CPU info:
    CPU Model Name: Intel(R) Xeon(R) CPU E5-2630 v2 @ 2.60GHz
    Hardware threads: 24
    Total Memory: 268381192 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\SVD/cntk.cntk currentDirectory=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data RunDir=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082728.104126\Speech_SVD@release_cpu DataDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data ConfigDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\SVD OutputDir=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082728.104126\Speech_SVD@release_cpu DeviceId=-1 timestamping=true
CNTK 2.0.beta6.0+ (HEAD 5f1fab, Dec 15 2016 06:29:34) on dphaim-26-new at 2016/12/15 08:33:44

C:\jenkins\workspace\CNTK-Test-Windows-W1\x64\release\cntk.exe  configFile=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\SVD/cntk.cntk  currentDirectory=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data  RunDir=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082728.104126\Speech_SVD@release_cpu  DataDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data  ConfigDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\SVD  OutputDir=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082728.104126\Speech_SVD@release_cpu  DeviceId=-1  timestamping=true
Changed current directory to C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data

12/15/2016 08:33:44: ##############################################################################
12/15/2016 08:33:44: #                                                                            #
12/15/2016 08:33:44: # speechTrain command (train action)                                         #
12/15/2016 08:33:44: #                                                                            #
12/15/2016 08:33:44: ##############################################################################

12/15/2016 08:33:44: 
Creating virgin network.
SimpleNetworkBuilder Using CPU
reading script file 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
12/15/2016 08:33:45: 
Model has 25 nodes. Using CPU.

12/15/2016 08:33:45: Training criterion:   CrossEntropyWithSoftmax = CrossEntropyWithSoftmax
12/15/2016 08:33:45: Evaluation criterion: EvalClassificationError = ClassificationError


Allocating matrices for forward and/or backward propagation.

Memory Sharing: Out of 40 matrices, 19 are shared as 8, and 21 are not shared.

	{ H1 : [512 x 1 x *]
	  W0*features : [512 x *] (gradient) }
	{ W0 : [512 x 363] (gradient)
	  W0*features+B0 : [512 x 1 x *] }
	{ B0 : [512 x 1] (gradient)
	  H1 : [512 x 1 x *] (gradient)
	  W1*H1+B1 : [512 x 1 x *] (gradient)
	  W2*H1 : [132 x 1 x *] }
	{ B1 : [512 x 1] (gradient)
	  H2 : [512 x 1 x *] (gradient)
	  HLast : [132 x 1 x *] (gradient) }
	{ W1 : [512 x 512] (gradient)
	  W1*H1+B1 : [512 x 1 x *] }
	{ W0*features+B0 : [512 x 1 x *] (gradient)
	  W1*H1 : [512 x 1 x *] }
	{ HLast : [132 x 1 x *]
	  W2 : [132 x 512] (gradient) }
	{ H2 : [512 x 1 x *]
	  W1*H1 : [512 x 1 x *] (gradient) }


12/15/2016 08:33:45: Training 516740 parameters in 6 out of 6 parameter tensors and 15 nodes with gradient:

12/15/2016 08:33:45: 	Node 'B0' (LearnableParameter operation) : [512 x 1]
12/15/2016 08:33:45: 	Node 'B1' (LearnableParameter operation) : [512 x 1]
12/15/2016 08:33:45: 	Node 'B2' (LearnableParameter operation) : [132 x 1]
12/15/2016 08:33:45: 	Node 'W0' (LearnableParameter operation) : [512 x 363]
12/15/2016 08:33:45: 	Node 'W1' (LearnableParameter operation) : [512 x 512]
12/15/2016 08:33:45: 	Node 'W2' (LearnableParameter operation) : [132 x 512]


12/15/2016 08:33:45: Precomputing --> 3 PreCompute nodes found.

12/15/2016 08:33:45: 	MeanOfFeatures = Mean()
12/15/2016 08:33:45: 	InvStdOfFeatures = InvStdDev()
12/15/2016 08:33:45: 	Prior = Mean()
minibatchiterator: epoch 0: frames [0..252734] (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

12/15/2016 08:33:49: Precomputing --> Completed.


12/15/2016 08:33:49: Starting Epoch 1: learning rate per sample = 0.015625  effective momentum = 0.900000  momentum as time constant = 607.4 samples
minibatchiterator: epoch 0: frames [0..20480] (first utterance at frame 0), data subset 0 of 1, with 1 datapasses

12/15/2016 08:33:49: Starting minibatch loop.
12/15/2016 08:33:49:  Epoch[ 1 of 3]-Minibatch[   1-  10, 3.13%]: CrossEntropyWithSoftmax = 4.59755211 * 640; EvalClassificationError = 0.93125000 * 640; time = 0.1653s; samplesPerSecond = 3871.0
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[  11-  20, 6.25%]: CrossEntropyWithSoftmax = 4.34610329 * 640; EvalClassificationError = 0.92031250 * 640; time = 0.1402s; samplesPerSecond = 4564.1
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[  21-  30, 9.38%]: CrossEntropyWithSoftmax = 3.98222656 * 640; EvalClassificationError = 0.89062500 * 640; time = 0.0561s; samplesPerSecond = 11402.7
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[  31-  40, 12.50%]: CrossEntropyWithSoftmax = 3.74152527 * 640; EvalClassificationError = 0.84531250 * 640; time = 0.0560s; samplesPerSecond = 11434.1
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[  41-  50, 15.63%]: CrossEntropyWithSoftmax = 3.83818665 * 640; EvalClassificationError = 0.86718750 * 640; time = 0.0560s; samplesPerSecond = 11437.4
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[  51-  60, 18.75%]: CrossEntropyWithSoftmax = 3.71641235 * 640; EvalClassificationError = 0.87500000 * 640; time = 0.0558s; samplesPerSecond = 11474.9
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[  61-  70, 21.88%]: CrossEntropyWithSoftmax = 3.41802368 * 640; EvalClassificationError = 0.79687500 * 640; time = 0.0555s; samplesPerSecond = 11540.5
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[  71-  80, 25.00%]: CrossEntropyWithSoftmax = 3.53833008 * 640; EvalClassificationError = 0.82812500 * 640; time = 0.1607s; samplesPerSecond = 3982.1
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[  81-  90, 28.13%]: CrossEntropyWithSoftmax = 3.50628052 * 640; EvalClassificationError = 0.81718750 * 640; time = 0.0557s; samplesPerSecond = 11484.4
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[  91- 100, 31.25%]: CrossEntropyWithSoftmax = 3.41477966 * 640; EvalClassificationError = 0.80781250 * 640; time = 0.0553s; samplesPerSecond = 11569.7
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[ 101- 110, 34.38%]: CrossEntropyWithSoftmax = 3.51030884 * 640; EvalClassificationError = 0.82812500 * 640; time = 0.0572s; samplesPerSecond = 11187.4
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[ 111- 120, 37.50%]: CrossEntropyWithSoftmax = 3.28365479 * 640; EvalClassificationError = 0.79375000 * 640; time = 0.0566s; samplesPerSecond = 11298.6
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[ 121- 130, 40.63%]: CrossEntropyWithSoftmax = 3.20931702 * 640; EvalClassificationError = 0.79531250 * 640; time = 0.0550s; samplesPerSecond = 11631.3
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[ 131- 140, 43.75%]: CrossEntropyWithSoftmax = 3.07460327 * 640; EvalClassificationError = 0.75468750 * 640; time = 0.0555s; samplesPerSecond = 11540.9
12/15/2016 08:33:50:  Epoch[ 1 of 3]-Minibatch[ 141- 150, 46.88%]: CrossEntropyWithSoftmax = 2.97528992 * 640; EvalClassificationError = 0.72031250 * 640; time = 0.1613s; samplesPerSecond = 3968.1
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 151- 160, 50.00%]: CrossEntropyWithSoftmax = 3.11968384 * 640; EvalClassificationError = 0.74531250 * 640; time = 0.2218s; samplesPerSecond = 2884.9
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 161- 170, 53.13%]: CrossEntropyWithSoftmax = 2.84171753 * 640; EvalClassificationError = 0.71093750 * 640; time = 0.0555s; samplesPerSecond = 11536.1
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 171- 180, 56.25%]: CrossEntropyWithSoftmax = 2.74031372 * 640; EvalClassificationError = 0.66093750 * 640; time = 0.0561s; samplesPerSecond = 11404.1
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 181- 190, 59.38%]: CrossEntropyWithSoftmax = 2.83858032 * 640; EvalClassificationError = 0.72656250 * 640; time = 0.0555s; samplesPerSecond = 11524.1
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 191- 200, 62.50%]: CrossEntropyWithSoftmax = 2.74630737 * 640; EvalClassificationError = 0.69218750 * 640; time = 0.1507s; samplesPerSecond = 4246.5
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 201- 210, 65.63%]: CrossEntropyWithSoftmax = 2.61033325 * 640; EvalClassificationError = 0.66250000 * 640; time = 0.0561s; samplesPerSecond = 11416.3
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 211- 220, 68.75%]: CrossEntropyWithSoftmax = 2.61330566 * 640; EvalClassificationError = 0.65000000 * 640; time = 0.0560s; samplesPerSecond = 11419.0
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 221- 230, 71.88%]: CrossEntropyWithSoftmax = 2.54591064 * 640; EvalClassificationError = 0.66406250 * 640; time = 0.0560s; samplesPerSecond = 11433.1
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 231- 240, 75.00%]: CrossEntropyWithSoftmax = 2.57565918 * 640; EvalClassificationError = 0.66093750 * 640; time = 0.0560s; samplesPerSecond = 11424.1
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 241- 250, 78.13%]: CrossEntropyWithSoftmax = 2.49163818 * 640; EvalClassificationError = 0.63281250 * 640; time = 0.0553s; samplesPerSecond = 11580.4
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 251- 260, 81.25%]: CrossEntropyWithSoftmax = 2.39955444 * 640; EvalClassificationError = 0.62812500 * 640; time = 0.0557s; samplesPerSecond = 11487.9
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 261- 270, 84.38%]: CrossEntropyWithSoftmax = 2.27033691 * 640; EvalClassificationError = 0.59375000 * 640; time = 0.0562s; samplesPerSecond = 11395.4
12/15/2016 08:33:51:  Epoch[ 1 of 3]-Minibatch[ 271- 280, 87.50%]: CrossEntropyWithSoftmax = 2.52111816 * 640; EvalClassificationError = 0.66093750 * 640; time = 0.0558s; samplesPerSecond = 11471.4
12/15/2016 08:33:52:  Epoch[ 1 of 3]-Minibatch[ 281- 290, 90.63%]: CrossEntropyWithSoftmax = 2.27800293 * 640; EvalClassificationError = 0.59062500 * 640; time = 0.1286s; samplesPerSecond = 4975.2
12/15/2016 08:33:52:  Epoch[ 1 of 3]-Minibatch[ 291- 300, 93.75%]: CrossEntropyWithSoftmax = 2.26782837 * 640; EvalClassificationError = 0.61093750 * 640; time = 0.0556s; samplesPerSecond = 11515.1
12/15/2016 08:33:52:  Epoch[ 1 of 3]-Minibatch[ 301- 310, 96.88%]: CrossEntropyWithSoftmax = 2.24590454 * 640; EvalClassificationError = 0.58593750 * 640; time = 0.0552s; samplesPerSecond = 11604.1
12/15/2016 08:33:52:  Epoch[ 1 of 3]-Minibatch[ 311- 320, 100.00%]: CrossEntropyWithSoftmax = 2.24415283 * 640; EvalClassificationError = 0.59843750 * 640; time = 0.0550s; samplesPerSecond = 11634.0
12/15/2016 08:33:52: Finished Epoch[ 1 of 3]: [Training] CrossEntropyWithSoftmax = 3.04696693 * 20480; EvalClassificationError = 0.73583984 * 20480; totalSamplesSeen = 20480; learningRatePerSample = 0.015625; epochTime=2.52594s
12/15/2016 08:33:52: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082728.104126\Speech_SVD@release_cpu/models/cntkSpeech.dnn.1'

12/15/2016 08:33:52: Starting Epoch 2: learning rate per sample = 0.001953  effective momentum = 0.656119  momentum as time constant = 607.5 samples
minibatchiterator: epoch 1: frames [20480..40960] (first utterance at frame 20480), data subset 0 of 1, with 1 datapasses

12/15/2016 08:33:52: Starting minibatch loop.
12/15/2016 08:33:52:  Epoch[ 2 of 3]-Minibatch[   1-  10, 12.50%]: CrossEntropyWithSoftmax = 2.14624214 * 2560; EvalClassificationError = 0.56953125 * 2560; time = 0.2487s; samplesPerSecond = 10292.7
12/15/2016 08:33:52:  Epoch[ 2 of 3]-Minibatch[  11-  20, 25.00%]: CrossEntropyWithSoftmax = 2.06174126 * 2560; EvalClassificationError = 0.55742187 * 2560; time = 0.1435s; samplesPerSecond = 17838.1
12/15/2016 08:33:52:  Epoch[ 2 of 3]-Minibatch[  21-  30, 37.50%]: CrossEntropyWithSoftmax = 2.04994278 * 2560; EvalClassificationError = 0.55351562 * 2560; time = 0.1413s; samplesPerSecond = 18121.7
12/15/2016 08:33:53:  Epoch[ 2 of 3]-Minibatch[  31-  40, 50.00%]: CrossEntropyWithSoftmax = 2.03695602 * 2560; EvalClassificationError = 0.56132812 * 2560; time = 0.4540s; samplesPerSecond = 5638.5
12/15/2016 08:33:53:  Epoch[ 2 of 3]-Minibatch[  41-  50, 62.50%]: CrossEntropyWithSoftmax = 2.03086166 * 2560; EvalClassificationError = 0.55664063 * 2560; time = 0.1425s; samplesPerSecond = 17965.8
12/15/2016 08:33:53:  Epoch[ 2 of 3]-Minibatch[  51-  60, 75.00%]: CrossEntropyWithSoftmax = 1.97306137 * 2560; EvalClassificationError = 0.53671875 * 2560; time = 0.2476s; samplesPerSecond = 10339.8
12/15/2016 08:33:53:  Epoch[ 2 of 3]-Minibatch[  61-  70, 87.50%]: CrossEntropyWithSoftmax = 1.96746063 * 2560; EvalClassificationError = 0.53164062 * 2560; time = 0.1418s; samplesPerSecond = 18049.9
12/15/2016 08:33:54:  Epoch[ 2 of 3]-Minibatch[  71-  80, 100.00%]: CrossEntropyWithSoftmax = 1.95498352 * 2560; EvalClassificationError = 0.53750000 * 2560; time = 0.3973s; samplesPerSecond = 6443.0
12/15/2016 08:33:54: Finished Epoch[ 2 of 3]: [Training] CrossEntropyWithSoftmax = 2.02765617 * 20480; EvalClassificationError = 0.55053711 * 20480; totalSamplesSeen = 40960; learningRatePerSample = 0.001953125; epochTime=1.9188s
12/15/2016 08:33:54: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082728.104126\Speech_SVD@release_cpu/models/cntkSpeech.dnn.2'

12/15/2016 08:33:54: Starting Epoch 3: learning rate per sample = 0.000098  effective momentum = 0.656119  momentum as time constant = 2429.9 samples
minibatchiterator: epoch 2: frames [40960..61440] (first utterance at frame 40960), data subset 0 of 1, with 1 datapasses

12/15/2016 08:33:54: Starting minibatch loop.
12/15/2016 08:33:55:  Epoch[ 3 of 3]-Minibatch[   1-  10, 50.00%]: CrossEntropyWithSoftmax = 1.95358448 * 10240; EvalClassificationError = 0.53603516 * 10240; time = 1.0329s; samplesPerSecond = 9913.8
12/15/2016 08:33:56:  Epoch[ 3 of 3]-Minibatch[  11-  20, 100.00%]: CrossEntropyWithSoftmax = 1.97540913 * 10240; EvalClassificationError = 0.55253906 * 10240; time = 0.6321s; samplesPerSecond = 16199.6
12/15/2016 08:33:56: Finished Epoch[ 3 of 3]: [Training] CrossEntropyWithSoftmax = 1.96449680 * 20480; EvalClassificationError = 0.54428711 * 20480; totalSamplesSeen = 61440; learningRatePerSample = 9.7656251e-005; epochTime=1.66979s
12/15/2016 08:33:56: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082728.104126\Speech_SVD@release_cpu/models/cntkSpeech.dnn'

12/15/2016 08:33:56: Action "train" complete.


12/15/2016 08:33:56: ##############################################################################
12/15/2016 08:33:56: #                                                                            #
12/15/2016 08:33:56: # modelDecomposition command (SVD action)                                    #
12/15/2016 08:33:56: #                                                                            #
12/15/2016 08:33:56: ##############################################################################

--------------------------------------------------------------------------------------------
ParameterSVD: start to process group 0 with KeepRatio=0.50
--------------------------------------------------------------------------------------------
Performing SVD for a   512-by-363   matrix (node name: W0                  ) ---  computation time  0.12 secs ;  keep 50.0% energy ===> keep   104 svd values (reduce to 49.0% parameters) 
Performing SVD for a   512-by-512   matrix (node name: W1                  ) ---  computation time  0.34 secs ;  keep 50.0% energy ===> keep   128 svd values (reduce to 50.0% parameters) 
Performing SVD for a   132-by-512   matrix (node name: W2                  ) ---  computation time  0.02 secs ;  keep 50.0% energy ===> keep    32 svd values (reduce to 30.5% parameters) 


12/15/2016 08:33:56: ##############################################################################
12/15/2016 08:33:56: #                                                                            #
12/15/2016 08:33:56: # SVDTrain command (train action)                                            #
12/15/2016 08:33:56: #                                                                            #
12/15/2016 08:33:56: ##############################################################################

12/15/2016 08:33:56: 
Starting from checkpoint. Loading network from 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082728.104126\Speech_SVD@release_cpu/models/cntkSpeech.svd.dnn.0'.
NDLBuilder Using CPU
reading script file 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
12/15/2016 08:33:57: 
Model has 31 nodes. Using CPU.

12/15/2016 08:33:57: Training criterion:   CrossEntropyWithSoftmax = CrossEntropyWithSoftmax
12/15/2016 08:33:57: Evaluation criterion: EvalClassificationError = ClassificationError

12/15/2016 08:33:57: Training 243836 parameters in 9 out of 9 parameter tensors and 21 nodes with gradient:

12/15/2016 08:33:57: 	Node 'B0' (LearnableParameter operation) : [512 x 1]
12/15/2016 08:33:57: 	Node 'B1' (LearnableParameter operation) : [512 x 1]
12/15/2016 08:33:57: 	Node 'B2' (LearnableParameter operation) : [132 x 1]
12/15/2016 08:33:57: 	Node 'W0_U' (LearnableParameter operation) : [512 x 104]
12/15/2016 08:33:57: 	Node 'W0_V' (LearnableParameter operation) : [104 x 363]
12/15/2016 08:33:57: 	Node 'W1_U' (LearnableParameter operation) : [512 x 128]
12/15/2016 08:33:57: 	Node 'W1_V' (LearnableParameter operation) : [128 x 512]
12/15/2016 08:33:57: 	Node 'W2_U' (LearnableParameter operation) : [132 x 32]
12/15/2016 08:33:57: 	Node 'W2_V' (LearnableParameter operation) : [32 x 512]

12/15/2016 08:33:57: No PreCompute nodes found, or all already computed. Skipping pre-computation step.

12/15/2016 08:33:57: Starting Epoch 1: learning rate per sample = 0.000098  effective momentum = 0.656119  momentum as time constant = 2429.9 samples
minibatchiterator: epoch 0: frames [0..20480] (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

12/15/2016 08:33:57: Starting minibatch loop.
12/15/2016 08:33:58:  Epoch[ 1 of 2]-Minibatch[   1-  10, 50.00%]: CrossEntropyWithSoftmax = 1.92566795 * 10240; EvalClassificationError = 0.52519531 * 10240; time = 0.7999s; samplesPerSecond = 12802.4
12/15/2016 08:33:58:  Epoch[ 1 of 2]-Minibatch[  11-  20, 100.00%]: CrossEntropyWithSoftmax = 1.87599449 * 10240; EvalClassificationError = 0.52617187 * 10240; time = 0.6051s; samplesPerSecond = 16923.9
12/15/2016 08:33:58: Finished Epoch[ 1 of 2]: [Training] CrossEntropyWithSoftmax = 1.90083122 * 20480; EvalClassificationError = 0.52568359 * 20480; totalSamplesSeen = 20480; learningRatePerSample = 9.7656251e-005; epochTime=1.66644s
12/15/2016 08:33:58: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082728.104126\Speech_SVD@release_cpu/models/cntkSpeech.svd.dnn.1'

12/15/2016 08:33:58: Starting Epoch 2: learning rate per sample = 0.000098  effective momentum = 0.656119  momentum as time constant = 2429.9 samples
minibatchiterator: epoch 1: frames [20480..40960] (first utterance at frame 20480), data subset 0 of 1, with 1 datapasses

12/15/2016 08:33:58: Starting minibatch loop.
12/15/2016 08:33:59:  Epoch[ 2 of 2]-Minibatch[   1-  10, 50.00%]: CrossEntropyWithSoftmax = 1.89576473 * 10240; EvalClassificationError = 0.52421875 * 10240; time = 0.8964s; samplesPerSecond = 11423.3
12/15/2016 08:34:00:  Epoch[ 2 of 2]-Minibatch[  11-  20, 100.00%]: CrossEntropyWithSoftmax = 1.87905712 * 10240; EvalClassificationError = 0.52246094 * 10240; time = 0.7156s; samplesPerSecond = 14309.2
12/15/2016 08:34:00: Finished Epoch[ 2 of 2]: [Training] CrossEntropyWithSoftmax = 1.88741093 * 20480; EvalClassificationError = 0.52333984 * 20480; totalSamplesSeen = 40960; learningRatePerSample = 9.7656251e-005; epochTime=1.61826s
12/15/2016 08:34:00: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082728.104126\Speech_SVD@release_cpu/models/cntkSpeech.svd.dnn'

12/15/2016 08:34:00: Action "train" complete.

12/15/2016 08:34:00: __COMPLETED__
