Hi,
it stops after this message:
[NOTE] TOKEN_ACCURACY refers to token accuracy, i.e., (1.0 - token_error_rate).
EPOCH 1 RUNNING ... TAG: 10_1.0 lrate 4e-05,

Brief error:
ERROR (train-ctc-parallel:AddVecToRows():cuda-matrix.cc:541) cudaError_t 48 : "no kernel image is available for execution on the device" returned from 'cudaGetLastError()'

in python it finds device

torch.cuda.is_available()
True

Detailed error:
./exp/nml_seq_fw_seq_tw/train_lstm/log/tr.iter1.log
train-ctc-parallel --report-step=1000 --num-sequence=10 --frame-limit=25000 --learn-rate=0.00004 --momentum=0.9 --verbose=1 'ark,s,cs:apply-cmvn --norm-vars=true --utt2spk=ark:./exp/nml_seq_fw_seq_tw/train_tr95/utt2spk scp:./exp/nml_seq_fw_seq_tw/train_tr95/cmvn.scp scp:./exp/nml_seq_fw_seq_tw/train_lstm/train_10_1.0.scp ark:- | splice-feats --left-context=1 --right-context=1 ark:- ark:- | add-deltas ark:- ark:- | subsample-feats --n=3 --offset=1 ark:- ark:- |' 'ark:gunzip -c ./exp/nml_seq_fw_seq_tw/train_lstm/labels.tr.gz|' ./exp/nml_seq_fw_seq_tw/train_lstm/nnet/nnet.iter0 ./exp/nml_seq_fw_seq_tw/train_lstm/nnet/nnet.iter1

LOG (train-ctc-parallel:SelectGpuIdAuto():cuda-device.cc:262) Selecting from 1 GPUs
LOG (train-ctc-parallel:SelectGpuIdAuto():cuda-device.cc:277) cudaSetDevice(0): Tesla V100-PCIE-16GB free:15724M, used:428M, total:16152M, free/total:0.973502
LOG (train-ctc-parallel:SelectGpuIdAuto():cuda-device.cc:310) Selected device: 0 (automatically)
LOG (train-ctc-parallel:FinalizeActiveGpu():cuda-device.cc:194) The active GPU is [0]: Tesla V100-PCIE-16GB free:15676M, used:476M, total:16152M, free/total:0.97053 version 7.0
LOG (train-ctc-parallel:PrintMemoryUsage():cuda-device.cc:334) Memory used: 0 bytes.
LOG (train-ctc-parallel:DisableCaching():cuda-device.cc:731) Disabling caching of GPU memory.
LOG (train-ctc-parallel:SetUpdateAlgorithm():net.cc:483) Selecting SGD with momentum as optimization algorithm.
LOG (train-ctc-parallel:SetTrainMode():net.cc:408) Setting TrainMode for layer 0
LOG (train-ctc-parallel:SetTrainMode():net.cc:408) Setting TrainMode for layer 1
LOG (train-ctc-parallel:SetTrainMode():net.cc:408) Setting TrainMode for layer 2
LOG (train-ctc-parallel:SetTrainMode():net.cc:408) Setting TrainMode for layer 3

add-deltas ark:- ark:-
splice-feats --left-context=1 --right-context=1 ark:- ark:-
apply-cmvn --norm-vars=true --utt2spk=ark:./exp/nml_seq_fw_seq_tw/train_tr95/utt2spk scp:./exp/nml_seq_fw_seq_tw/train_tr95/cmvn.scp scp:./exp/nml_seq_fw_seq_tw/train_lstm/train_10_1.0.scp ark:-
subsample-feats --n=3 --offset=1 ark:- ark:-
LOG (train-ctc-parallel:main():train-ctc-parallel.cc:133) TRAINING STARTED

ERROR (train-ctc-parallel:AddVecToRows():cuda-matrix.cc:541) cudaError_t 48 : "no kernel image is available for execution on the device" returned from 'cudaGetLastError()'
WARNING (train-ctc-parallel:Close():kaldi-io.cc:446) Pipe gunzip -c ./exp/nml_seq_fw_seq_tw/train_lstm/labels.tr.gz| had nonzero return status 13
WARNING (train-ctc-parallel:Close():kaldi-io.cc:446) Pipe apply-cmvn --norm-vars=true --utt2spk=ark:./exp/nml_seq_fw_seq_tw/train_tr95/utt2spk scp:./exp/nml_seq_fw_seq_tw/train_tr95/cmvn.scp scp:./exp/nml_seq_fw_seq_tw/train_lstm/train_10_1.0.scp ark:- | splice-feats --left-context=1 --right-context=1 ark:- ark:- | add-deltas ark:- ark:- | subsample-feats --n=3 --offset=1 ark:- ark:- | had nonzero return status 36096

ERROR (train-ctc-parallel:AddVecToRows():cuda-matrix.cc:541) cudaError_t 48 : "no kernel image is available for execution on the device" returned from 'cudaGetLastError()'

[stack trace: ]
eesen::KaldiGetStackTraceabi:cxx11
eesen::KaldiErrorMessage::~KaldiErrorMessage()
eesen::CuMatrixBase::AddVecToRows(float, eesen::CuVectorBase const&, float)
eesen::BiLstmParallel::PropagateFncRecurrentDropoutPassForward(eesen::CuMatrixBase const&, int, int)
eesen::BiLstmParallel::PropagateFnc(eesen::CuMatrixBase const&, eesen::CuMatrixBase)
eesen::Layer::Propagate(eesen::CuMatrixBase const&, eesen::CuMatrix)
eesen::Net::Propagate(eesen::CuMatrixBase const&, eesen::CuMatrix*)
train-ctc-parallel(main+0x1494) [0x434c48]
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7fb368c82830]
train-ctc-parallel(_start+0x29) [0x432119]