gcn run on cmu

geographconv.txt

conda activate py27
(py27) ash@ash-ThinkPad-T470:~/Documents/geographconv$ THEANO_FLAGS='device=cuda0,floatX=float32' nice -n 9 python -u gcnmain.py -hid 300 300 300 -bucket 50 -batch 500 -d ./data/cmu/ -enc latin1 -mindf 10 -reg 0.0 -dropout 0.5 -cel 5 -highway
11/15/2018 09:10:49 AM Could not initialize pygpu, support disabled
Traceback (most recent call last):
  File "/home/ash/miniconda3/envs/py27/lib/python2.7/site-packages/theano/gpuarray/__init__.py", line 227, in <module>
    use(config.device)
  File "/home/ash/miniconda3/envs/py27/lib/python2.7/site-packages/theano/gpuarray/__init__.py", line 214, in use
    init_dev(device, preallocate=preallocate)
  File "/home/ash/miniconda3/envs/py27/lib/python2.7/site-packages/theano/gpuarray/__init__.py", line 99, in init_dev
    **args)
  File "pygpu/gpuarray.pyx", line 658, in pygpu.gpuarray.init
  File "pygpu/gpuarray.pyx", line 587, in pygpu.gpuarray.pygpu_init
GpuArrayException: Could not load "libnvrtc.so": libnvrtc.so: cannot open shared object file: No such file or directory
11/15/2018 09:10:49 AM In order to work for big datasets fix https://github.com/Theano/Theano/pull/5721 should be applied to theano.
11/15/2018 09:10:49 AM loading data from dumped file...
11/15/2018 09:10:49 AM loading data finished!
11/15/2018 09:10:49 AM stacking training, dev and test features and creating indices...
11/15/2018 09:10:49 AM running mlp with graph conv...
11/15/2018 09:10:49 AM highway is True
11/15/2018 09:10:49 AM Graphconv model input size 9467, output size 129 and hidden layers [300, 300, 300] regul 0.0 dropout 0.5.
11/15/2018 09:10:49 AM 3 gconv layers
/home/ash/miniconda3/envs/py27/lib/python2.7/site-packages/lasagne/layers/helper.py:216: UserWarning: get_output() was called with unused kwargs:
	A
  % "\n\t".join(suggestions))
/home/ash/Documents/geographconv/gcnmodel.py:402: UserWarning: theano.function was asked to create a function computing outputs given certain inputs, but the provided input variable at index 1 is not part of the computational graph needed to compute the outputs: SparseVariable{csr,float32}.
To make this warning into an error, you can pass the parameter on_unused_input='raise' to theano.function. To disable it completely, use on_unused_input='ignore'.
  self.f_gates.append(theano.function([self.X_sym, self.A_sym], self.gate_outputs[i], on_unused_input='warn'))
11/15/2018 09:10:54 AM ***********percentile 1.000000 ******************
11/15/2018 09:10:54 AM 5685 training samples
11/15/2018 09:10:54 AM training for 10000 epochs with batch size 500
11/15/2018 09:10:55 AM epoch 0 train loss 4.86 train acc 0.01 val loss 4.86 val acc 0.01 best val acc 0.01 maxdown 0
11/15/2018 09:10:56 AM epoch 1 train loss 4.85 train acc 0.08 val loss 4.85 val acc 0.03 best val acc 0.03 maxdown 0
11/15/2018 09:10:57 AM epoch 2 train loss 4.83 train acc 0.14 val loss 4.85 val acc 0.04 best val acc 0.04 maxdown 0
11/15/2018 09:10:58 AM epoch 3 train loss 4.82 train acc 0.15 val loss 4.84 val acc 0.04 best val acc 0.04 maxdown 0
11/15/2018 09:10:59 AM epoch 4 train loss 4.80 train acc 0.16 val loss 4.84 val acc 0.03 best val acc 0.03 maxdown 0
11/15/2018 09:11:00 AM epoch 5 train loss 4.79 train acc 0.16 val loss 4.83 val acc 0.04 best val acc 0.04 maxdown 0
11/15/2018 09:11:01 AM epoch 6 train loss 4.77 train acc 0.17 val loss 4.82 val acc 0.04 best val acc 0.04 maxdown 0
11/15/2018 09:11:02 AM epoch 7 train loss 4.75 train acc 0.18 val loss 4.81 val acc 0.04 best val acc 0.04 maxdown 0
11/15/2018 09:11:03 AM epoch 8 train loss 4.73 train acc 0.20 val loss 4.80 val acc 0.04 best val acc 0.04 maxdown 0
11/15/2018 09:11:04 AM epoch 9 train loss 4.71 train acc 0.23 val loss 4.79 val acc 0.06 best val acc 0.06 maxdown 0
11/15/2018 09:11:05 AM epoch 10 train loss 4.69 train acc 0.25 val loss 4.78 val acc 0.08 best val acc 0.08 maxdown 0
11/15/2018 09:11:06 AM epoch 11 train loss 4.67 train acc 0.27 val loss 4.76 val acc 0.10 best val acc 0.10 maxdown 0
11/15/2018 09:11:07 AM epoch 12 train loss 4.65 train acc 0.30 val loss 4.75 val acc 0.11 best val acc 0.11 maxdown 0
11/15/2018 09:11:08 AM epoch 13 train loss 4.62 train acc 0.32 val loss 4.74 val acc 0.12 best val acc 0.12 maxdown 0
11/15/2018 09:11:09 AM epoch 14 train loss 4.59 train acc 0.33 val loss 4.72 val acc 0.13 best val acc 0.13 maxdown 0
11/15/2018 09:11:09 AM epoch 15 train loss 4.56 train acc 0.34 val loss 4.70 val acc 0.14 best val acc 0.14 maxdown 0
11/15/2018 09:11:10 AM epoch 16 train loss 4.53 train acc 0.36 val loss 4.68 val acc 0.15 best val acc 0.15 maxdown 0
11/15/2018 09:11:11 AM epoch 17 train loss 4.50 train acc 0.38 val loss 4.66 val acc 0.15 best val acc 0.15 maxdown 0
11/15/2018 09:11:12 AM epoch 18 train loss 4.47 train acc 0.39 val loss 4.64 val acc 0.16 best val acc 0.16 maxdown 0
11/15/2018 09:11:13 AM epoch 19 train loss 4.44 train acc 0.40 val loss 4.62 val acc 0.17 best val acc 0.17 maxdown 0
11/15/2018 09:11:14 AM epoch 20 train loss 4.40 train acc 0.40 val loss 4.60 val acc 0.17 best val acc 0.17 maxdown 0
11/15/2018 09:11:15 AM epoch 21 train loss 4.37 train acc 0.42 val loss 4.58 val acc 0.17 best val acc 0.17 maxdown 0
11/15/2018 09:11:16 AM epoch 22 train loss 4.33 train acc 0.42 val loss 4.55 val acc 0.18 best val acc 0.18 maxdown 0
11/15/2018 09:11:17 AM epoch 23 train loss 4.30 train acc 0.43 val loss 4.53 val acc 0.18 best val acc 0.18 maxdown 0
11/15/2018 09:11:18 AM epoch 24 train loss 4.26 train acc 0.44 val loss 4.51 val acc 0.18 best val acc 0.18 maxdown 0
11/15/2018 09:11:19 AM epoch 25 train loss 4.22 train acc 0.44 val loss 4.48 val acc 0.18 best val acc 0.18 maxdown 0
11/15/2018 09:11:20 AM epoch 26 train loss 4.18 train acc 0.45 val loss 4.46 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:11:21 AM epoch 27 train loss 4.15 train acc 0.46 val loss 4.44 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:11:22 AM epoch 28 train loss 4.11 train acc 0.46 val loss 4.42 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:11:23 AM epoch 29 train loss 4.07 train acc 0.47 val loss 4.39 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:11:24 AM epoch 30 train loss 4.04 train acc 0.47 val loss 4.37 val acc 0.19 best val acc 0.19 maxdown 0
11/15/2018 09:11:25 AM epoch 31 train loss 4.00 train acc 0.48 val loss 4.36 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:11:26 AM epoch 32 train loss 3.97 train acc 0.48 val loss 4.34 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:11:27 AM epoch 33 train loss 3.93 train acc 0.49 val loss 4.32 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:11:28 AM epoch 34 train loss 3.90 train acc 0.49 val loss 4.31 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:11:29 AM epoch 35 train loss 3.87 train acc 0.50 val loss 4.28 val acc 0.21 best val acc 0.21 maxdown 0
11/15/2018 09:11:30 AM epoch 36 train loss 3.83 train acc 0.50 val loss 4.27 val acc 0.21 best val acc 0.21 maxdown 0
11/15/2018 09:11:31 AM epoch 37 train loss 3.80 train acc 0.51 val loss 4.26 val acc 0.21 best val acc 0.21 maxdown 0
11/15/2018 09:11:32 AM epoch 38 train loss 3.76 train acc 0.52 val loss 4.24 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:11:33 AM epoch 39 train loss 3.73 train acc 0.52 val loss 4.22 val acc 0.21 best val acc 0.21 maxdown 0
11/15/2018 09:11:34 AM epoch 40 train loss 3.69 train acc 0.53 val loss 4.20 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:11:34 AM epoch 41 train loss 3.65 train acc 0.52 val loss 4.19 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:11:35 AM epoch 42 train loss 3.61 train acc 0.53 val loss 4.17 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:11:36 AM epoch 43 train loss 3.58 train acc 0.54 val loss 4.15 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:11:37 AM epoch 44 train loss 3.54 train acc 0.54 val loss 4.13 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:11:38 AM epoch 45 train loss 3.50 train acc 0.54 val loss 4.11 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:11:39 AM epoch 46 train loss 3.46 train acc 0.54 val loss 4.10 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:40 AM epoch 47 train loss 3.41 train acc 0.55 val loss 4.07 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:11:41 AM epoch 48 train loss 3.38 train acc 0.55 val loss 4.05 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:42 AM epoch 49 train loss 3.34 train acc 0.55 val loss 4.04 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:11:43 AM epoch 50 train loss 3.29 train acc 0.56 val loss 4.01 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:44 AM epoch 51 train loss 3.25 train acc 0.56 val loss 3.98 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:45 AM epoch 52 train loss 3.21 train acc 0.57 val loss 3.96 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:46 AM epoch 53 train loss 3.16 train acc 0.57 val loss 3.94 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:47 AM epoch 54 train loss 3.12 train acc 0.58 val loss 3.92 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:48 AM epoch 55 train loss 3.07 train acc 0.57 val loss 3.89 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:49 AM epoch 56 train loss 3.03 train acc 0.58 val loss 3.87 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:11:50 AM epoch 57 train loss 2.98 train acc 0.58 val loss 3.84 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:51 AM epoch 58 train loss 2.94 train acc 0.58 val loss 3.81 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:52 AM epoch 59 train loss 2.89 train acc 0.59 val loss 3.80 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:53 AM epoch 60 train loss 2.85 train acc 0.59 val loss 3.77 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:11:54 AM epoch 61 train loss 2.80 train acc 0.58 val loss 3.75 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:55 AM epoch 62 train loss 2.75 train acc 0.59 val loss 3.73 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:11:56 AM epoch 63 train loss 2.70 train acc 0.59 val loss 3.72 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:11:57 AM epoch 64 train loss 2.66 train acc 0.58 val loss 3.69 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:11:58 AM epoch 65 train loss 2.61 train acc 0.58 val loss 3.67 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:11:59 AM epoch 66 train loss 2.57 train acc 0.58 val loss 3.65 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:12:00 AM epoch 67 train loss 2.52 train acc 0.58 val loss 3.63 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:12:01 AM epoch 68 train loss 2.48 train acc 0.59 val loss 3.61 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:12:02 AM epoch 69 train loss 2.44 train acc 0.59 val loss 3.60 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:12:03 AM epoch 70 train loss 2.40 train acc 0.59 val loss 3.58 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:12:04 AM epoch 71 train loss 2.36 train acc 0.59 val loss 3.56 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:12:05 AM epoch 72 train loss 2.31 train acc 0.61 val loss 3.56 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:12:06 AM epoch 73 train loss 2.28 train acc 0.61 val loss 3.53 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:12:07 AM epoch 74 train loss 2.24 train acc 0.61 val loss 3.51 val acc 0.26 best val acc 0.26 maxdown 0
11/15/2018 09:12:08 AM epoch 75 train loss 2.20 train acc 0.61 val loss 3.50 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:12:09 AM epoch 76 train loss 2.16 train acc 0.62 val loss 3.47 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:12:10 AM epoch 77 train loss 2.13 train acc 0.63 val loss 3.48 val acc 0.25 best val acc 0.25 maxdown 1
11/15/2018 09:12:11 AM epoch 78 train loss 2.09 train acc 0.63 val loss 3.45 val acc 0.26 best val acc 0.26 maxdown 0
11/15/2018 09:12:12 AM epoch 79 train loss 2.05 train acc 0.64 val loss 3.46 val acc 0.26 best val acc 0.26 maxdown 1
11/15/2018 09:12:13 AM epoch 80 train loss 2.01 train acc 0.64 val loss 3.45 val acc 0.26 best val acc 0.26 maxdown 0
11/15/2018 09:12:14 AM epoch 81 train loss 1.98 train acc 0.64 val loss 3.43 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:12:15 AM epoch 82 train loss 1.94 train acc 0.65 val loss 3.44 val acc 0.26 best val acc 0.25 maxdown 1
11/15/2018 09:12:16 AM epoch 83 train loss 1.91 train acc 0.66 val loss 3.42 val acc 0.26 best val acc 0.26 maxdown 0
11/15/2018 09:12:17 AM epoch 84 train loss 1.87 train acc 0.66 val loss 3.42 val acc 0.25 best val acc 0.26 maxdown 1
11/15/2018 09:12:18 AM epoch 85 train loss 1.84 train acc 0.66 val loss 3.43 val acc 0.25 best val acc 0.26 maxdown 2
11/15/2018 09:12:19 AM epoch 86 train loss 1.81 train acc 0.67 val loss 3.42 val acc 0.26 best val acc 0.26 maxdown 3
11/15/2018 09:12:20 AM epoch 87 train loss 1.77 train acc 0.67 val loss 3.42 val acc 0.25 best val acc 0.26 maxdown 4
11/15/2018 09:12:21 AM epoch 88 train loss 1.74 train acc 0.67 val loss 3.43 val acc 0.26 best val acc 0.26 maxdown 5
11/15/2018 09:12:22 AM epoch 89 train loss 1.71 train acc 0.68 val loss 3.43 val acc 0.25 best val acc 0.26 maxdown 6
11/15/2018 09:12:23 AM epoch 90 train loss 1.68 train acc 0.68 val loss 3.43 val acc 0.25 best val acc 0.26 maxdown 7
11/15/2018 09:12:25 AM epoch 91 train loss 1.65 train acc 0.69 val loss 3.45 val acc 0.25 best val acc 0.26 maxdown 8
11/15/2018 09:12:26 AM epoch 92 train loss 1.62 train acc 0.69 val loss 3.45 val acc 0.25 best val acc 0.26 maxdown 9
11/15/2018 09:12:27 AM epoch 93 train loss 1.59 train acc 0.70 val loss 3.45 val acc 0.24 best val acc 0.26 maxdown 10
11/15/2018 09:12:28 AM epoch 94 train loss 1.56 train acc 0.71 val loss 3.45 val acc 0.26 best val acc 0.26 maxdown 11
11/15/2018 09:12:28 AM validation results went down. early stopping ...
11/15/2018 09:12:28 AM dev results:
11/15/2018 09:12:28 AM Mean: 520 Median: 46 Acc@161: 60
11/15/2018 09:12:28 AM test results:
11/15/2018 09:12:29 AM Mean: 540 Median: 47 Acc@161: 60






(py27) ash@ash-ThinkPad-T470:~/Documents/geographconv$ THEANO_FLAGS='device=cuda0,floatX=float32' nice -n 9 python -u gcnmain.py -hid 300 300 300 -bucket 50 -batch 500 -d ./data/cmu/ -enc latin1 -mindf 10 -reg 0.0 -dropout 0.5 -cel 5 -highway -seed 2018
11/15/2018 09:13:10 AM Could not initialize pygpu, support disabled
Traceback (most recent call last):
  File "/home/ash/miniconda3/envs/py27/lib/python2.7/site-packages/theano/gpuarray/__init__.py", line 227, in <module>
    use(config.device)
  File "/home/ash/miniconda3/envs/py27/lib/python2.7/site-packages/theano/gpuarray/__init__.py", line 214, in use
    init_dev(device, preallocate=preallocate)
  File "/home/ash/miniconda3/envs/py27/lib/python2.7/site-packages/theano/gpuarray/__init__.py", line 99, in init_dev
    **args)
  File "pygpu/gpuarray.pyx", line 658, in pygpu.gpuarray.init
  File "pygpu/gpuarray.pyx", line 587, in pygpu.gpuarray.pygpu_init
GpuArrayException: Could not load "libnvrtc.so": libnvrtc.so: cannot open shared object file: No such file or directory
11/15/2018 09:13:10 AM In order to work for big datasets fix https://github.com/Theano/Theano/pull/5721 should be applied to theano.
11/15/2018 09:13:10 AM loading data from dumped file...
11/15/2018 09:13:10 AM loading data finished!
11/15/2018 09:13:10 AM stacking training, dev and test features and creating indices...
11/15/2018 09:13:10 AM running mlp with graph conv...
11/15/2018 09:13:10 AM highway is True
11/15/2018 09:13:10 AM Graphconv model input size 9467, output size 129 and hidden layers [300, 300, 300] regul 0.0 dropout 0.5.
11/15/2018 09:13:10 AM 3 gconv layers
/home/ash/miniconda3/envs/py27/lib/python2.7/site-packages/lasagne/layers/helper.py:216: UserWarning: get_output() was called with unused kwargs:
	A
  % "\n\t".join(suggestions))
/home/ash/Documents/geographconv/gcnmodel.py:402: UserWarning: theano.function was asked to create a function computing outputs given certain inputs, but the provided input variable at index 1 is not part of the computational graph needed to compute the outputs: SparseVariable{csr,float32}.
To make this warning into an error, you can pass the parameter on_unused_input='raise' to theano.function. To disable it completely, use on_unused_input='ignore'.
  self.f_gates.append(theano.function([self.X_sym, self.A_sym], self.gate_outputs[i], on_unused_input='warn'))
11/15/2018 09:13:15 AM ***********percentile 1.000000 ******************
11/15/2018 09:13:15 AM 5685 training samples
11/15/2018 09:13:15 AM training for 10000 epochs with batch size 500
11/15/2018 09:13:16 AM epoch 0 train loss 4.86 train acc 0.01 val loss 4.86 val acc 0.01 best val acc 0.01 maxdown 0
11/15/2018 09:13:17 AM epoch 1 train loss 4.85 train acc 0.08 val loss 4.85 val acc 0.03 best val acc 0.03 maxdown 0
11/15/2018 09:13:17 AM epoch 2 train loss 4.83 train acc 0.13 val loss 4.85 val acc 0.04 best val acc 0.04 maxdown 0
11/15/2018 09:13:18 AM epoch 3 train loss 4.82 train acc 0.16 val loss 4.84 val acc 0.05 best val acc 0.05 maxdown 0
11/15/2018 09:13:19 AM epoch 4 train loss 4.80 train acc 0.18 val loss 4.84 val acc 0.05 best val acc 0.05 maxdown 0
11/15/2018 09:13:20 AM epoch 5 train loss 4.79 train acc 0.19 val loss 4.83 val acc 0.06 best val acc 0.06 maxdown 0
11/15/2018 09:13:21 AM epoch 6 train loss 4.77 train acc 0.21 val loss 4.82 val acc 0.06 best val acc 0.06 maxdown 0
11/15/2018 09:13:22 AM epoch 7 train loss 4.75 train acc 0.23 val loss 4.81 val acc 0.07 best val acc 0.07 maxdown 0
11/15/2018 09:13:23 AM epoch 8 train loss 4.73 train acc 0.23 val loss 4.80 val acc 0.08 best val acc 0.08 maxdown 0
11/15/2018 09:13:24 AM epoch 9 train loss 4.71 train acc 0.25 val loss 4.79 val acc 0.08 best val acc 0.08 maxdown 0
11/15/2018 09:13:25 AM epoch 10 train loss 4.69 train acc 0.27 val loss 4.78 val acc 0.09 best val acc 0.09 maxdown 0
11/15/2018 09:13:26 AM epoch 11 train loss 4.67 train acc 0.28 val loss 4.76 val acc 0.09 best val acc 0.09 maxdown 0
11/15/2018 09:13:26 AM epoch 12 train loss 4.64 train acc 0.29 val loss 4.75 val acc 0.11 best val acc 0.11 maxdown 0
11/15/2018 09:13:27 AM epoch 13 train loss 4.62 train acc 0.31 val loss 4.73 val acc 0.12 best val acc 0.12 maxdown 0
11/15/2018 09:13:28 AM epoch 14 train loss 4.59 train acc 0.33 val loss 4.72 val acc 0.13 best val acc 0.13 maxdown 0
11/15/2018 09:13:29 AM epoch 15 train loss 4.56 train acc 0.35 val loss 4.70 val acc 0.14 best val acc 0.14 maxdown 0
11/15/2018 09:13:30 AM epoch 16 train loss 4.53 train acc 0.36 val loss 4.68 val acc 0.15 best val acc 0.15 maxdown 0
11/15/2018 09:13:31 AM epoch 17 train loss 4.50 train acc 0.38 val loss 4.66 val acc 0.15 best val acc 0.15 maxdown 0
11/15/2018 09:13:32 AM epoch 18 train loss 4.47 train acc 0.39 val loss 4.64 val acc 0.16 best val acc 0.16 maxdown 0
11/15/2018 09:13:33 AM epoch 19 train loss 4.43 train acc 0.41 val loss 4.62 val acc 0.17 best val acc 0.17 maxdown 0
11/15/2018 09:13:34 AM epoch 20 train loss 4.40 train acc 0.41 val loss 4.59 val acc 0.17 best val acc 0.17 maxdown 0
11/15/2018 09:13:35 AM epoch 21 train loss 4.36 train acc 0.42 val loss 4.57 val acc 0.18 best val acc 0.18 maxdown 0
11/15/2018 09:13:36 AM epoch 22 train loss 4.33 train acc 0.43 val loss 4.54 val acc 0.18 best val acc 0.18 maxdown 0
11/15/2018 09:13:37 AM epoch 23 train loss 4.29 train acc 0.44 val loss 4.52 val acc 0.18 best val acc 0.18 maxdown 0
11/15/2018 09:13:38 AM epoch 24 train loss 4.26 train acc 0.43 val loss 4.50 val acc 0.19 best val acc 0.19 maxdown 0
11/15/2018 09:13:39 AM epoch 25 train loss 4.22 train acc 0.45 val loss 4.48 val acc 0.19 best val acc 0.19 maxdown 0
11/15/2018 09:13:40 AM epoch 26 train loss 4.18 train acc 0.45 val loss 4.45 val acc 0.19 best val acc 0.19 maxdown 0
11/15/2018 09:13:40 AM epoch 27 train loss 4.14 train acc 0.45 val loss 4.43 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:13:41 AM epoch 28 train loss 4.11 train acc 0.46 val loss 4.40 val acc 0.19 best val acc 0.19 maxdown 0
11/15/2018 09:13:42 AM epoch 29 train loss 4.07 train acc 0.47 val loss 4.38 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:13:43 AM epoch 30 train loss 4.04 train acc 0.47 val loss 4.37 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:13:44 AM epoch 31 train loss 4.00 train acc 0.47 val loss 4.34 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:13:45 AM epoch 32 train loss 3.97 train acc 0.48 val loss 4.33 val acc 0.20 best val acc 0.20 maxdown 0
11/15/2018 09:13:46 AM epoch 33 train loss 3.93 train acc 0.48 val loss 4.31 val acc 0.21 best val acc 0.21 maxdown 0
11/15/2018 09:13:47 AM epoch 34 train loss 3.90 train acc 0.49 val loss 4.29 val acc 0.21 best val acc 0.21 maxdown 0
11/15/2018 09:13:48 AM epoch 35 train loss 3.87 train acc 0.50 val loss 4.28 val acc 0.21 best val acc 0.21 maxdown 0
11/15/2018 09:13:49 AM epoch 36 train loss 3.83 train acc 0.51 val loss 4.26 val acc 0.21 best val acc 0.21 maxdown 0
11/15/2018 09:13:50 AM epoch 37 train loss 3.80 train acc 0.52 val loss 4.24 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:13:51 AM epoch 38 train loss 3.76 train acc 0.52 val loss 4.23 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:13:52 AM epoch 39 train loss 3.73 train acc 0.53 val loss 4.21 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:13:53 AM epoch 40 train loss 3.69 train acc 0.54 val loss 4.19 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:13:54 AM epoch 41 train loss 3.66 train acc 0.54 val loss 4.18 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:13:55 AM epoch 42 train loss 3.62 train acc 0.53 val loss 4.16 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:13:56 AM epoch 43 train loss 3.58 train acc 0.54 val loss 4.15 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:13:57 AM epoch 44 train loss 3.54 train acc 0.54 val loss 4.12 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:13:58 AM epoch 45 train loss 3.50 train acc 0.54 val loss 4.10 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:13:59 AM epoch 46 train loss 3.46 train acc 0.54 val loss 4.08 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:14:00 AM epoch 47 train loss 3.42 train acc 0.54 val loss 4.07 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:14:01 AM epoch 48 train loss 3.38 train acc 0.54 val loss 4.04 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:14:02 AM epoch 49 train loss 3.34 train acc 0.54 val loss 4.02 val acc 0.22 best val acc 0.22 maxdown 0
11/15/2018 09:14:03 AM epoch 50 train loss 3.30 train acc 0.55 val loss 4.00 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:14:04 AM epoch 51 train loss 3.26 train acc 0.55 val loss 3.98 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:14:05 AM epoch 52 train loss 3.22 train acc 0.55 val loss 3.96 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:14:06 AM epoch 53 train loss 3.17 train acc 0.56 val loss 3.93 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:07 AM epoch 54 train loss 3.13 train acc 0.57 val loss 3.91 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:14:08 AM epoch 55 train loss 3.09 train acc 0.57 val loss 3.89 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:09 AM epoch 56 train loss 3.04 train acc 0.57 val loss 3.87 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:10 AM epoch 57 train loss 3.00 train acc 0.58 val loss 3.84 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:10 AM epoch 58 train loss 2.95 train acc 0.58 val loss 3.82 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:14:11 AM epoch 59 train loss 2.90 train acc 0.58 val loss 3.79 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:12 AM epoch 60 train loss 2.86 train acc 0.58 val loss 3.77 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:13 AM epoch 61 train loss 2.81 train acc 0.58 val loss 3.75 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:14 AM epoch 62 train loss 2.76 train acc 0.57 val loss 3.73 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:15 AM epoch 63 train loss 2.72 train acc 0.58 val loss 3.71 val acc 0.23 best val acc 0.23 maxdown 0
11/15/2018 09:14:16 AM epoch 64 train loss 2.67 train acc 0.57 val loss 3.69 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:17 AM epoch 65 train loss 2.63 train acc 0.57 val loss 3.66 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:18 AM epoch 66 train loss 2.59 train acc 0.57 val loss 3.65 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:19 AM epoch 67 train loss 2.54 train acc 0.57 val loss 3.63 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:20 AM epoch 68 train loss 2.50 train acc 0.58 val loss 3.61 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:21 AM epoch 69 train loss 2.46 train acc 0.58 val loss 3.58 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:22 AM epoch 70 train loss 2.41 train acc 0.59 val loss 3.57 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:23 AM epoch 71 train loss 2.37 train acc 0.59 val loss 3.55 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:24 AM epoch 72 train loss 2.34 train acc 0.60 val loss 3.53 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:25 AM epoch 73 train loss 2.30 train acc 0.61 val loss 3.52 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:26 AM epoch 74 train loss 2.25 train acc 0.61 val loss 3.50 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:27 AM epoch 75 train loss 2.21 train acc 0.62 val loss 3.49 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:28 AM epoch 76 train loss 2.17 train acc 0.62 val loss 3.48 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:29 AM epoch 77 train loss 2.14 train acc 0.63 val loss 3.47 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:30 AM epoch 78 train loss 2.10 train acc 0.63 val loss 3.45 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:31 AM epoch 79 train loss 2.07 train acc 0.63 val loss 3.44 val acc 0.24 best val acc 0.24 maxdown 0
11/15/2018 09:14:32 AM epoch 80 train loss 2.03 train acc 0.64 val loss 3.44 val acc 0.24 best val acc 0.24 maxdown 1
11/15/2018 09:14:33 AM epoch 81 train loss 1.99 train acc 0.64 val loss 3.43 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:34 AM epoch 82 train loss 1.96 train acc 0.65 val loss 3.41 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:35 AM epoch 83 train loss 1.92 train acc 0.65 val loss 3.41 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:36 AM epoch 84 train loss 1.89 train acc 0.66 val loss 3.40 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:37 AM epoch 85 train loss 1.86 train acc 0.66 val loss 3.41 val acc 0.25 best val acc 0.25 maxdown 1
11/15/2018 09:14:38 AM epoch 86 train loss 1.82 train acc 0.66 val loss 3.41 val acc 0.25 best val acc 0.25 maxdown 2
11/15/2018 09:14:39 AM epoch 87 train loss 1.78 train acc 0.66 val loss 3.40 val acc 0.25 best val acc 0.25 maxdown 3
11/15/2018 09:14:40 AM epoch 88 train loss 1.76 train acc 0.68 val loss 3.39 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:41 AM epoch 89 train loss 1.72 train acc 0.67 val loss 3.41 val acc 0.25 best val acc 0.25 maxdown 1
11/15/2018 09:14:42 AM epoch 90 train loss 1.70 train acc 0.68 val loss 3.39 val acc 0.25 best val acc 0.25 maxdown 0
11/15/2018 09:14:43 AM epoch 91 train loss 1.66 train acc 0.69 val loss 3.39 val acc 0.25 best val acc 0.25 maxdown 1
11/15/2018 09:14:44 AM epoch 92 train loss 1.63 train acc 0.69 val loss 3.41 val acc 0.25 best val acc 0.25 maxdown 2
11/15/2018 09:14:45 AM epoch 93 train loss 1.60 train acc 0.70 val loss 3.40 val acc 0.24 best val acc 0.25 maxdown 3
11/15/2018 09:14:46 AM epoch 94 train loss 1.57 train acc 0.70 val loss 3.43 val acc 0.25 best val acc 0.25 maxdown 4
11/15/2018 09:14:47 AM epoch 95 train loss 1.55 train acc 0.71 val loss 3.40 val acc 0.25 best val acc 0.25 maxdown 5
11/15/2018 09:14:48 AM epoch 96 train loss 1.51 train acc 0.71 val loss 3.44 val acc 0.24 best val acc 0.25 maxdown 6
11/15/2018 09:14:49 AM epoch 97 train loss 1.48 train acc 0.72 val loss 3.44 val acc 0.24 best val acc 0.25 maxdown 7
11/15/2018 09:14:50 AM epoch 98 train loss 1.46 train acc 0.72 val loss 3.45 val acc 0.25 best val acc 0.25 maxdown 8
11/15/2018 09:14:51 AM epoch 99 train loss 1.43 train acc 0.73 val loss 3.44 val acc 0.24 best val acc 0.25 maxdown 9
11/15/2018 09:14:52 AM epoch 100 train loss 1.40 train acc 0.73 val loss 3.46 val acc 0.24 best val acc 0.25 maxdown 10
11/15/2018 09:14:53 AM epoch 101 train loss 1.38 train acc 0.74 val loss 3.47 val acc 0.24 best val acc 0.25 maxdown 11
11/15/2018 09:14:53 AM validation results went down. early stopping ...
11/15/2018 09:14:53 AM dev results:
11/15/2018 09:14:53 AM Mean: 528 Median: 45 Acc@161: 60
11/15/2018 09:14:53 AM test results:
11/15/2018 09:14:54 AM Mean: 535 Median: 48 Acc@161: 60