CPU info:
    CPU Model Name: Intel(R) Xeon(R) CPU W3550 @ 3.07GHz
    Hardware threads: 4
    Total Memory: 12580388 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\LSTM/cntk.cntk currentDirectory=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data RunDir=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@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\LSTM OutputDir=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu DeviceId=0 timestamping=true speechTrain=[SGD=[momentumAsTimeConstant=0:6074.9]] modelSelector=0
CNTK 2.0.beta6.0+ (HEAD 5f1fab, Dec 15 2016 06:29:34) on cntk-muc02 at 2016/12/15 08:34:21

C:\jenkins\workspace\CNTK-Test-Windows-W1\x64\release\cntk.exe  configFile=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\LSTM/cntk.cntk  currentDirectory=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data  RunDir=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@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\LSTM  OutputDir=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu  DeviceId=0  timestamping=true  speechTrain=[SGD=[momentumAsTimeConstant=0:6074.9]]  modelSelector=0
Changed current directory to C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data
12/15/2016 08:34:22: -------------------------------------------------------------------
12/15/2016 08:34:22: Build info: 

12/15/2016 08:34:22: 		Built time: Dec 15 2016 06:29:34
12/15/2016 08:34:22: 		Last modified date: Wed Dec 14 12:53:20 2016
12/15/2016 08:34:22: 		Build type: Release
12/15/2016 08:34:22: 		Build target: GPU
12/15/2016 08:34:22: 		With ASGD: yes
12/15/2016 08:34:22: 		Math lib: mkl
12/15/2016 08:34:22: 		CUDA_PATH: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0
12/15/2016 08:34:22: 		CUB_PATH: c:\src\cub-1.4.1
12/15/2016 08:34:22: 		CUDNN_PATH: C:\local\cudnn-8.0-windows10-x64-v5.1
12/15/2016 08:34:22: 		Build Branch: HEAD
12/15/2016 08:34:22: 		Build SHA1: 5f1fabfe95e68af0787193f8849159f824d914d5 (modified)
12/15/2016 08:34:22: 		Built by svcphil on liana-08-w
12/15/2016 08:34:22: 		Build Path: C:\jenkins\workspace\CNTK-Build-Windows\Source\CNTK\
12/15/2016 08:34:22: -------------------------------------------------------------------
12/15/2016 08:34:22: -------------------------------------------------------------------
12/15/2016 08:34:22: GPU info:

12/15/2016 08:34:22: 		Device[0]: cores = 2496; computeCapability = 5.2; type = "Quadro M4000"; memory = 8192 MB
12/15/2016 08:34:22: -------------------------------------------------------------------

Configuration After Processing and Variable Resolution:

configparameters: cntk.cntk:// Note: These options are overridden from the command line in some test cases.=true
configparameters: cntk.cntk:command=speechCreate:speechTrain
configparameters: cntk.cntk:ConfigDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\LSTM
configparameters: cntk.cntk:currentDirectory=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data
configparameters: cntk.cntk:DataDir=C:\jenkins\workspace\CNTK-Test-Windows-W1\Tests\EndToEndTests\Speech\Data
configparameters: cntk.cntk:deviceId=0
configparameters: cntk.cntk:frameMode=false
configparameters: cntk.cntk:modelPath=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu/models/cntkSpeech.dnn
configparameters: cntk.cntk:modelSelector=0
configparameters: cntk.cntk:OutputDir=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu
configparameters: cntk.cntk:parallelTrain=false
configparameters: cntk.cntk:precision=float
configparameters: cntk.cntk:RunDir=C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu
configparameters: cntk.cntk:speechCreate={
    action = "edit"
    outputModelPath = "C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu/models/cntkSpeech.dnn.initial"
    BrainScriptNetworkBuilder = {
        useLayerNorm = true
        // dimensions (needed for both model and readers)
        baseFeatDim = 33
        featDim = 11 * baseFeatDim
        labelDim = 132
        // hidden dimensions
        innerCellDim  = 1024
        hiddenDim     = 256
        numLSTMLayers = 3        // number of hidden LSTM model layers
        modelUsingCuDNN5 = Sequential
        (
            MeanVarNorm :
            (_ => OptimizedRNNStack(ParameterTensor {0:0, initOutputRank=-1, init='heNormal', initValueScale=1/10}, _, hiddenDim, numLayers=numLSTMLayers, bidirectional=true)) :
            DenseLayer {labelDim, init='heUniform', initValueScale=1/3}
        )
        modelUsingLayersLikeCuDNN5 = Sequential
        (
            MeanVarNorm :
            LayerStack {numLSTMLayers, _ => Sequential (
                (x => Splice (
                    RecurrentLSTMLayer {hiddenDim, init='heUniform', initValueScale=1/10} (x) :
                    RecurrentLSTMLayer {hiddenDim, goBackwards=true, init='heUniform', initValueScale=1/10} (x)
                ))
            )} :
            DenseLayer {labelDim, init='heUniform', initValueScale=1/3}
        )
        modelUsingLayers = Sequential
        (
            MeanVarNorm :
            LayerStack {numLSTMLayers, _ => Sequential (
                if useLayerNorm then LayerNormalizationLayer{} else Identity :
                RecurrentLSTMLayer {hiddenDim, cellShape=innerCellDim, init='heUniform', initValueScale=1/3}
            )} :
            DenseLayer {labelDim, init='heUniform', initValueScale=1/3}
        )
        modelRegressionTest (features) =
        {
            useSelfStabilization = true
            featNorm = MeanVarNorm(features)
            // we define the LSTM locally for now, since the one in CNTK.core.bs has a slightly changed configuration that breaks this test
            Stabilize (x, enabled=true) =
                if enabled
                then {
beta = Exp (BS.Parameters.BiasParam ((1))) 
                    result = beta .* x
                }.result
                else x
            LSTMP (outputDim, cellDim=outputDim, x, inputDim=x.dim, prevState, enableSelfStabilization=false) =
            {
                _privateInnards = {       // encapsulate the inner workings
                    dh = prevState.h // previous values
                    dc = prevState.c
                    // parameter macros--these carry their own weight matrices
                    B() = BS.Parameters.BiasParam (cellDim)
                    W(v) = BS.Parameters.WeightParam (cellDim, Inferred)  * Stabilize (v, enabled=enableSelfStabilization) // input-to-hidden
                    H(h) = BS.Parameters.WeightParam (cellDim, outputDim) * Stabilize (h, enabled=enableSelfStabilization) // hidden-to-hidden
                    C(c) = BS.Parameters.DiagWeightParam (cellDim)       .* Stabilize (c, enabled=enableSelfStabilization) // cell-to-hiddden (note: applied elementwise)
                    // note: the W(x) here are all different, they all come with their own set of weights; same for H(dh), C(dc), and B()
                    it = Sigmoid (W(x) + B() + H(dh) + C(dc))          // input gate(t)
                    bit = it .* Tanh (W(x) + (H(dh) + B()))            // applied to tanh of input network
                    ft = Sigmoid (W(x) + B() + H(dh) + C(dc))          // forget-me-not gate(t)
                    bft = ft .* dc                                     // applied to cell(t-1)
                    ct = bft + bit                                     // c(t) is sum of both
                    ot = Sigmoid (W(x) + B() + H(dh) + C(ct))          // output gate(t)
                    ht = ot .* Tanh (ct)                               // applied to tanh(cell(t))
                }
                c = _privateInnards.ct          // cell value
                h = if outputDim != cellDim     // output/hidden state
                    then {                      // project
                        Wmr = BS.Parameters.WeightParam (outputDim, cellDim);
                        htp = Wmr * Stabilize (_privateInnards.ht, enabled=enableSelfStabilization)
                    }.htp         // TODO: ^^ extend BS syntax to allow to say: then { Wmr = WeightParam(outputDim, cellDim) } in Wmr * Stabilize (...)
                    else _privateInnards.ht     // no projection
                dim = outputDim
            }
            RecurrentLSTMP (outputDim, cellDim=outputDim.dim, x, inputDim=x.dim, previousHook=BS.RNNs.PreviousHC, enableSelfStabilization=false) =
            {
                prevState = previousHook (lstmState)
                inputDim1 = inputDim ; cellDim1 = cellDim ; enableSelfStabilization1 = enableSelfStabilization
                lstmState = LSTMP (outputDim, cellDim=cellDim1, x, inputDim=inputDim1, prevState, enableSelfStabilization=enableSelfStabilization1)
            }.lstmState // we return the state record (h,c)
            // define the stack of hidden LSTM layers  --TODO: change to RecurrentLSTMPStack(), change stabilizer config
            S(x) = Stabilize (x, enabled=useSelfStabilization)
            LSTMoutput[k:1..numLSTMLayers] =
                if k == 1
                then /*BS.RNNs.*/ RecurrentLSTMP (hiddenDim, cellDim=innerCellDim, /*S*/ (featNorm),        inputDim=baseFeatDim, enableSelfStabilization=useSelfStabilization).h
                else /*BS.RNNs.*/ RecurrentLSTMP (hiddenDim, cellDim=innerCellDim, /*S*/ (LSTMoutput[k-1]), inputDim=hiddenDim,   enableSelfStabilization=useSelfStabilization).h
            // and add a softmax layer on top
            W = BS.Parameters.WeightParam (labelDim, Inferred)
            B = BS.Parameters.BiasParam   (labelDim)
            // (unnecessarily using explicit Times with inferInputRankToMap in order to have a test for inferInputRankToMap parameter)
            z = Times (W, S(LSTMoutput[numLSTMLayers]), inferInputRankToMap=0) + B; // top-level input to Softmax
        }.z
        // features
        features = Input((1 : featDim),  tag='feature') // TEST: Artificially reading data transposed
        realFeatures = FlattenDimensions (Transpose (features), 1, 2)             //       and swapping them back to (featDim:1), for testing Transpose()
feashift = RowSlice(featDim - baseFeatDim, baseFeatDim, realFeatures);  
        labels   = Input(labelDim, tag='label')
        // link model to inputs
models = [| modelRegressionTest; modelUsingLayers; modelUsingCuDNN5; modelUsingLayersLikeCuDNN5 |]  
model = models[0]     
        z = model (feashift)
        // link model to training
        ce  = /*Pass*/ SumElements (ReduceLogSum (z) - TransposeTimes (labels,          z),  tag='criterion')  // manually-defined per-sample objective
        err = /*Pass*/ SumElements (BS.Constants.One - TransposeTimes (labels, Hardmax (z)), tag='evaluation') // also track frame errors
        // decoding
        logPrior = LogPrior(labels)	 
        scaledLogLikelihood = Pass (z - logPrior, tag='output') // using Pass() since we can't assign a tag to x - y
        featureNodes = (features)
        labelNodes = (labels)
        criterionNodes = (ce)
        evaluationNodes = (err)
        outputNodes = (scaledLogLikelihood)
    }
}

configparameters: cntk.cntk:speechTrain={
    action = "train"
    BrainScriptNetworkBuilder = (BS.Network.Load("C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu/models/cntkSpeech.dnn.initial"))
    SGD = {
        epochSize = 20480 ; maxEpochs = 4 ; minibatchSize = 20
        learningRatesPerMB = 0.5 ; momentumAsTimeConstant = 2500
        numMBsToShowResult = 10
        keepCheckPointFiles = true       
    }
    reader = {
        readerType = "HTKMLFReader"
        randomize = "auto" ; readMethod = "blockRandomize"
        nbruttsineachrecurrentiter = 32
        miniBatchMode = "partial" ; 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   = { labelDim = 132 ; labelType = "category" ; 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" }
    }
} [SGD=[momentumAsTimeConstant=0:6074.9]]

configparameters: cntk.cntk:timestamping=true
configparameters: cntk.cntk:traceLevel=1
configparameters: cntk.cntk:truncated=true
12/15/2016 08:34:22: Commands: speechCreate speechTrain
12/15/2016 08:34:22: precision = "float"

12/15/2016 08:34:22: ##############################################################################
12/15/2016 08:34:22: #                                                                            #
12/15/2016 08:34:22: # speechCreate command (edit action)                                         #
12/15/2016 08:34:22: #                                                                            #
12/15/2016 08:34:22: ##############################################################################

Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[132 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.
Node '<placeholder>' (LearnableParameter operation): Initializating Parameter[1024 x 0] as uniform later when dimensions are fully known.

Post-processing network...

6 roots:
	ce = SumElements()
	err = SumElements()
	logPrior._ = Mean()
	scaledLogLikelihood = Pass()
	z.featNorm.invStdDev = InvStdDev()
	z.featNorm.mean = Mean()

Loop[0] --> Loop_z.LSTMoutput[1].lstmState.h.htp -> 35 nodes

	z.LSTMoutput[1].prevState.h	z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0]	z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0]	z.LSTMoutput[1].prevState.c	z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result
	z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1]	z.LSTMoutput[1].lstmState._privateInnards.ft._	z.LSTMoutput[1].lstmState._privateInnards.ft
	z.LSTMoutput[1].lstmState._privateInnards.bft	z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0]	z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1]
	z.LSTMoutput[1].lstmState._privateInnards.it._	z.LSTMoutput[1].lstmState._privateInnards.it	z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result
	z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0]	z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]	z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z
	z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1]	z.LSTMoutput[1].lstmState._privateInnards.bit	z.LSTMoutput[1].lstmState._privateInnards.ct
	z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1]	z.LSTMoutput[1].lstmState._privateInnards.ot._
	z.LSTMoutput[1].lstmState._privateInnards.ot	z.LSTMoutput[1].lstmState._privateInnards.ht.ElementTimesArgs[1]	z.LSTMoutput[1].lstmState._privateInnards.ht
	z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].result	z.LSTMoutput[1].lstmState.h.htp

Loop[1] --> Loop_z.LSTMoutput[2].lstmState.h.htp -> 35 nodes

	z.LSTMoutput[2].prevState.h	z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0]	z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0]	z.LSTMoutput[2].prevState.c	z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result
	z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1]	z.LSTMoutput[2].lstmState._privateInnards.ft._	z.LSTMoutput[2].lstmState._privateInnards.ft
	z.LSTMoutput[2].lstmState._privateInnards.bft	z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0]	z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1]
	z.LSTMoutput[2].lstmState._privateInnards.it._	z.LSTMoutput[2].lstmState._privateInnards.it	z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result
	z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0]	z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]	z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z
	z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1]	z.LSTMoutput[2].lstmState._privateInnards.bit	z.LSTMoutput[2].lstmState._privateInnards.ct
	z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1]	z.LSTMoutput[2].lstmState._privateInnards.ot._
	z.LSTMoutput[2].lstmState._privateInnards.ot	z.LSTMoutput[2].lstmState._privateInnards.ht.ElementTimesArgs[1]	z.LSTMoutput[2].lstmState._privateInnards.ht
	z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].result	z.LSTMoutput[2].lstmState.h.htp

Loop[2] --> Loop_z.LSTMoutput[3].lstmState.h.htp -> 35 nodes

	z.LSTMoutput[3].prevState.h	z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0]	z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0]	z.LSTMoutput[3].prevState.c	z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result
	z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1]	z.LSTMoutput[3].lstmState._privateInnards.ft._	z.LSTMoutput[3].lstmState._privateInnards.ft
	z.LSTMoutput[3].lstmState._privateInnards.bft	z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0]	z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1]
	z.LSTMoutput[3].lstmState._privateInnards.it._	z.LSTMoutput[3].lstmState._privateInnards.it	z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result
	z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0]	z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]	z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z
	z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1]	z.LSTMoutput[3].lstmState._privateInnards.bit	z.LSTMoutput[3].lstmState._privateInnards.ct
	z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1]	z.LSTMoutput[3].lstmState._privateInnards.ot._
	z.LSTMoutput[3].lstmState._privateInnards.ot	z.LSTMoutput[3].lstmState._privateInnards.ht.ElementTimesArgs[1]	z.LSTMoutput[3].lstmState._privateInnards.ht
	z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].result	z.LSTMoutput[3].lstmState.h.htp

Validating network. 287 nodes to process in pass 1.

Validating --> z.W = LearnableParameter() :  -> [132 x 0]
Validating --> z.z.PlusArgs[0].y.beta._ = LearnableParameter() :  -> [1]
Validating --> z.z.PlusArgs[0].y.beta = Exp (z.z.PlusArgs[0].y.beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState.h.Wmr = LearnableParameter() :  -> [256 x 1024]
Validating --> z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState.h.Wmr = LearnableParameter() :  -> [256 x 1024]
Validating --> z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState.h.Wmr = LearnableParameter() :  -> [256 x 1024]
Validating --> z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> features = InputValue() :  -> [1 x 363 x *]
Validating --> realFeatures.x = TransposeDimensions (features) : [1 x 363 x *] -> [363 x 1 x *]
Validating --> realFeatures = Reshape (realFeatures.x) : [363 x 1 x *] -> [363 x *]
Validating --> feashift = Slice (realFeatures) : [363 x *] -> [33 x *]
Validating --> z.featNorm.mean = Mean (feashift) : [33 x *] -> [33]
Validating --> z.featNorm.ElementTimesArgs[0] = Minus (feashift, z.featNorm.mean) : [33 x *], [33] -> [33 x *]
Validating --> z.featNorm.invStdDev = InvStdDev (feashift) : [33 x *] -> [33]
Validating --> z.featNorm = ElementTimes (z.featNorm.ElementTimesArgs[0], z.featNorm.invStdDev) : [33 x *], [33] -> [33 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.featNorm) : [1], [33 x *] -> [33 x *]
Node 'z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 33].
Node 'z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 33] <- uniform(seed=1, init dims=[1024 x 33], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 33], [33 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.featNorm) : [1], [33 x *] -> [33 x *]
Node 'z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 33].
Node 'z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 33] <- uniform(seed=1, init dims=[1024 x 33], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 33], [33 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.featNorm) : [1], [33 x *] -> [33 x *]
Node 'z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 33].
Node 'z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 33] <- uniform(seed=1, init dims=[1024 x 33], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 33], [33 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta, z.featNorm) : [1], [33 x *] -> [33 x *]
Node 'z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 33].
Node 'z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 33] <- uniform(seed=1, init dims=[1024 x 33], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result) : [1024 x 33], [33 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[1].prevState.c) : [1], [0] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._ = Plus (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft = Sigmoid (z.LSTMoutput[1].lstmState._privateInnards.ft._) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bft = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft, z.LSTMoutput[1].prevState.c) : [1024 x *], [0] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[1].prevState.c) : [1], [0] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._ = Plus (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it = Sigmoid (z.LSTMoutput[1].lstmState._privateInnards.it._) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z = Plus (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1] = Tanh (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it, z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1]) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ct = Plus (z.LSTMoutput[1].lstmState._privateInnards.bft, z.LSTMoutput[1].lstmState._privateInnards.bit) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[1].lstmState._privateInnards.ct) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1] = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._ = Plus (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1]) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot = Sigmoid (z.LSTMoutput[1].lstmState._privateInnards.ot._) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ht.ElementTimesArgs[1] = Tanh (z.LSTMoutput[1].lstmState._privateInnards.ct) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ht = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot, z.LSTMoutput[1].lstmState._privateInnards.ht.ElementTimesArgs[1]) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta, z.LSTMoutput[1].lstmState._privateInnards.ht) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState.h.htp = Times (z.LSTMoutput[1].lstmState.h.Wmr, z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].result) : [256 x 1024], [1024 x *] -> [256 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].lstmState.h.htp) : [1], [256 x *] -> [256 x *]
Node 'z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 256].
Node 'z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 256] <- uniform(seed=1, init dims=[1024 x 256], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].lstmState.h.htp) : [1], [256 x *] -> [256 x *]
Node 'z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 256].
Node 'z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 256] <- uniform(seed=1, init dims=[1024 x 256], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].lstmState.h.htp) : [1], [256 x *] -> [256 x *]
Node 'z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 256].
Node 'z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 256] <- uniform(seed=1, init dims=[1024 x 256], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].lstmState.h.htp) : [1], [256 x *] -> [256 x *]
Node 'z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 256].
Node 'z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 256] <- uniform(seed=1, init dims=[1024 x 256], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[2].prevState.c) : [1], [0] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._ = Plus (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft = Sigmoid (z.LSTMoutput[2].lstmState._privateInnards.ft._) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bft = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft, z.LSTMoutput[2].prevState.c) : [1024 x *], [0] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[2].prevState.c) : [1], [0] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._ = Plus (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it = Sigmoid (z.LSTMoutput[2].lstmState._privateInnards.it._) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z = Plus (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1] = Tanh (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it, z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1]) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ct = Plus (z.LSTMoutput[2].lstmState._privateInnards.bft, z.LSTMoutput[2].lstmState._privateInnards.bit) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[2].lstmState._privateInnards.ct) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1] = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._ = Plus (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1]) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot = Sigmoid (z.LSTMoutput[2].lstmState._privateInnards.ot._) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ht.ElementTimesArgs[1] = Tanh (z.LSTMoutput[2].lstmState._privateInnards.ct) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ht = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot, z.LSTMoutput[2].lstmState._privateInnards.ht.ElementTimesArgs[1]) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta, z.LSTMoutput[2].lstmState._privateInnards.ht) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState.h.htp = Times (z.LSTMoutput[2].lstmState.h.Wmr, z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].result) : [256 x 1024], [1024 x *] -> [256 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].lstmState.h.htp) : [1], [256 x *] -> [256 x *]
Node 'z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 256].
Node 'z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 256] <- uniform(seed=1, init dims=[1024 x 256], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].lstmState.h.htp) : [1], [256 x *] -> [256 x *]
Node 'z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 256].
Node 'z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 256] <- uniform(seed=1, init dims=[1024 x 256], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].lstmState.h.htp) : [1], [256 x *] -> [256 x *]
Node 'z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 256].
Node 'z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 256] <- uniform(seed=1, init dims=[1024 x 256], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 0]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].lstmState.h.htp) : [1], [256 x *] -> [256 x *]
Node 'z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) operation: Tensor shape was inferred as [1024 x 256].
Node 'z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0]' (LearnableParameter operation): Initializing Parameter[1024 x 256] <- uniform(seed=1, init dims=[1024 x 256], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[3].prevState.c) : [1], [0] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._ = Plus (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft = Sigmoid (z.LSTMoutput[3].lstmState._privateInnards.ft._) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bft = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft, z.LSTMoutput[3].prevState.c) : [1024 x *], [0] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[3].prevState.c) : [1], [0] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._ = Plus (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it = Sigmoid (z.LSTMoutput[3].lstmState._privateInnards.it._) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [0] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [1] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z = Plus (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1] = Tanh (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it, z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1]) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ct = Plus (z.LSTMoutput[3].lstmState._privateInnards.bft, z.LSTMoutput[3].lstmState._privateInnards.bit) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[3].lstmState._privateInnards.ct) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1] = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._ = Plus (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1]) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot = Sigmoid (z.LSTMoutput[3].lstmState._privateInnards.ot._) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ht.ElementTimesArgs[1] = Tanh (z.LSTMoutput[3].lstmState._privateInnards.ct) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ht = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot, z.LSTMoutput[3].lstmState._privateInnards.ht.ElementTimesArgs[1]) : [1024 x *], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta, z.LSTMoutput[3].lstmState._privateInnards.ht) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState.h.htp = Times (z.LSTMoutput[3].lstmState.h.Wmr, z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].result) : [256 x 1024], [1024 x *] -> [256 x *]
Validating --> z.z.PlusArgs[0].y.result = ElementTimes (z.z.PlusArgs[0].y.beta, z.LSTMoutput[3].lstmState.h.htp) : [1], [256 x *] -> [256 x *]
Node 'z.W' (LearnableParameter operation) operation: Tensor shape was inferred as [132 x 256].
Node 'z.W' (LearnableParameter operation): Initializing Parameter[132 x 256] <- uniform(seed=1, init dims=[132 x 256], range=0.050000(0.050000*1.000000), onCPU=true.
)Validating --> z.z.PlusArgs[0] = Times (z.W, z.z.PlusArgs[0].y.result) : [132 x 256], [256 x *] -> [132 x *]
Validating --> z.B = LearnableParameter() :  -> [132]
Validating --> z = Plus (z.z.PlusArgs[0], z.B) : [132 x *], [132] -> [132 x *]
Validating --> ce.matrix.MinusArgs[0].r = ReduceElements (z) : [132 x *] -> [1 x *]
Validating --> labels = InputValue() :  -> [132 x *]
Validating --> ce.matrix.MinusArgs[1] = TransposeTimes (labels, z) : [132 x *], [132 x *] -> [1 x *]
Validating --> ce.matrix = Minus (ce.matrix.MinusArgs[0].r, ce.matrix.MinusArgs[1]) : [1 x *], [1 x *] -> [1 x *]
Validating --> ce = SumElements (ce.matrix) : [1 x *] -> [1]
Validating --> BS.Constants.One = LearnableParameter() :  -> [1]
Validating --> err.matrix.MinusArgs[1].rightMatrix = Hardmax (z) : [132 x *] -> [132 x *]
Validating --> err.matrix.MinusArgs[1] = TransposeTimes (labels, err.matrix.MinusArgs[1].rightMatrix) : [132 x *], [132 x *] -> [1 x *]
Validating --> err.matrix = Minus (BS.Constants.One, err.matrix.MinusArgs[1]) : [1], [1 x *] -> [1 x *]
Validating --> err = SumElements (err.matrix) : [1 x *] -> [1]
Validating --> logPrior._ = Mean (labels) : [132 x *] -> [132]
Validating --> logPrior = Log (logPrior._) : [132] -> [132]
Validating --> scaledLogLikelihood._ = Minus (z, logPrior) : [132 x *], [132] -> [132 x *]
Validating --> scaledLogLikelihood = Pass (scaledLogLikelihood._) : [132 x *] -> [132 x *]

Validating network. 197 nodes to process in pass 2.

Validating --> z.LSTMoutput[1].prevState.h = PastValue (z.LSTMoutput[1].lstmState.h.htp) : [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].prevState.c = PastValue (z.LSTMoutput[1].lstmState._privateInnards.ct) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[1].prevState.c) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[1].prevState.c) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[2].prevState.h = PastValue (z.LSTMoutput[2].lstmState.h.htp) : [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].prevState.c = PastValue (z.LSTMoutput[2].lstmState._privateInnards.ct) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[2].prevState.c) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[2].prevState.c) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]
Validating --> z.LSTMoutput[3].prevState.h = PastValue (z.LSTMoutput[3].lstmState.h.htp) : [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].prevState.c = PastValue (z.LSTMoutput[3].lstmState._privateInnards.ct) : [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[3].prevState.c) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[3].prevState.c) : [1], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256 x *] -> [256 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *] -> [1024 x *]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024 x *], [1024] -> [1024 x *]

Validating network. 45 nodes to process in pass 3.


Validating network, final pass.




Post-processing network complete.

12/15/2016 08:34:23: 
Model with 287 nodes saved as 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu/models/cntkSpeech.dnn.initial'.

12/15/2016 08:34:23: Action "edit" complete.


12/15/2016 08:34:23: ##############################################################################
12/15/2016 08:34:23: #                                                                            #
12/15/2016 08:34:23: # speechTrain command (train action)                                         #
12/15/2016 08:34:23: #                                                                            #
12/15/2016 08:34:23: ##############################################################################

parallelTrain option is not enabled. ParallelTrain config will be ignored.
12/15/2016 08:34:23: 
Creating virgin network.
Load: Loading model file: C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu/models/cntkSpeech.dnn.initial
Post-processing network...

6 roots:
	ce = SumElements()
	err = SumElements()
	logPrior._ = Mean()
	scaledLogLikelihood = Pass()
	z.featNorm.invStdDev = InvStdDev()
	z.featNorm.mean = Mean()

Loop[0] --> Loop_z.LSTMoutput[1].lstmState.h.htp -> 35 nodes

	z.LSTMoutput[1].prevState.h	z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0]	z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0]	z.LSTMoutput[1].prevState.c	z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result
	z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1]	z.LSTMoutput[1].lstmState._privateInnards.ft._	z.LSTMoutput[1].lstmState._privateInnards.ft
	z.LSTMoutput[1].lstmState._privateInnards.bft	z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0]	z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1]
	z.LSTMoutput[1].lstmState._privateInnards.it._	z.LSTMoutput[1].lstmState._privateInnards.it	z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result
	z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0]	z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]	z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z
	z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1]	z.LSTMoutput[1].lstmState._privateInnards.bit	z.LSTMoutput[1].lstmState._privateInnards.ct
	z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1]	z.LSTMoutput[1].lstmState._privateInnards.ot._
	z.LSTMoutput[1].lstmState._privateInnards.ot	z.LSTMoutput[1].lstmState._privateInnards.ht.ElementTimesArgs[1]	z.LSTMoutput[1].lstmState._privateInnards.ht
	z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].result	z.LSTMoutput[1].lstmState.h.htp

Loop[1] --> Loop_z.LSTMoutput[2].lstmState.h.htp -> 35 nodes

	z.LSTMoutput[2].prevState.h	z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0]	z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0]	z.LSTMoutput[2].prevState.c	z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result
	z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1]	z.LSTMoutput[2].lstmState._privateInnards.ft._	z.LSTMoutput[2].lstmState._privateInnards.ft
	z.LSTMoutput[2].lstmState._privateInnards.bft	z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0]	z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1]
	z.LSTMoutput[2].lstmState._privateInnards.it._	z.LSTMoutput[2].lstmState._privateInnards.it	z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result
	z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0]	z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]	z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z
	z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1]	z.LSTMoutput[2].lstmState._privateInnards.bit	z.LSTMoutput[2].lstmState._privateInnards.ct
	z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1]	z.LSTMoutput[2].lstmState._privateInnards.ot._
	z.LSTMoutput[2].lstmState._privateInnards.ot	z.LSTMoutput[2].lstmState._privateInnards.ht.ElementTimesArgs[1]	z.LSTMoutput[2].lstmState._privateInnards.ht
	z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].result	z.LSTMoutput[2].lstmState.h.htp

Loop[2] --> Loop_z.LSTMoutput[3].lstmState.h.htp -> 35 nodes

	z.LSTMoutput[3].prevState.h	z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0]	z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0]	z.LSTMoutput[3].prevState.c	z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result
	z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1]	z.LSTMoutput[3].lstmState._privateInnards.ft._	z.LSTMoutput[3].lstmState._privateInnards.ft
	z.LSTMoutput[3].lstmState._privateInnards.bft	z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result	z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]
	z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0]	z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1]
	z.LSTMoutput[3].lstmState._privateInnards.it._	z.LSTMoutput[3].lstmState._privateInnards.it	z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result
	z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0]	z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]	z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z
	z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1]	z.LSTMoutput[3].lstmState._privateInnards.bit	z.LSTMoutput[3].lstmState._privateInnards.ct
	z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result	z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1]	z.LSTMoutput[3].lstmState._privateInnards.ot._
	z.LSTMoutput[3].lstmState._privateInnards.ot	z.LSTMoutput[3].lstmState._privateInnards.ht.ElementTimesArgs[1]	z.LSTMoutput[3].lstmState._privateInnards.ht
	z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].result	z.LSTMoutput[3].lstmState.h.htp

Validating network. 287 nodes to process in pass 1.

Validating --> z.W = LearnableParameter() :  -> [132 x 256]
Validating --> z.z.PlusArgs[0].y.beta._ = LearnableParameter() :  -> [1]
Validating --> z.z.PlusArgs[0].y.beta = Exp (z.z.PlusArgs[0].y.beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState.h.Wmr = LearnableParameter() :  -> [256 x 1024]
Validating --> z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState.h.Wmr = LearnableParameter() :  -> [256 x 1024]
Validating --> z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState.h.Wmr = LearnableParameter() :  -> [256 x 1024]
Validating --> z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 33]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> features = InputValue() :  -> [1 x 363 x *1]
Validating --> realFeatures.x = TransposeDimensions (features) : [1 x 363 x *1] -> [363 x 1 x *1]
Validating --> realFeatures = Reshape (realFeatures.x) : [363 x 1 x *1] -> [363 x *1]
Validating --> feashift = Slice (realFeatures) : [363 x *1] -> [33 x *1]
Validating --> z.featNorm.mean = Mean (feashift) : [33 x *1] -> [33]
Validating --> z.featNorm.ElementTimesArgs[0] = Minus (feashift, z.featNorm.mean) : [33 x *1], [33] -> [33 x *1]
Validating --> z.featNorm.invStdDev = InvStdDev (feashift) : [33 x *1] -> [33]
Validating --> z.featNorm = ElementTimes (z.featNorm.ElementTimesArgs[0], z.featNorm.invStdDev) : [33 x *1], [33] -> [33 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.featNorm) : [1], [33 x *1] -> [33 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 33], [33 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 33]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.featNorm) : [1], [33 x *1] -> [33 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 33], [33 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 33]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.featNorm) : [1], [33 x *1] -> [33 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 33], [33 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 33]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta, z.featNorm) : [1], [33 x *1] -> [33 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result) : [1024 x 33], [33 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[1].prevState.c) : [1], [1024] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._ = Plus (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft = Sigmoid (z.LSTMoutput[1].lstmState._privateInnards.ft._) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bft = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft, z.LSTMoutput[1].prevState.c) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0] = Plus (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[1].prevState.c) : [1], [1024] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._ = Plus (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it = Sigmoid (z.LSTMoutput[1].lstmState._privateInnards.it._) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z = Plus (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1] = Tanh (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it, z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1]) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ct = Plus (z.LSTMoutput[1].lstmState._privateInnards.bft, z.LSTMoutput[1].lstmState._privateInnards.bit) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[1].lstmState._privateInnards.ct) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1] = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._ = Plus (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1]) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot = Sigmoid (z.LSTMoutput[1].lstmState._privateInnards.ot._) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ht.ElementTimesArgs[1] = Tanh (z.LSTMoutput[1].lstmState._privateInnards.ct) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ht = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot, z.LSTMoutput[1].lstmState._privateInnards.ht.ElementTimesArgs[1]) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta, z.LSTMoutput[1].lstmState._privateInnards.ht) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState.h.htp = Times (z.LSTMoutput[1].lstmState.h.Wmr, z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].result) : [256 x 1024], [1024 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].lstmState.h.htp) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].lstmState.h.htp) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].lstmState.h.htp) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].lstmState.h.htp) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[2].prevState.c) : [1], [1024] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._ = Plus (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft = Sigmoid (z.LSTMoutput[2].lstmState._privateInnards.ft._) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bft = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft, z.LSTMoutput[2].prevState.c) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0] = Plus (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[2].prevState.c) : [1], [1024] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._ = Plus (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it = Sigmoid (z.LSTMoutput[2].lstmState._privateInnards.it._) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z = Plus (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1] = Tanh (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it, z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1]) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ct = Plus (z.LSTMoutput[2].lstmState._privateInnards.bft, z.LSTMoutput[2].lstmState._privateInnards.bit) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[2].lstmState._privateInnards.ct) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1] = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._ = Plus (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1]) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot = Sigmoid (z.LSTMoutput[2].lstmState._privateInnards.ot._) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ht.ElementTimesArgs[1] = Tanh (z.LSTMoutput[2].lstmState._privateInnards.ct) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ht = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot, z.LSTMoutput[2].lstmState._privateInnards.ht.ElementTimesArgs[1]) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta, z.LSTMoutput[2].lstmState._privateInnards.ht) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState.h.htp = Times (z.LSTMoutput[2].lstmState.h.Wmr, z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].result) : [256 x 1024], [1024 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].lstmState.h.htp) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].lstmState.h.htp) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].lstmState.h.htp) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].lstmState.h.htp) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0] = LearnableParameter() :  -> [1024 x 256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._ = LearnableParameter() :  -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta = Exp (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._) : [1] -> [1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1] = LearnableParameter() :  -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[3].prevState.c) : [1], [1024] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._ = Plus (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft = Sigmoid (z.LSTMoutput[3].lstmState._privateInnards.ft._) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bft = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft, z.LSTMoutput[3].prevState.c) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0] = Plus (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[3].prevState.c) : [1], [1024] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._ = Plus (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it = Sigmoid (z.LSTMoutput[3].lstmState._privateInnards.it._) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256] -> [256]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024], [1024] -> [1024]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z = Plus (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1] = Tanh (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it, z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1]) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ct = Plus (z.LSTMoutput[3].lstmState._privateInnards.bft, z.LSTMoutput[3].lstmState._privateInnards.bit) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[3].lstmState._privateInnards.ct) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1] = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._ = Plus (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1]) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot = Sigmoid (z.LSTMoutput[3].lstmState._privateInnards.ot._) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ht.ElementTimesArgs[1] = Tanh (z.LSTMoutput[3].lstmState._privateInnards.ct) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ht = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot, z.LSTMoutput[3].lstmState._privateInnards.ht.ElementTimesArgs[1]) : [1024 x *1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta, z.LSTMoutput[3].lstmState._privateInnards.ht) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState.h.htp = Times (z.LSTMoutput[3].lstmState.h.Wmr, z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].result) : [256 x 1024], [1024 x *1] -> [256 x *1]
Validating --> z.z.PlusArgs[0].y.result = ElementTimes (z.z.PlusArgs[0].y.beta, z.LSTMoutput[3].lstmState.h.htp) : [1], [256 x *1] -> [256 x *1]
Validating --> z.z.PlusArgs[0] = Times (z.W, z.z.PlusArgs[0].y.result) : [132 x 256], [256 x *1] -> [132 x *1]
Validating --> z.B = LearnableParameter() :  -> [132]
Validating --> z = Plus (z.z.PlusArgs[0], z.B) : [132 x *1], [132] -> [132 x *1]
Validating --> ce.matrix.MinusArgs[0].r = ReduceElements (z) : [132 x *1] -> [1 x *1]
Validating --> labels = InputValue() :  -> [132 x *1]
Validating --> ce.matrix.MinusArgs[1] = TransposeTimes (labels, z) : [132 x *1], [132 x *1] -> [1 x *1]
Validating --> ce.matrix = Minus (ce.matrix.MinusArgs[0].r, ce.matrix.MinusArgs[1]) : [1 x *1], [1 x *1] -> [1 x *1]
Validating --> ce = SumElements (ce.matrix) : [1 x *1] -> [1]
Validating --> BS.Constants.One = LearnableParameter() :  -> [1]
Validating --> err.matrix.MinusArgs[1].rightMatrix = Hardmax (z) : [132 x *1] -> [132 x *1]
Validating --> err.matrix.MinusArgs[1] = TransposeTimes (labels, err.matrix.MinusArgs[1].rightMatrix) : [132 x *1], [132 x *1] -> [1 x *1]
Validating --> err.matrix = Minus (BS.Constants.One, err.matrix.MinusArgs[1]) : [1], [1 x *1] -> [1 x *1]
Validating --> err = SumElements (err.matrix) : [1 x *1] -> [1]
Validating --> logPrior._ = Mean (labels) : [132 x *1] -> [132]
Validating --> logPrior = Log (logPrior._) : [132] -> [132]
Validating --> scaledLogLikelihood._ = Minus (z, logPrior) : [132 x *1], [132] -> [132 x *1]
Validating --> scaledLogLikelihood = Pass (scaledLogLikelihood._) : [132 x *1] -> [132 x *1]

Validating network. 197 nodes to process in pass 2.

Validating --> z.LSTMoutput[1].prevState.h = PastValue (z.LSTMoutput[1].lstmState.h.htp) : [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].prevState.c = PastValue (z.LSTMoutput[1].lstmState._privateInnards.ct) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[1].prevState.c) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[1].prevState.c) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[1].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[2].prevState.h = PastValue (z.LSTMoutput[2].lstmState.h.htp) : [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].prevState.c = PastValue (z.LSTMoutput[2].lstmState._privateInnards.ct) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[2].prevState.c) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[2].prevState.c) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[2].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]
Validating --> z.LSTMoutput[3].prevState.h = PastValue (z.LSTMoutput[3].lstmState.h.htp) : [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].prevState.c = PastValue (z.LSTMoutput[3].lstmState._privateInnards.ct) : [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[3].prevState.c) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1] = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] = Times (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta, z.LSTMoutput[3].prevState.c) : [1], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1] = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result) : [1024], [1024 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result = ElementTimes (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta, z.LSTMoutput[3].prevState.h) : [1], [256 x *1] -> [256 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] = Times (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result) : [1024 x 256], [256 x *1] -> [1024 x *1]
Validating --> z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] = Plus (z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0], z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]) : [1024 x *1], [1024] -> [1024 x *1]

Validating network. 45 nodes to process in pass 3.


Validating network, final pass.




Post-processing network complete.

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
12/15/2016 08:34:23: 
Model has 287 nodes. Using GPU 0.

12/15/2016 08:34:23: Training criterion:   ce = SumElements
12/15/2016 08:34:23: Evaluation criterion: err = SumElements


Allocating matrices for forward and/or backward propagation.

Memory Sharing: Out of 556 matrices, 347 are shared as 132, and 209 are not shared.

	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0] : [1024 x 256] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0] : [1024] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0] : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bft : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0] : [1024 x 256] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] }
	{ z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._ : [1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit : [1024 x *1] }
	{ z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0] : [1024 x 256] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ct : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit : [1024 x *1] }
	{ z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0] : [1024 x *1] }
	{ z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta : [1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ht.ElementTimesArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1] : [1024] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0] : [1024 x 256] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it : [1024 x *1] }
	{ z.LSTMoutput[3].lstmState.h.Wmr : [256 x 1024] (gradient)
	  z.z.PlusArgs[0].y.result : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0] : [1024 x 33] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._ : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._ : [1024 x *1] }
	{ z.z.PlusArgs[0] : [132 x *1]
	  z.z.PlusArgs[0].y.beta : [1] (gradient) }
	{ z : [132 x *1]
	  z.W : [132 x 256] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1] : [1024] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0] : [1024 x *1] }
	{ z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta._ : [1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._ : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._ : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bft : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._ : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0] : [1024] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [33 x *1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1] : [1024] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] : [1024 x *1] }
	{ z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1] : [1024] (gradient)
	  z.LSTMoutput[2].prevState.h : [256 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.ot._ : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ht : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1] : [1024] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] : [1024 x 256] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[2].lstmState.h.Wmr : [256 x 1024] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] : [1024 x 256] (gradient) }
	{ z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] : [1024 x 256] (gradient) }
	{ z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._ : [1] (gradient) }
	{ ce.matrix.MinusArgs[0].r : [1 x *1]
	  z.LSTMoutput[3].lstmState.h.htp : [256 x *1] (gradient)
	  z.z.PlusArgs[0] : [132 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState.h.htp : [256 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].prevState.c : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] (gradient) }
	{ z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1] : [1024] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0] : [1024] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta : [1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ht : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta : [1] (gradient) }
	{ z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta : [1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0] : [1024 x 256] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._ : [1024 x *1] (gradient) }
	{ z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1] : [1024] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].result : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].prevState.c : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[2].lstmState.h.htp : [256 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ct : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] (gradient) }
	{ ce.matrix.MinusArgs[0].r : [1 x *1] (gradient)
	  z.B : [132] (gradient) }
	{ ce.matrix.MinusArgs[1] : [1 x *1]
	  z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta : [1] (gradient)
	  z.z.PlusArgs[0].y.beta._ : [1] (gradient) }
	{ ce.matrix : [1 x *1]
	  z : [132 x *1] (gradient)
	  z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].result : [1024 x *1] (gradient)
	  z.z.PlusArgs[0].y.result : [256 x *1] (gradient) }
	{ ce.matrix.MinusArgs[1] : [1 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ht : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bft : [1024 x *1] (gradient) }
	{ z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0] : [1024 x 256] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta : [1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._ : [1024 x *1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0] : [1024] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].prevState.c : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta : [1] (gradient) }
	{ ce.matrix : [1 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot : [1024 x *1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0] : [1024] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it : [1024 x *1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ot : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta : [1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._ : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft : [1024 x *1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0] : [1024 x 256] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta : [1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._ : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] (gradient) }
	{ z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1] : [1024] (gradient)
	  z.LSTMoutput[3].prevState.h : [256 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0] : [1024 x 256] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].result : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0] : [1024 x 256] (gradient)
	  z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1] : [1024 x *1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[1].prevState.h : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z : [1024 x *1] (gradient)
	  z.LSTMoutput[2].prevState.c : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[2].prevState.h : [256 x *1] }
	{ z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[3].prevState.h : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [33 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z : [1024 x *1] (gradient)
	  z.LSTMoutput[3].prevState.c : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._ : [1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._ : [1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] : [1024 x 33] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta._ : [1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] : [1024 x 33] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] : [1024 x 33] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [33 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [33 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result : [33 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [33 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta : [1] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] : [1024 x 256] (gradient) }
	{ z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._ : [1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1] : [1024] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].result : [256 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._ : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bft : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result : [33 x *1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1] : [1024] (gradient)
	  z.LSTMoutput[1].prevState.h : [256 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.bft : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0] : [1024] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1] : [1024] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [33 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0] : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] : [1024 x 256] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0] : [1024 x 256] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta : [1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._ : [1] (gradient) }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._ : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1] : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._ : [1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].result : [1024 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.it : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0] : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0] : [1024 x 256] (gradient) }
	{ z.LSTMoutput[1].lstmState.h.Wmr : [256 x 1024] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ht.ElementTimesArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].result : [256 x *1] }
	{ z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1] : [1024 x *1] (gradient)
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0] : [1024 x *1] }
	{ z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0] : [1024 x *1]
	  z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta : [1] (gradient)
	  z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta._ : [1] (gradient) }


12/15/2016 08:34:24: Training 6219945 parameters in 87 out of 87 parameter tensors and 269 nodes with gradient:

12/15/2016 08:34:24: 	Node 'z.B' (LearnableParameter operation) : [132]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 33]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 33]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 33]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 33]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState.h.Wmr' (LearnableParameter operation) : [256 x 1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[1].lstmState.h.htp.TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState.h.Wmr' (LearnableParameter operation) : [256 x 1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[2].lstmState.h.htp.TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.bit.ElementTimesArgs[1].z.PlusArgs[1].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[0].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[0]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ft._.PlusArgs[1].ElementTimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[0].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[0]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.it._.PlusArgs[1].ElementTimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[0].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[0].PlusArgs[1]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[0]' (LearnableParameter operation) : [1024 x 256]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[0].PlusArgs[1].TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[0]' (LearnableParameter operation) : [1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState._privateInnards.ot._.PlusArgs[1].ElementTimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState.h.Wmr' (LearnableParameter operation) : [256 x 1024]
12/15/2016 08:34:24: 	Node 'z.LSTMoutput[3].lstmState.h.htp.TimesArgs[1].beta._' (LearnableParameter operation) : [1]
12/15/2016 08:34:24: 	Node 'z.W' (LearnableParameter operation) : [132 x 256]
12/15/2016 08:34:24: 	Node 'z.z.PlusArgs[0].y.beta._' (LearnableParameter operation) : [1]


12/15/2016 08:34:24: Precomputing --> 3 PreCompute nodes found.

12/15/2016 08:34:24: 	z.featNorm.mean = Mean()
12/15/2016 08:34:24: 	z.featNorm.invStdDev = InvStdDev()
12/15/2016 08:34:24: 	logPrior._ = 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 08:34:25: Precomputing --> Completed.


12/15/2016 08:34:25: Starting Epoch 1: learning rate per sample = 0.000781  effective momentum = 0.000000  momentum as time constant = 0.0 samples
minibatchiterator: epoch 0: frames [0..20480] (first utterance at frame 0), data subset 0 of 1, with 1 datapasses

12/15/2016 08:34:25: Starting minibatch loop.
12/15/2016 08:34:28:  Epoch[ 1 of 4]-Minibatch[   1-  10, 0.98%]: ce = 4.76651276 * 6400; err = 0.88140625 * 6400; time = 2.6716s; samplesPerSecond = 2395.6
12/15/2016 08:34:30:  Epoch[ 1 of 4]-Minibatch[  11-  20, 1.95%]: ce = 4.59868011 * 6400; err = 0.88515625 * 6400; time = 2.5398s; samplesPerSecond = 2519.9
12/15/2016 08:34:33:  Epoch[ 1 of 4]-Minibatch[  21-  30, 2.93%]: ce = 4.57680396 * 5494; err = 0.90899163 * 5494; time = 2.5867s; samplesPerSecond = 2123.9
12/15/2016 08:34:35:  Epoch[ 1 of 4]-Minibatch[  31-  40, 3.91%]: ce = 4.47557362 * 2062; err = 0.91949564 * 2062; time = 2.5707s; samplesPerSecond = 802.1
12/15/2016 08:34:37: Finished Epoch[ 1 of 4]: [Training] ce = 4.63036333 * 20498; err = 0.89350181 * 20498; totalSamplesSeen = 20498; learningRatePerSample = 0.00078125001; epochTime=11.4141s
12/15/2016 08:34:37: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu/models/cntkSpeech.dnn.1'

12/15/2016 08:34:37: Starting Epoch 2: learning rate per sample = 0.000781  effective momentum = 0.900025  momentum as time constant = 6076.0 samples
minibatchiterator: epoch 1: frames [20480..40960] (first utterance at frame 20498), data subset 0 of 1, with 1 datapasses

12/15/2016 08:34:37: Starting minibatch loop.
12/15/2016 08:34:40:  Epoch[ 2 of 4]-Minibatch[   1-  10, 0.98%]: ce = 4.34373657 * 6400; err = 0.81421875 * 6400; time = 2.5302s; samplesPerSecond = 2529.4
12/15/2016 08:34:42:  Epoch[ 2 of 4]-Minibatch[  11-  20, 1.95%]: ce = 4.39863586 * 6400; err = 0.89078125 * 6400; time = 2.5262s; samplesPerSecond = 2533.4
12/15/2016 08:34:45:  Epoch[ 2 of 4]-Minibatch[  21-  30, 2.93%]: ce = 4.28678166 * 5626; err = 0.86260220 * 5626; time = 2.5592s; samplesPerSecond = 2198.4
12/15/2016 08:34:47:  Epoch[ 2 of 4]-Minibatch[  31-  40, 3.91%]: ce = 4.46916730 * 1816; err = 0.94438326 * 1816; time = 2.5767s; samplesPerSecond = 704.8
12/15/2016 08:34:50:  Epoch[ 2 of 4]-Minibatch[  41-  50, 4.88%]: ce = 4.74094013 * 238; err = 0.94117647 * 238; time = 2.5747s; samplesPerSecond = 92.4
12/15/2016 08:34:50: Finished Epoch[ 2 of 4]: [Training] ce = 4.36025245 * 20514; err = 0.86462903 * 20514; totalSamplesSeen = 41012; learningRatePerSample = 0.00078125001; epochTime=13.2957s
12/15/2016 08:34:51: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu/models/cntkSpeech.dnn.2'

12/15/2016 08:34:51: Starting Epoch 3: learning rate per sample = 0.000781  effective momentum = 0.900025  momentum as time constant = 6076.0 samples
minibatchiterator: epoch 2: frames [40960..61440] (first utterance at frame 41012), data subset 0 of 1, with 1 datapasses

12/15/2016 08:34:51: Starting minibatch loop.
12/15/2016 08:34:54:  Epoch[ 3 of 4]-Minibatch[   1-  10, 0.98%]: ce = 4.12664307 * 6400; err = 0.83187500 * 6400; time = 2.5290s; samplesPerSecond = 2530.7
12/15/2016 08:34:56:  Epoch[ 3 of 4]-Minibatch[  11-  20, 1.95%]: ce = 4.13185425 * 6400; err = 0.85656250 * 6400; time = 2.4926s; samplesPerSecond = 2567.5
12/15/2016 08:34:59:  Epoch[ 3 of 4]-Minibatch[  21-  30, 2.93%]: ce = 4.24645121 * 5748; err = 0.90657620 * 5748; time = 2.5319s; samplesPerSecond = 2270.2
12/15/2016 08:35:01:  Epoch[ 3 of 4]-Minibatch[  31-  40, 3.91%]: ce = 4.27430935 * 1828; err = 0.91630197 * 1828; time = 2.5375s; samplesPerSecond = 720.4
12/15/2016 08:35:02: Finished Epoch[ 3 of 4]: [Training] ce = 4.17555027 * 20598; err = 0.86823963 * 20598; totalSamplesSeen = 61610; learningRatePerSample = 0.00078125001; epochTime=11.3717s
12/15/2016 08:35:03: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu/models/cntkSpeech.dnn.3'

12/15/2016 08:35:03: Starting Epoch 4: learning rate per sample = 0.000781  effective momentum = 0.900025  momentum as time constant = 6076.0 samples
minibatchiterator: epoch 3: frames [61440..81920] (first utterance at frame 61610), data subset 0 of 1, with 1 datapasses

12/15/2016 08:35:03: Starting minibatch loop.
12/15/2016 08:35:06:  Epoch[ 4 of 4]-Minibatch[   1-  10, 0.98%]: ce = 4.02134796 * 6400; err = 0.82812500 * 6400; time = 2.5438s; samplesPerSecond = 2516.0
12/15/2016 08:35:08:  Epoch[ 4 of 4]-Minibatch[  11-  20, 1.95%]: ce = 3.98399384 * 6400; err = 0.85078125 * 6400; time = 2.5335s; samplesPerSecond = 2526.1
12/15/2016 08:35:11:  Epoch[ 4 of 4]-Minibatch[  21-  30, 2.93%]: ce = 4.29594791 * 5882; err = 0.90394424 * 5882; time = 2.5408s; samplesPerSecond = 2315.0
12/15/2016 08:35:13:  Epoch[ 4 of 4]-Minibatch[  31-  40, 3.91%]: ce = 4.36383398 * 1682; err = 0.95362663 * 1682; time = 2.5522s; samplesPerSecond = 659.0
12/15/2016 08:35:14: Finished Epoch[ 4 of 4]: [Training] ce = 4.11602613 * 20376; err = 0.86700039 * 20376; totalSamplesSeen = 81986; learningRatePerSample = 0.00078125001; epochTime=10.4423s
12/15/2016 08:35:14: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20161215082815.293809\Speech\LSTM_Truncated@release_gpu/models/cntkSpeech.dnn'

12/15/2016 08:35:14: Action "train" complete.

12/15/2016 08:35:14: __COMPLETED__
