Skip to content

Commit

Permalink
Updated baselines
Browse files Browse the repository at this point in the history
  • Loading branch information
@vmazalov
vmazalov committed Mar 20, 2017
1 parent d6eafc6 commit 54814cd
Show file tree
Hide file tree
Showing 8 changed files with 8 additions and 8 deletions.
2 changes: 1 addition & 1 deletion Tests/EndToEndTests/Speech/LSTM_CTC/baseline.linux.cpu.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -474,7 +474,7 @@ Here are the ones that don't share memory:
02/18/2017 07:06:38: Starting Epoch 1: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples

02/18/2017 07:06:38: Starting minibatch loop.
02/18/2017 07:06:39: Finished Epoch[ 1 of 10]: [Training] cr = 4.16293501 * 368; Err = 2.52941181 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=1.00518s
02/18/2017 07:06:39: Finished Epoch[ 1 of 10]: [Training] cr = 4.16293501 * 368; Err = 2.36764709 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=0.475233s
02/18/2017 07:06:39: SGD: Saving checkpoint model '/tmp/cntk-test-20170218070416.834755/Speech_LSTM_CTC@debug_gpu/models/simple.dnn.1'

02/18/2017 07:06:39: Starting Epoch 2: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples
Expand Down
2 changes: 1 addition & 1 deletion Tests/EndToEndTests/Speech/LSTM_CTC/baseline.linux.gpu.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,7 @@ Memory Sharing: Out of 200 matrices, 71 are shared as 27, and 129 are not shared
02/18/2017 07:06:38: Starting Epoch 1: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples

02/18/2017 07:06:38: Starting minibatch loop.
02/18/2017 07:06:39: Finished Epoch[ 1 of 10]: [Training] cr = 4.16293501 * 368; Err = 2.52941181 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=1.00518s
02/18/2017 07:06:39: Finished Epoch[ 1 of 10]: [Training] cr = 4.16293501 * 368; Err = 2.36764709 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=0.984606s
02/18/2017 07:06:39: SGD: Saving checkpoint model '/tmp/cntk-test-20170218070416.834755/Speech_LSTM_CTC@debug_gpu/models/simple.dnn.1'

02/18/2017 07:06:39: Starting Epoch 2: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples
Expand Down
2 changes: 1 addition & 1 deletion Tests/EndToEndTests/Speech/LSTM_CTC/baseline.windows.cpu.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -467,7 +467,7 @@ Here are the ones that don't share memory:
02/22/2017 21:20:37: Starting Epoch 1: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples

02/22/2017 21:20:37: Starting minibatch loop.
02/22/2017 21:20:38: Finished Epoch[ 1 of 10]: [Training] cr = 4.16293534 * 368; Err = 2.52941181 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=0.926568s
02/22/2017 21:20:38: Finished Epoch[ 1 of 10]: [Training] cr = 4.16293534 * 368; Err = 2.36764709 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=0.793934s
02/22/2017 21:20:38: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20170222211959.232036\Speech_LSTM_CTC@release_cpu/models/simple.dnn.1'

02/22/2017 21:20:38: Starting Epoch 2: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples
Expand Down
2 changes: 1 addition & 1 deletion Tests/EndToEndTests/Speech/LSTM_CTC/baseline.windows.gpu.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -340,7 +340,7 @@ Memory Sharing: Out of 200 matrices, 71 are shared as 27, and 129 are not shared
02/18/2017 09:28:11: Starting Epoch 1: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples

02/18/2017 09:28:11: Starting minibatch loop.
02/18/2017 09:28:13: Finished Epoch[ 1 of 10]: [Training] cr = 4.16293501 * 368; Err = 2.52941181 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=1.03913s
02/18/2017 09:28:13: Finished Epoch[ 1 of 10]: [Training] cr = 4.16293501 * 368; Err = 2.36764709 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=1.01936s
02/18/2017 09:28:13: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20170218092651.300722\Speech_LSTM_CTC@release_gpu/models/simple.dnn.1'

02/18/2017 09:28:13: Starting Epoch 2: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples
Expand Down
2 changes: 1 addition & 1 deletion Tests/EndToEndTests/Speech/LSTM_CTC_MLF/baseline.linux.cpu.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -474,7 +474,7 @@ Here are the ones that don't share memory:
02/18/2017 07:06:38: Starting Epoch 1: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples

02/18/2017 07:06:38: Starting minibatch loop.
02/18/2017 07:06:39: Finished Epoch[ 1 of 10]: [Training] cr = 4.16290018 * 368; Err = 2.51470582 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=0.486473s
02/18/2017 07:06:39: Finished Epoch[ 1 of 10]: [Training] cr = 4.16290018 * 368; Err = 2.36764709 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=0.515702s
02/18/2017 07:06:39: SGD: Saving checkpoint model '/tmp/cntk-test-20170218070416.834755/Speech_LSTM_CTC@debug_gpu/models/simple.dnn.1'

02/18/2017 07:06:39: Starting Epoch 2: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples
Expand Down
2 changes: 1 addition & 1 deletion Tests/EndToEndTests/Speech/LSTM_CTC_MLF/baseline.linux.gpu.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,7 @@ Memory Sharing: Out of 200 matrices, 71 are shared as 27, and 129 are not shared
02/18/2017 07:06:38: Starting Epoch 1: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples

02/18/2017 07:06:38: Starting minibatch loop.
02/18/2017 07:06:39: Finished Epoch[ 1 of 10]: [Training] cr = 4.16290018 * 368; Err = 2.51470582 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=1.20341s
02/18/2017 07:06:39: Finished Epoch[ 1 of 10]: [Training] cr = 4.16290018 * 368; Err = 2.36764709 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=1.21637s
02/18/2017 07:06:39: SGD: Saving checkpoint model '/tmp/cntk-test-20170218070416.834755/Speech_LSTM_CTC@debug_gpu/models/simple.dnn.1'

02/18/2017 07:06:39: Starting Epoch 2: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples
Expand Down
2 changes: 1 addition & 1 deletion Tests/EndToEndTests/Speech/LSTM_CTC_MLF/baseline.windows.cpu.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -467,7 +467,7 @@ Here are the ones that don't share memory:
02/22/2017 21:20:37: Starting Epoch 1: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples

02/22/2017 21:20:37: Starting minibatch loop.
02/22/2017 21:20:38: Finished Epoch[ 1 of 10]: [Training] cr = 4.16290018 * 368; Err = 2.51470582 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=0.926568s
02/22/2017 21:20:38: Finished Epoch[ 1 of 10]: [Training] cr = 4.16290018 * 368; Err = 2.36764709 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=0.963661s
02/22/2017 21:20:38: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20170222211959.232036\Speech_LSTM_CTC@release_cpu/models/simple.dnn.1'

02/22/2017 21:20:38: Starting Epoch 2: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples
Expand Down
2 changes: 1 addition & 1 deletion Tests/EndToEndTests/Speech/LSTM_CTC_MLF/baseline.windows.gpu.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -340,7 +340,7 @@ Memory Sharing: Out of 200 matrices, 71 are shared as 27, and 129 are not shared
02/18/2017 09:28:11: Starting Epoch 1: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples

02/18/2017 09:28:11: Starting minibatch loop.
02/18/2017 09:28:13: Finished Epoch[ 1 of 10]: [Training] cr = 4.16290018 * 368; Err = 2.51470582 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=0.74581s
02/18/2017 09:28:13: Finished Epoch[ 1 of 10]: [Training] cr = 4.16290018 * 368; Err = 2.36764709 * 368; totalSamplesSeen = 368; learningRatePerSample = 0.0049999999; epochTime=1.00822s
02/18/2017 09:28:13: SGD: Saving checkpoint model 'C:\Users\svcphil\AppData\Local\Temp\cntk-test-20170218092651.300722\Speech_LSTM_CTC@release_gpu/models/simple.dnn.1'

02/18/2017 09:28:13: Starting Epoch 2: learning rate per sample = 0.005000 effective momentum = 0.900000 momentum as time constant = 189.8 samples
Expand Down

0 comments on commit 54814cd

Please sign in to comment.