1.28384094 * 2560; err = 0.38828125 * 2560; time = 0.0094s; samplesPerSecond = 273580.3
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 191- 200, 62.50%]: ce = 1.32117004 * 2560; err = 0.40000000 * 2560; time = 0.0092s; samplesPerSecond = 277850.1
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 201- 210, 65.63%]: ce = 1.30416870 * 2560; err = 0.38085938 * 2560; time = 0.0093s; samplesPerSecond = 274169.2
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 211- 220, 68.75%]: ce = 1.31772766 * 2560; err = 0.39765625 * 2560; time = 0.0092s; samplesPerSecond = 279207.7
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 221- 230, 71.88%]: ce = 1.24123840 * 2560; err = 0.37148437 * 2560; time = 0.0092s; samplesPerSecond = 278484.9
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 231- 240, 75.00%]: ce = 1.26621399 * 2560; err = 0.38476563 * 2560; time = 0.0092s; samplesPerSecond = 278639.5
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 241- 250, 78.13%]: ce = 1.23011169 * 2560; err = 0.37031250 * 2560; time = 0.0092s; samplesPerSecond = 277928.6
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 251- 260, 81.25%]: ce = 1.19255066 * 2560; err = 0.35820313 * 2560; time = 0.0094s; samplesPerSecond = 272537.6
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 261- 270, 84.38%]: ce = 1.20788269 * 2560; err = 0.36914063 * 2560; time = 0.0092s; samplesPerSecond = 278257.8
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 271- 280, 87.50%]: ce = 1.24570618 * 2560; err = 0.37656250 * 2560; time = 0.0092s; samplesPerSecond = 278327.4
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 281- 290, 90.63%]: ce = 1.17422485 * 2560; err = 0.34257813 * 2560; time = 0.0092s; samplesPerSecond = 278230.6
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 291- 300, 93.75%]: ce = 1.17809753 * 2560; err = 0.35312500 * 2560; time = 0.0092s; samplesPerSecond = 278001.0
01/11/2018 08:57:10:  Epoch[ 1 of 2]-Minibatch[ 301- 310, 96.88%]: ce = 1.19910583 * 2560; err = 0.35625000 * 2560; time = 0.0093s; samplesPerSecond = 273867.1
01/11/2018 08:57:11:  Epoch[ 1 of 2]-Minibatch[ 311- 320, 100.00%]: ce = 1.15553284 * 2560; err = 0.34570313 * 2560; time = 0.0092s; samplesPerSecond = 277440.6
01/11/2018 08:57:11: Finished Epoch[ 1 of 2]: [Training] ce = 1.48309174 * 81920; err = 0.42297363 * 81920; totalSamplesSeen = 81920; learningRatePerSample = 0.003125; epochTime=0.431829s
01/11/2018 08:57:11: SGD: Saving checkpoint model 'C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/Pre2/cntkSpeech.1'

01/11/2018 08:57:11: Starting Epoch 2: learning rate per sample = 0.003125  effective momentum = 0.900000  momentum as time constant = 2429.8 samples
minibatchiterator: epoch 1: frames [81920..163840] (first utterance at frame 81920), data subset 0 of 1, with 1 datapasses

01/11/2018 08:57:11: Starting minibatch loop.
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[   1-  10, 3.13%]: ce = 1.16412601 * 2560; err = 0.36210938 * 2560; time = 0.0118s; samplesPerSecond = 217151.6
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[  11-  20, 6.25%]: ce = 1.18867970 * 2560; err = 0.35742188 * 2560; time = 0.0094s; samplesPerSecond = 273253.2
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[  21-  30, 9.38%]: ce = 1.15690613 * 2560; err = 0.35625000 * 2560; time = 0.0095s; samplesPerSecond = 269925.5
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[  31-  40, 12.50%]: ce = 1.15283051 * 2560; err = 0.35390625 * 2560; time = 0.0093s; samplesPerSecond = 275817.5
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[  41-  50, 15.63%]: ce = 1.19624062 * 2560; err = 0.35000000 * 2560; time = 0.0094s; samplesPerSecond = 271981.6
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[  51-  60, 18.75%]: ce = 1.13569336 * 2560; err = 0.35000000 * 2560; time = 0.0093s; samplesPerSecond = 276661.0
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[  61-  70, 21.88%]: ce = 1.14269714 * 2560; err = 0.35390625 * 2560; time = 0.0092s; samplesPerSecond = 277859.2
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[  71-  80, 25.00%]: ce = 1.17199554 * 2560; err = 0.36562500 * 2560; time = 0.0096s; samplesPerSecond = 267620.1
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[  81-  90, 28.13%]: ce = 1.17918625 * 2560; err = 0.36679688 * 2560; time = 0.0092s; samplesPerSecond = 277880.3
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[  91- 100, 31.25%]: ce = 1.19158630 * 2560; err = 0.36484375 * 2560; time = 0.0094s; samplesPerSecond = 273390.4
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 101- 110, 34.38%]: ce = 1.14164963 * 2560; err = 0.34414062 * 2560; time = 0.0092s; samplesPerSecond = 278097.6
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 111- 120, 37.50%]: ce = 1.13930664 * 2560; err = 0.34257813 * 2560; time = 0.0092s; samplesPerSecond = 277582.0
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 121- 130, 40.63%]: ce = 1.09886627 * 2560; err = 0.33906250 * 2560; time = 0.0092s; samplesPerSecond = 278712.3
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 131- 140, 43.75%]: ce = 1.12534027 * 2560; err = 0.34882812 * 2560; time = 0.0092s; samplesPerSecond = 278291.1
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 141- 150, 46.88%]: ce = 1.10109558 * 2560; err = 0.33359375 * 2560; time = 0.0095s; samplesPerSecond = 269584.4
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 151- 160, 50.00%]: ce = 1.08001862 * 2560; err = 0.34101562 * 2560; time = 0.0092s; samplesPerSecond = 278557.6
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 161- 170, 53.13%]: ce = 1.12076874 * 2560; err = 0.33359375 * 2560; time = 0.0101s; samplesPerSecond = 254566.8
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 171- 180, 56.25%]: ce = 1.07955017 * 2560; err = 0.33476563 * 2560; time = 0.0093s; samplesPerSecond = 274251.4
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 181- 190, 59.38%]: ce = 1.11439514 * 2560; err = 0.34531250 * 2560; time = 0.0093s; samplesPerSecond = 274522.0
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 191- 200, 62.50%]: ce = 1.08090973 * 2560; err = 0.32578125 * 2560; time = 0.0097s; samplesPerSecond = 265057.0
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 201- 210, 65.63%]: ce = 1.12362366 * 2560; err = 0.33281250 * 2560; time = 0.0216s; samplesPerSecond = 118721.9
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 211- 220, 68.75%]: ce = 1.09581451 * 2560; err = 0.33554688 * 2560; time = 0.0096s; samplesPerSecond = 266306.0
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 221- 230, 71.88%]: ce = 1.04845886 * 2560; err = 0.32968750 * 2560; time = 0.0114s; samplesPerSecond = 224577.2
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 231- 240, 75.00%]: ce = 1.09396973 * 2560; err = 0.33945313 * 2560; time = 0.0094s; samplesPerSecond = 270979.8
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 241- 250, 78.13%]: ce = 1.09650269 * 2560; err = 0.34140625 * 2560; time = 0.0096s; samplesPerSecond = 266930.8
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 251- 260, 81.25%]: ce = 1.07186279 * 2560; err = 0.32734375 * 2560; time = 0.0094s; samplesPerSecond = 273075.4
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 261- 270, 84.38%]: ce = 1.11242065 * 2560; err = 0.34296875 * 2560; time = 0.0094s; samplesPerSecond = 272991.0
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 271- 280, 87.50%]: ce = 1.09167480 * 2560; err = 0.33437500 * 2560; time = 0.0093s; samplesPerSecond = 276094.1
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 281- 290, 90.63%]: ce = 1.10017090 * 2560; err = 0.34414062 * 2560; time = 0.0093s; samplesPerSecond = 276410.1
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 291- 300, 93.75%]: ce = 1.09057312 * 2560; err = 0.32578125 * 2560; time = 0.0096s; samplesPerSecond = 266883.5
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 301- 310, 96.88%]: ce = 1.08012695 * 2560; err = 0.33281250 * 2560; time = 0.0094s; samplesPerSecond = 273793.9
01/11/2018 08:57:11:  Epoch[ 2 of 2]-Minibatch[ 311- 320, 100.00%]: ce = 1.07658386 * 2560; err = 0.33593750 * 2560; time = 0.0092s; samplesPerSecond = 277242.3
01/11/2018 08:57:11: Finished Epoch[ 2 of 2]: [Training] ce = 1.12011328 * 81920; err = 0.34349365 * 81920; totalSamplesSeen = 163840; learningRatePerSample = 0.003125; epochTime=0.321051s
01/11/2018 08:57:11: SGD: Saving checkpoint model 'C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/Pre2/cntkSpeech'

01/11/2018 08:57:11: Action "train" complete.


01/11/2018 08:57:11: ##############################################################################
01/11/2018 08:57:11: #                                                                            #
01/11/2018 08:57:11: # addLayer3 command (edit action)                                            #
01/11/2018 08:57:11: #                                                                            #
01/11/2018 08:57:11: ##############################################################################


01/11/2018 08:57:11: Action "edit" complete.


01/11/2018 08:57:11: ##############################################################################
01/11/2018 08:57:11: #                                                                            #
01/11/2018 08:57:11: # speechTrain command (train action)                                         #
01/11/2018 08:57:11: #                                                                            #
01/11/2018 08:57:11: ##############################################################################

01/11/2018 08:57:11: 
Starting from checkpoint. Loading network from 'C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/cntkSpeech.0'.
NDLBuilder Using GPU 0
reading script file C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/glob_0000.scp ... 948 entries
total 132 state names in state list C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/state.list
htkmlfreader: reading MLF file C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data/glob_0000.mlf ... total 948 entries
...............................................................................................feature set 0: 252734 frames in 948 out of 948 utterances
label set 0: 129 classes
minibatchutterancesource: 948 utterances grouped into 3 chunks, av. chunk size: 316.0 utterances, 84244.7 frames
01/11/2018 08:57:11: 
Model has 29 nodes. Using GPU 0.

01/11/2018 08:57:11: Training criterion:   ce = CrossEntropyWithSoftmax
01/11/2018 08:57:11: Evaluation criterion: err = ClassificationError

01/11/2018 08:57:11: Training 779396 parameters in 8 out of 8 parameter tensors and 20 nodes with gradient:

01/11/2018 08:57:11: 	Node 'HL1.W' (LearnableParameter operation) : [512 x 363]
01/11/2018 08:57:11: 	Node 'HL1.b' (LearnableParameter operation) : [512 x 1]
01/11/2018 08:57:11: 	Node 'HL2.W' (LearnableParameter operation) : [512 x 512]
01/11/2018 08:57:11: 	Node 'HL2.b' (LearnableParameter operation) : [512 x 1]
01/11/2018 08:57:11: 	Node 'HL3.W' (LearnableParameter operation) : [512 x 512]
01/11/2018 08:57:11: 	Node 'HL3.b' (LearnableParameter operation) : [512 x 1]
01/11/2018 08:57:11: 	Node 'OL.W' (LearnableParameter operation) : [132 x 512]
01/11/2018 08:57:11: 	Node 'OL.b' (LearnableParameter operation) : [132 x 1]

01/11/2018 08:57:11: No PreCompute nodes found, or all already computed. Skipping pre-computation step.

01/11/2018 08:57:11: Starting Epoch 1: learning rate per sample = 0.003125  effective momentum = 0.900117  momentum as time constant = 2432.7 samples
minibatchiterator: epoch 0: frames [0..81920] (first utterance at frame 0), data subset 0 of 1, with 1 datapasses
requiredata: determined feature kind as 33-dimensional 'USER' with frame shift 10.0 ms

01/11/2018 08:57:11: Starting minibatch loop.
01/11/2018 08:57:11:  Epoch[ 1 of 4]-Minibatch[   1-  10, 3.13%]: ce = 4.04514732 * 2560; err = 0.84101563 * 2560; time = 0.0213s; samplesPerSecond = 120301.3
01/11/2018 08:57:11:  Epoch[ 1 of 4]-Minibatch[  11-  20, 6.25%]: ce = 2.57487679 * 2560; err = 0.61679688 * 2560; time = 0.0119s; samplesPerSecond = 215637.1
01/11/2018 08:57:11:  Epoch[ 1 of 4]-Minibatch[  21-  30, 9.38%]: ce = 2.06998596 * 2560; err = 0.56523437 * 2560; time = 0.0118s; samplesPerSecond = 216435.6
01/11/2018 08:57:11:  Epoch[ 1 of 4]-Minibatch[  31-  40, 12.50%]: ce = 1.69130554 * 2560; err = 0.47031250 * 2560; time = 0.0118s; samplesPerSecond = 216706.7
01/11/2018 08:57:11:  Epoch[ 1 of 4]-Minibatch[  41-  50, 15.63%]: ce = 1.51569901 * 2560; err = 0.43671875 * 2560; time = 0.0118s; samplesPerSecond = 217013.5
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[  51-  60, 18.75%]: ce = 1.45793076 * 2560; err = 0.41914062 * 2560; time = 0.0118s; samplesPerSecond = 216783.8
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[  61-  70, 21.88%]: ce = 1.46249542 * 2560; err = 0.43203125 * 2560; time = 0.0118s; samplesPerSecond = 217131.3
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[  71-  80, 25.00%]: ce = 1.37602081 * 2560; err = 0.40351562 * 2560; time = 0.0118s; samplesPerSecond = 216759.9
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[  81-  90, 28.13%]: ce = 1.32697144 * 2560; err = 0.38632813 * 2560; time = 0.0118s; samplesPerSecond = 217125.8
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[  91- 100, 31.25%]: ce = 1.28866119 * 2560; err = 0.37617187 * 2560; time = 0.0118s; samplesPerSecond = 216783.8
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 101- 110, 34.38%]: ce = 1.31844482 * 2560; err = 0.38437500 * 2560; time = 0.0118s; samplesPerSecond = 216717.7
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 111- 120, 37.50%]: ce = 1.27721405 * 2560; err = 0.36992188 * 2560; time = 0.0118s; samplesPerSecond = 216743.4
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 121- 130, 40.63%]: ce = 1.24465790 * 2560; err = 0.37382813 * 2560; time = 0.0118s; samplesPerSecond = 217372.8
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 131- 140, 43.75%]: ce = 1.25987854 * 2560; err = 0.38710937 * 2560; time = 0.0118s; samplesPerSecond = 217426.4
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 141- 150, 46.88%]: ce = 1.20045929 * 2560; err = 0.35976562 * 2560; time = 0.0118s; samplesPerSecond = 216818.7
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 151- 160, 50.00%]: ce = 1.22033539 * 2560; err = 0.36914063 * 2560; time = 0.0118s; samplesPerSecond = 217223.4
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 161- 170, 53.13%]: ce = 1.21545715 * 2560; err = 0.36093750 * 2560; time = 0.0118s; samplesPerSecond = 216221.7
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 171- 180, 56.25%]: ce = 1.19536133 * 2560; err = 0.36406250 * 2560; time = 0.0118s; samplesPerSecond = 217144.2
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 181- 190, 59.38%]: ce = 1.21321716 * 2560; err = 0.36796875 * 2560; time = 0.0118s; samplesPerSecond = 216287.5
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 191- 200, 62.50%]: ce = 1.25707092 * 2560; err = 0.38085938 * 2560; time = 0.0118s; samplesPerSecond = 217063.2
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 201- 210, 65.63%]: ce = 1.25220337 * 2560; err = 0.36484375 * 2560; time = 0.0118s; samplesPerSecond = 216545.4
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 211- 220, 68.75%]: ce = 1.25466614 * 2560; err = 0.38789062 * 2560; time = 0.0118s; samplesPerSecond = 216430.1
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 221- 230, 71.88%]: ce = 1.18672180 * 2560; err = 0.35429688 * 2560; time = 0.0118s; samplesPerSecond = 216723.2
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 231- 240, 75.00%]: ce = 1.21309814 * 2560; err = 0.37539062 * 2560; time = 0.0118s; samplesPerSecond = 216316.7
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 241- 250, 78.13%]: ce = 1.18207397 * 2560; err = 0.35585937 * 2560; time = 0.0118s; samplesPerSecond = 216406.3
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 251- 260, 81.25%]: ce = 1.14777222 * 2560; err = 0.34140625 * 2560; time = 0.0119s; samplesPerSecond = 215848.0
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 261- 270, 84.38%]: ce = 1.13528748 * 2560; err = 0.35156250 * 2560; time = 0.0120s; samplesPerSecond = 212935.9
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 271- 280, 87.50%]: ce = 1.19689026 * 2560; err = 0.36328125 * 2560; time = 0.0119s; samplesPerSecond = 215957.2
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 281- 290, 90.63%]: ce = 1.13403015 * 2560; err = 0.33554688 * 2560; time = 0.0118s; samplesPerSecond = 216818.7
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 291- 300, 93.75%]: ce = 1.14353638 * 2560; err = 0.35273437 * 2560; time = 0.0118s; samplesPerSecond = 216552.8
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 301- 310, 96.88%]: ce = 1.15669556 * 2560; err = 0.34765625 * 2560; time = 0.0118s; samplesPerSecond = 216831.5
01/11/2018 08:57:12:  Epoch[ 1 of 4]-Minibatch[ 311- 320, 100.00%]: ce = 1.10986328 * 2560; err = 0.33359375 * 2560; time = 0.0118s; samplesPerSecond = 216464.9
01/11/2018 08:57:12: Finished Epoch[ 1 of 4]: [Training] ce = 1.41637592 * 81920; err = 0.40404053 * 81920; totalSamplesSeen = 81920; learningRatePerSample = 0.003125; epochTime=0.513195s
01/11/2018 08:57:12: SGD: Saving checkpoint model 'C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/cntkSpeech.1'

01/11/2018 08:57:12: Starting Epoch 2: learning rate per sample = 0.003125  effective momentum = 0.810210  momentum as time constant = 2432.7 samples
minibatchiterator: epoch 1: frames [81920..163840] (first utterance at frame 81920), data subset 0 of 1, with 1 datapasses

01/11/2018 08:57:12: Starting minibatch loop.
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[   1-  10, 6.25%]: ce = 1.26108437 * 5120; err = 0.37500000 * 5120; time = 0.0257s; samplesPerSecond = 199220.2
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[  11-  20, 12.50%]: ce = 1.40673923 * 5120; err = 0.40703125 * 5120; time = 0.0175s; samplesPerSecond = 292162.4
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[  21-  30, 18.75%]: ce = 1.22149639 * 5120; err = 0.35937500 * 5120; time = 0.0175s; samplesPerSecond = 292609.9
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[  31-  40, 25.00%]: ce = 1.13947525 * 5120; err = 0.35195312 * 5120; time = 0.0175s; samplesPerSecond = 292416.0
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[  41-  50, 31.25%]: ce = 1.15874138 * 5120; err = 0.35000000 * 5120; time = 0.0175s; samplesPerSecond = 292941.4
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[  51-  60, 37.50%]: ce = 1.13039322 * 5120; err = 0.33984375 * 5120; time = 0.0175s; samplesPerSecond = 293211.5
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[  61-  70, 43.75%]: ce = 1.10522003 * 5120; err = 0.34609375 * 5120; time = 0.0175s; samplesPerSecond = 293036.9
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[  71-  80, 50.00%]: ce = 1.07494049 * 5120; err = 0.33437500 * 5120; time = 0.0175s; samplesPerSecond = 293379.5
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[  81-  90, 56.25%]: ce = 1.08323288 * 5120; err = 0.32832031 * 5120; time = 0.0174s; samplesPerSecond = 293753.2
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[  91- 100, 62.50%]: ce = 1.10492630 * 5120; err = 0.35058594 * 5120; time = 0.0174s; samplesPerSecond = 293931.9
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[ 101- 110, 68.75%]: ce = 1.09108047 * 5120; err = 0.32636719 * 5120; time = 0.0174s; samplesPerSecond = 293717.8
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[ 111- 120, 75.00%]: ce = 1.06803894 * 5120; err = 0.33242187 * 5120; time = 0.0175s; samplesPerSecond = 293063.8
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[ 121- 130, 81.25%]: ce = 1.07306976 * 5120; err = 0.33281250 * 5120; time = 0.0175s; samplesPerSecond = 292412.7
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[ 131- 140, 87.50%]: ce = 1.20960236 * 5120; err = 0.36835937 * 5120; time = 0.0175s; samplesPerSecond = 293070.5
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[ 141- 150, 93.75%]: ce = 1.07773590 * 5120; err = 0.32851562 * 5120; time = 0.0175s; samplesPerSecond = 292705.2
01/11/2018 08:57:12:  Epoch[ 2 of 4]-Minibatch[ 151- 160, 100.00%]: ce = 1.05148163 * 5120; err = 0.31875000 * 5120; time = 0.0175s; samplesPerSecond = 292899.5
01/11/2018 08:57:12: Finished Epoch[ 2 of 4]: [Training] ce = 1.14107866 * 81920; err = 0.34686279 * 81920; totalSamplesSeen = 163840; learningRatePerSample = 0.003125; epochTime=0.291842s
01/11/2018 08:57:12: SGD: Saving checkpoint model 'C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/cntkSpeech.2'

01/11/2018 08:57:12: Starting Epoch 3: learning rate per sample = 0.003125  effective momentum = 0.810210  momentum as time constant = 2432.7 samples
minibatchiterator: epoch 2: frames [163840..245760] (first utterance at frame 163840), data subset 0 of 1, with 1 datapasses

01/11/2018 08:57:12: Starting minibatch loop.
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[   1-  10, 6.25%]: ce = 1.07412243 * 5120; err = 0.33593750 * 5120; time = 0.0189s; samplesPerSecond = 271282.7
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[  11-  20, 12.50%]: ce = 1.09550304 * 5120; err = 0.33242187 * 5120; time = 0.0175s; samplesPerSecond = 292454.4
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[  21-  30, 18.75%]: ce = 1.08694725 * 5120; err = 0.33945313 * 5120; time = 0.0176s; samplesPerSecond = 290772.0
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[  31-  40, 25.00%]: ce = 1.04788971 * 5120; err = 0.32480469 * 5120; time = 0.0176s; samplesPerSecond = 291659.8
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[  41-  50, 31.25%]: ce = 1.07330208 * 5120; err = 0.32773438 * 5120; time = 0.0176s; samplesPerSecond = 291693.0
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[  51-  60, 37.50%]: ce = 1.08705254 * 5120; err = 0.33222656 * 5120; time = 0.0178s; samplesPerSecond = 288117.9
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[  61-  70, 43.75%]: ce = 1.06946869 * 5120; err = 0.33320312 * 5120; time = 0.0175s; samplesPerSecond = 292292.5
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[  71-  80, 50.00%]: ce = 1.07995758 * 5120; err = 0.33769531 * 5120; time = 0.0175s; samplesPerSecond = 293139.3
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[  81-  90, 56.25%]: ce = 1.10155334 * 5120; err = 0.35058594 * 5120; time = 0.0175s; samplesPerSecond = 293030.2
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[  91- 100, 62.50%]: ce = 1.02064209 * 5120; err = 0.31406250 * 5120; time = 0.0175s; samplesPerSecond = 293332.4
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[ 101- 110, 68.75%]: ce = 1.02912445 * 5120; err = 0.32519531 * 5120; time = 0.0176s; samplesPerSecond = 290689.4
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[ 111- 120, 75.00%]: ce = 1.05624924 * 5120; err = 0.32734375 * 5120; time = 0.0175s; samplesPerSecond = 292871.0
01/11/2018 08:57:12:  Epoch[ 3 of 4]-Minibatch[ 121- 130, 81.25%]: ce = 1.06630859 * 5120; err = 0.33730469 * 5120; time = 0.0175s; samplesPerSecond = 293082.2
01/11/2018 08:57:13:  Epoch[ 3 of 4]-Minibatch[ 131- 140, 87.50%]: ce = 1.09063416 * 5120; err = 0.34375000 * 5120; time = 0.0177s; samplesPerSecond = 289543.6
01/11/2018 08:57:13:  Epoch[ 3 of 4]-Minibatch[ 141- 150, 93.75%]: ce = 1.02371521 * 5120; err = 0.31660156 * 5120; time = 0.0175s; samplesPerSecond = 293335.8
01/11/2018 08:57:13:  Epoch[ 3 of 4]-Minibatch[ 151- 160, 100.00%]: ce = 1.03207855 * 5120; err = 0.32617188 * 5120; time = 0.0174s; samplesPerSecond = 293662.2
01/11/2018 08:57:13: Finished Epoch[ 3 of 4]: [Training] ce = 1.06465931 * 81920; err = 0.33153076 * 81920; totalSamplesSeen = 245760; learningRatePerSample = 0.003125; epochTime=0.284911s
01/11/2018 08:57:13: SGD: Saving checkpoint model 'C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/cntkSpeech.3'

01/11/2018 08:57:13: Starting Epoch 4: learning rate per sample = 0.003125  effective momentum = 0.810210  momentum as time constant = 2432.7 samples
minibatchiterator: epoch 3: frames [245760..327680] (first utterance at frame 245760), data subset 0 of 1, with 1 datapasses

01/11/2018 08:57:13: Starting minibatch loop.
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[   1-  10, 6.25%]: ce = 1.02240515 * 5120; err = 0.32734375 * 5120; time = 0.0190s; samplesPerSecond = 268988.1
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[  11-  20, 12.50%]: ce = 1.00561662 * 4926; err = 0.31790499 * 4926; time = 0.0540s; samplesPerSecond = 91195.9
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[  21-  30, 18.75%]: ce = 1.02030258 * 5120; err = 0.31718750 * 5120; time = 0.0175s; samplesPerSecond = 291967.5
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[  31-  40, 25.00%]: ce = 1.03147869 * 5120; err = 0.32089844 * 5120; time = 0.0175s; samplesPerSecond = 292497.9
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[  41-  50, 31.25%]: ce = 1.03559341 * 5120; err = 0.32343750 * 5120; time = 0.0175s; samplesPerSecond = 292765.5
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[  51-  60, 37.50%]: ce = 0.99760704 * 5120; err = 0.31464844 * 5120; time = 0.0175s; samplesPerSecond = 292461.1
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[  61-  70, 43.75%]: ce = 1.01162643 * 5120; err = 0.31718750 * 5120; time = 0.0176s; samplesPerSecond = 290928.9
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[  71-  80, 50.00%]: ce = 1.00835876 * 5120; err = 0.30839844 * 5120; time = 0.0175s; samplesPerSecond = 292951.4
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[  81-  90, 56.25%]: ce = 0.97858810 * 5120; err = 0.31562500 * 5120; time = 0.0176s; samplesPerSecond = 290137.6
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[  91- 100, 62.50%]: ce = 0.98578568 * 5120; err = 0.30195312 * 5120; time = 0.0174s; samplesPerSecond = 293642.0
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[ 101- 110, 68.75%]: ce = 1.03475266 * 5120; err = 0.32089844 * 5120; time = 0.0175s; samplesPerSecond = 291947.5
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[ 111- 120, 75.00%]: ce = 0.98508987 * 5120; err = 0.30683594 * 5120; time = 0.0175s; samplesPerSecond = 293177.9
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[ 121- 130, 81.25%]: ce = 0.99634094 * 5120; err = 0.31250000 * 5120; time = 0.0175s; samplesPerSecond = 293154.4
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[ 131- 140, 87.50%]: ce = 0.96515045 * 5120; err = 0.29863281 * 5120; time = 0.0175s; samplesPerSecond = 292775.5
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[ 141- 150, 93.75%]: ce = 0.97302704 * 5120; err = 0.29843750 * 5120; time = 0.0175s; samplesPerSecond = 292593.2
01/11/2018 08:57:13:  Epoch[ 4 of 4]-Minibatch[ 151- 160, 100.00%]: ce = 0.96172943 * 5120; err = 0.30351563 * 5120; time = 0.0175s; samplesPerSecond = 292979.9
01/11/2018 08:57:13: Finished Epoch[ 4 of 4]: [Training] ce = 1.00105877 * 81920; err = 0.31295166 * 81920; totalSamplesSeen = 327680; learningRatePerSample = 0.003125; epochTime=0.322537s
01/11/2018 08:57:13: SGD: Saving checkpoint model 'C:\local\cygwin-2.8.2-x64\tmp\cntk-test-20180111085400.505371\Speech\DNN_DiscriminativePreTraining@release_gpu/models/cntkSpeech'

01/11/2018 08:57:13: Action "train" complete.

01/11/2018 08:57:13: __COMPLETED__
