bottleneck_report.txt

`bottleneck` is a tool that can be used as an initial step for debugging
bottlenecks in your program.

It summarizes runs of your script with the Python profiler and PyTorch's
autograd profiler. Because your script will be profiled, please ensure that it
exits in a finite amount of time.

For more complicated uses of the profilers, please see
https://docs.python.org/3/library/profile.html and
http://pytorch.org/docs/master/autograd.html#profiler for more information.
Running environment analysis...
Running your script with cProfile
Loading data/small
Loading claims data...
Model with dropout!
Let's use 1 GPU(s)!
Created model with 52,718,058 parameters.
Created dataset...
Num Distinct Claims 109810
Num Data Points 125050
Num Distinct Claims 109810
Num Data Points 125050
{ data batch size: 8 }
{ learning rate: 0.001 }
{ sparse_evidences: False }
{ loss: BCEWithLogitsLoss }
{ data: data/small }
{ training size: 800 }
{ batch size: 1 }
{ epochs: 2 }
{ optimizer: Adam }
Training...
[0:0.02:5.938811s] training loss: 1.6231301203370094, training accuracy: 0.6328125, training recall: 0.0
[0:0.04:3.072096s] training loss: 1.173102017492056, training accuracy: 0.65625, training recall: 0.0
[0:0.06:1.630766s] training loss: 1.0724168377928436, training accuracy: 0.734375, training recall: 0.0
[0:0.08:1.619488s] training loss: 0.8814745219424367, training accuracy: 0.765625, training recall: 0.0
[0:0.1:2.572515s] training loss: 0.8730866834521294, training accuracy: 0.71875, training recall: 1.0
[0:0.12:1.546245s] training loss: 0.9108042484149337, training accuracy: 0.7578125, training recall: 1.0
[0:0.14:2.433965s] training loss: 0.7182806897908449, training accuracy: 0.765625, training recall: 0.5
[0:0.16:2.023946s] training loss: 0.8657938931137323, training accuracy: 0.7265625, training recall: 0.0
[0:0.18:2.127755s] training loss: 0.6886722575873137, training accuracy: 0.75, training recall: 0.5
[0:0.2:1.770661s] training loss: 0.8139848560094833, training accuracy: 0.671875, training recall: 1.0
[0:0.22:1.972374s] training loss: 0.7275752890855074, training accuracy: 0.7421875, training recall: 0.0
[0:0.24:1.544883s] training loss: 0.6973544601351023, training accuracy: 0.7421875, training recall: 0.0
[0:0.26:1.557599s] training loss: 0.7982896994799376, training accuracy: 0.75, training recall: 0.0
[0:0.28:1.623917s] training loss: 0.8108441215008497, training accuracy: 0.734375, training recall: 0.0
[0:0.3:1.528511s] training loss: 0.6856408761814237, training accuracy: 0.7421875, training recall: 0.0
[0:0.32:1.663925s] training loss: 0.6733939610421658, training accuracy: 0.734375, training recall: 0.0
[0:0.34:1.679641s] training loss: 0.6175812222063541, training accuracy: 0.75, training recall: 0.0
[0:0.36:1.551957s] training loss: 0.677701226901263, training accuracy: 0.765625, training recall: 0.0
[0:0.38:1.995453s] training loss: 0.9662745241075754, training accuracy: 0.6640625, training recall: 0.0
[0:0.4:1.985363s] training loss: 0.6214914629235864, training accuracy: 0.8046875, training recall: 0.0
[0:0.42:1.520813s] training loss: 0.6950810309499502, training accuracy: 0.671875, training recall: 0.0
[0:0.44:1.949299s] training loss: 0.6697106561623514, training accuracy: 0.7734375, training recall: 0.0
[0:0.46:1.664331s] training loss: 0.3882807632908225, training accuracy: 0.8203125, training recall: 0.0
[0:0.48:1.954806s] training loss: 0.6438488196581602, training accuracy: 0.7109375, training recall: 0.0
[0:0.5:1.760818s] training loss: 0.5919922515749931, training accuracy: 0.765625, training recall: 0.0
[0:0.52:2.032238s] training loss: 0.591521198861301, training accuracy: 0.7265625, training recall: 1.0
[0:0.54:1.474513s] training loss: 0.5391217917203903, training accuracy: 0.765625, training recall: 0.0
[0:0.56:2.076071s] training loss: 0.48922090930864215, training accuracy: 0.8203125, training recall: 0.0
[0:0.58:1.569901s] training loss: 0.5226884409785271, training accuracy: 0.78125, training recall: 0.0
[0:0.6:1.597813s] training loss: 0.4956216402351856, training accuracy: 0.78125, training recall: 0.0
[0:0.62:1.533095s] training loss: 0.3604180235415697, training accuracy: 0.875, training recall: 0.0
[0:0.64:1.539096s] training loss: 0.5077857468277216, training accuracy: 0.8046875, training recall: 0.0
[0:0.66:1.955079s] training loss: 0.3785831592977047, training accuracy: 0.8359375, training recall: 0.0
[0:0.68:1.763357s] training loss: 0.5321468664333224, training accuracy: 0.78125, training recall: 1.0
[0:0.7:2.380956s] training loss: 0.513964687474072, training accuracy: 0.78125, training recall: 0.0
[0:0.72:1.558665s] training loss: 0.5321238022297621, training accuracy: 0.7578125, training recall: 0.0
[0:0.74:1.645185s] training loss: 0.40713804215192795, training accuracy: 0.84375, training recall: 0.0
[0:0.76:1.609209s] training loss: 0.5064878184348345, training accuracy: 0.7578125, training recall: 0.5
[0:0.78:1.614270s] training loss: 0.5730411037802696, training accuracy: 0.734375, training recall: 1.0
[0:0.8:1.554457s] training loss: 0.4606784489005804, training accuracy: 0.8125, training recall: 0.0
[0:0.82:1.744104s] training loss: 0.49953755736351013, training accuracy: 0.8125, training recall: 1.0
[0:0.84:1.934018s] training loss: 0.44786042999476194, training accuracy: 0.828125, training recall: 0.0
[0:0.86:1.588950s] training loss: 0.49147121235728264, training accuracy: 0.84375, training recall: 0.0
[0:0.88:1.382795s] training loss: 0.5213993526995182, training accuracy: 0.8046875, training recall: 1.0
[0:0.9:1.779955s] training loss: 0.48210098035633564, training accuracy: 0.796875, training recall: 0.0
[0:0.92:2.039976s] training loss: 0.4085076916962862, training accuracy: 0.8359375, training recall: 0.0
[0:0.94:1.714996s] training loss: 0.4213288389146328, training accuracy: 0.859375, training recall: 0.0
[0:0.96:1.953922s] training loss: 0.40388556849211454, training accuracy: 0.828125, training recall: 0.0
[0:0.98:1.892761s] training loss: 0.5295257912948728, training accuracy: 0.7421875, training recall: 1.0
Running validation...
[0:0.08] loss: 0.3757116477936506, accuracy: 0.796875, recall: 0.0
[0:0.16] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0:0.24] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0:0.32] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0:0.4] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0:0.48] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0:0.56] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0:0.64] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0:0.72] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0:0.8] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0:0.88] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0:0.96] loss: 0.35361096262931824, accuracy: 0.75, recall: 0.0
[0] mean accuracy: 0.7673437595367432
=> Saving a new best
[1:0.02:1.428112s] training loss: 0.41139044146984816, training accuracy: 0.8828125, training recall: 0.0
[1:0.04:1.676709s] training loss: 0.29435402527451515, training accuracy: 0.90625, training recall: 1.0
[1:0.06:1.404665s] training loss: 0.3301327209919691, training accuracy: 0.8515625, training recall: 1.0
[1:0.08:1.655425s] training loss: 0.32872068602591753, training accuracy: 0.828125, training recall: 1.0
[1:0.1:1.484476s] training loss: 0.34361122408881783, training accuracy: 0.8515625, training recall: 0.0
[1:0.12:1.604260s] training loss: 0.3051380505785346, training accuracy: 0.875, training recall: 0.0
[1:0.14:1.668015s] training loss: 0.29105651658028364, training accuracy: 0.90625, training recall: 0.0
[1:0.16:1.688648s] training loss: 0.30453469092026353, training accuracy: 0.859375, training recall: 0.5
[1:0.18:1.707480s] training loss: 0.32341317366808653, training accuracy: 0.84375, training recall: 0.0
[1:0.2:1.917086s] training loss: 0.2840189782436937, training accuracy: 0.890625, training recall: 1.0
[1:0.22:1.494102s] training loss: 0.29725144943222404, training accuracy: 0.84375, training recall: 1.0
[1:0.24:1.830562s] training loss: 0.3006244730204344, training accuracy: 0.8515625, training recall: 1.0
[1:0.26:1.501615s] training loss: 0.35047851875424385, training accuracy: 0.8203125, training recall: 0.5
[1:0.28:1.543516s] training loss: 0.2789093595929444, training accuracy: 0.8671875, training recall: 0.0
[1:0.3:1.580467s] training loss: 0.3859000587835908, training accuracy: 0.8125, training recall: 0.5
[1:0.32:1.645936s] training loss: 0.2816508440300822, training accuracy: 0.8828125, training recall: 0.6666666666666666
[1:0.34:1.714527s] training loss: 0.44030346907675266, training accuracy: 0.8359375, training recall: 0.0
[1:0.36:1.561506s] training loss: 0.3346678940579295, training accuracy: 0.828125, training recall: 0.0
[1:0.38:1.956036s] training loss: 0.32298314524814487, training accuracy: 0.8671875, training recall: 0.5
[1:0.4:1.487243s] training loss: 0.3204456907697022, training accuracy: 0.8359375, training recall: 1.0
[1:0.42:1.728977s] training loss: 0.38406798988580704, training accuracy: 0.859375, training recall: 0.0
[1:0.44:1.756821s] training loss: 0.4047816935926676, training accuracy: 0.8203125, training recall: 0.0
[1:0.46:1.702447s] training loss: 0.3510834714397788, training accuracy: 0.8359375, training recall: 0.0
[1:0.48:1.524238s] training loss: 0.28994843037799, training accuracy: 0.8671875, training recall: 0.0
[1:0.5:1.904696s] training loss: 0.32238247571513057, training accuracy: 0.8359375, training recall: 0.0
[1:0.52:1.970845s] training loss: 0.25225039990618825, training accuracy: 0.90625, training recall: 1.0
[1:0.54:2.024879s] training loss: 0.2784987366758287, training accuracy: 0.90625, training recall: 1.0
[1:0.56:1.723089s] training loss: 0.280810568947345, training accuracy: 0.8515625, training recall: 1.0
[1:0.58:1.675601s] training loss: 0.2675364534370601, training accuracy: 0.890625, training recall: 0.0
[1:0.6:1.684033s] training loss: 0.38728542253375053, training accuracy: 0.828125, training recall: 1.0
[1:0.62:1.724566s] training loss: 0.30334153212606907, training accuracy: 0.8515625, training recall: 0.0
[1:0.64:1.649828s] training loss: 0.3324657608754933, training accuracy: 0.84375, training recall: 1.0
[1:0.66:1.469348s] training loss: 0.29412295552901924, training accuracy: 0.8515625, training recall: 0.0
[1:0.68:1.736430s] training loss: 0.4308490986004472, training accuracy: 0.828125, training recall: 1.0
[1:0.7:1.969918s] training loss: 0.3570764111354947, training accuracy: 0.8515625, training recall: 0.0
[1:0.72:1.810704s] training loss: 0.26767566287890077, training accuracy: 0.875, training recall: 0.0
[1:0.74:1.704670s] training loss: 0.31728578032925725, training accuracy: 0.890625, training recall: 0.0
[1:0.76:1.501172s] training loss: 0.39553365763276815, training accuracy: 0.8203125, training recall: 1.0
[1:0.78:1.673308s] training loss: 0.4254737263545394, training accuracy: 0.8203125, training recall: 0.0
[1:0.8:1.600159s] training loss: 0.3124087289907038, training accuracy: 0.8671875, training recall: 0.0
[1:0.82:1.686096s] training loss: 0.31985856825485826, training accuracy: 0.90625, training recall: 0.0
[1:0.84:1.949868s] training loss: 0.4439758360385895, training accuracy: 0.796875, training recall: 0.5
[1:0.86:1.675226s] training loss: 0.42600266449153423, training accuracy: 0.8359375, training recall: 0.0
[1:0.88:1.866580s] training loss: 0.3461808133870363, training accuracy: 0.859375, training recall: 0.0
[1:0.9:1.792333s] training loss: 0.3492407794110477, training accuracy: 0.84375, training recall: 0.0
[1:0.92:1.685290s] training loss: 0.31043270137161016, training accuracy: 0.8828125, training recall: 0.5
[1:0.94:1.847972s] training loss: 0.38359946804121137, training accuracy: 0.828125, training recall: 0.0
[1:0.96:1.725602s] training loss: 0.3038687692023814, training accuracy: 0.8828125, training recall: 0.5
[1:0.98:1.927349s] training loss: 0.34647979494184256, training accuracy: 0.8203125, training recall: 0.75
Running validation...
[1:0.08] loss: 0.18983029294759035, accuracy: 1.0625, recall: 1.0
[1:0.16] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1:0.24] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1:0.32] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1:0.4] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1:0.48] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1:0.56] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1:0.64] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1:0.72] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1:0.8] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1:0.88] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1:0.96] loss: 0.17866380512714386, accuracy: 1.0, recall: 1.0
[1] mean accuracy: 0.8550000190734863
=> Saving a new best
Running your script with the autograd profiler...
Loading data/small
Model with dropout!
Let's use 1 GPU(s)!
Created model with 52,718,058 parameters.
Created dataset...
Num Distinct Claims 109810
Num Data Points 125050
Num Distinct Claims 109810
Num Data Points 125050
{ data batch size: 8 }
{ learning rate: 0.001 }
{ sparse_evidences: False }
{ loss: BCEWithLogitsLoss }
{ data: data/small }
{ training size: 800 }
{ batch size: 1 }
{ epochs: 2 }
{ optimizer: Adam }
Training...
[0:0.02:1.799549s] training loss: 2.770301204174757, training accuracy: 0.7109375, training recall: 0.0
[0:0.04:1.593595s] training loss: 1.7505038101226091, training accuracy: 0.7734375, training recall: 0.0
[0:0.06:1.873918s] training loss: 1.6763805729569867, training accuracy: 0.71875, training recall: 0.0
[0:0.08:1.903438s] training loss: 1.567927349358797, training accuracy: 0.7734375, training recall: 0.0
[0:0.1:1.637169s] training loss: 1.625314665492624, training accuracy: 0.75, training recall: 0.0
[0:0.12:1.571422s] training loss: 2.296710217371583, training accuracy: 0.625, training recall: 0.0
[0:0.14:1.761692s] training loss: 1.98728994326666, training accuracy: 0.6796875, training recall: 0.0
[0:0.16:1.629935s] training loss: 1.7831056993454695, training accuracy: 0.7578125, training recall: 0.0
[0:0.18:1.341526s] training loss: 1.7635273050982505, training accuracy: 0.734375, training recall: 1.0
[0:0.2:1.467295s] training loss: 1.1158334403298795, training accuracy: 0.765625, training recall: 0.0
[0:0.22:1.482381s] training loss: 1.4855445275679813, training accuracy: 0.734375, training recall: 0.5
[0:0.24:1.445297s] training loss: 2.0631422689184546, training accuracy: 0.6640625, training recall: 0.0
[0:0.26:1.469771s] training loss: 1.4318276066333055, training accuracy: 0.8046875, training recall: 0.0
[0:0.28:1.572237s] training loss: 1.5536113497801125, training accuracy: 0.703125, training recall: 1.0
[0:0.3:1.986415s] training loss: 1.3752242242917418, training accuracy: 0.6953125, training recall: 0.5
[0:0.32:1.484233s] training loss: 1.5654486939311028, training accuracy: 0.7109375, training recall: 0.0
[0:0.34:1.560451s] training loss: 1.5712722958996892, training accuracy: 0.703125, training recall: 0.0
[0:0.36:1.359259s] training loss: 1.6526267686858773, training accuracy: 0.75, training recall: 0.0
[0:0.38:1.561586s] training loss: 1.6815892346203327, training accuracy: 0.640625, training recall: 1.0
[0:0.4:1.815159s] training loss: 1.6041760230436921, training accuracy: 0.71875, training recall: 0.0
[0:0.42:1.597624s] training loss: 1.4776467336341739, training accuracy: 0.75, training recall: 0.0
[0:0.44:1.537539s] training loss: 1.4668190623633564, training accuracy: 0.7265625, training recall: 0.0
[0:0.46:1.380171s] training loss: 1.3052913688588887, training accuracy: 0.75, training recall: 0.0
[0:0.48:1.789986s] training loss: 1.4662022325210273, training accuracy: 0.71875, training recall: 0.3333333333333333
[0:0.5:1.966776s] training loss: 1.1509871631860733, training accuracy: 0.7109375, training recall: 0.5
[0:0.52:1.654017s] training loss: 1.2098692233266775, training accuracy: 0.765625, training recall: 0.0
[0:0.54:1.755357s] training loss: 1.8365082778036594, training accuracy: 0.6796875, training recall: 1.0
[0:0.56:1.584922s] training loss: 1.7866124876309186, training accuracy: 0.75, training recall: 0.0
[0:0.58:1.593552s] training loss: 1.4226869940757751, training accuracy: 0.6953125, training recall: 0.5
[0:0.6:1.785019s] training loss: 1.1620332039892673, training accuracy: 0.734375, training recall: 1.0
[0:0.62:1.766703s] training loss: 0.969112113583833, training accuracy: 0.734375, training recall: 0.0
[0:0.64:1.756973s] training loss: 1.0878374257590622, training accuracy: 0.7578125, training recall: 0.0
[0:0.66:1.637398s] training loss: 1.1008288180455565, training accuracy: 0.765625, training recall: 0.0
[0:0.68:1.713292s] training loss: 1.4257140755653381, training accuracy: 0.71875, training recall: 0.0
[0:0.7:1.346958s] training loss: 0.8036155193112791, training accuracy: 0.8046875, training recall: 0.0
[0:0.72:1.693948s] training loss: 1.1501932608662173, training accuracy: 0.71875, training recall: 0.5
[0:0.74:1.653027s] training loss: 1.2733882495667785, training accuracy: 0.6875, training recall: 1.0
[0:0.76:1.865552s] training loss: 0.8804683489724994, training accuracy: 0.7890625, training recall: 0.5
[0:0.78:1.594837s] training loss: 1.0608321423642337, training accuracy: 0.7265625, training recall: 1.0
[0:0.8:1.905689s] training loss: 1.063410222530365, training accuracy: 0.765625, training recall: 0.0
[0:0.82:1.678597s] training loss: 1.0425992123782635, training accuracy: 0.671875, training recall: 0.0
[0:0.84:1.500055s] training loss: 1.155817202059552, training accuracy: 0.75, training recall: 0.0
[0:0.86:1.557184s] training loss: 0.909684763289988, training accuracy: 0.765625, training recall: 0.25
[0:0.88:1.577996s] training loss: 0.6071510291658342, training accuracy: 0.7734375, training recall: 0.0
[0:0.9:1.608701s] training loss: 0.6835893406532705, training accuracy: 0.8046875, training recall: 0.0
[0:0.92:1.676723s] training loss: 0.8581198779866099, training accuracy: 0.734375, training recall: 0.0
[0:0.94:1.669043s] training loss: 0.7418234002543613, training accuracy: 0.8046875, training recall: 0.0
[0:0.96:1.361662s] training loss: 0.8131461623124778, training accuracy: 0.734375, training recall: 0.5
[0:0.98:1.797866s] training loss: 0.8278355170041323, training accuracy: 0.796875, training recall: 0.0
Running validation...
[0:0.08] loss: 1.643458679318428, accuracy: 0.6640625, recall: 0.0
[0:0.16] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0:0.24] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0:0.32] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0:0.4] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0:0.48] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0:0.56] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0:0.64] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0:0.72] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0:0.8] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0:0.88] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0:0.96] loss: 1.5467846393585205, accuracy: 0.625, recall: 0.0
[0] mean accuracy: 0.7328125238418579
=> Saving a new best
[1:0.02:1.790407s] training loss: 0.6766719100996852, training accuracy: 0.828125, training recall: 0.0
[1:0.04:1.729026s] training loss: 0.7068688278086483, training accuracy: 0.71875, training recall: 0.0
[1:0.06:1.976571s] training loss: 0.5333640808239579, training accuracy: 0.796875, training recall: 1.0
[1:0.08:1.701501s] training loss: 0.7337002027779818, training accuracy: 0.7734375, training recall: 0.0
[1:0.1:1.686112s] training loss: 0.4146875604055822, training accuracy: 0.796875, training recall: 0.0
[1:0.12:1.689502s] training loss: 0.6148916233796626, training accuracy: 0.828125, training recall: 0.0
[1:0.14:1.606292s] training loss: 0.7469601687043905, training accuracy: 0.75, training recall: 0.0
[1:0.16:1.578168s] training loss: 0.479857764672488, training accuracy: 0.8125, training recall: 1.0
[1:0.18:1.796025s] training loss: 0.6114837301429361, training accuracy: 0.796875, training recall: 0.0
[1:0.2:1.603344s] training loss: 0.6349358353763819, training accuracy: 0.7734375, training recall: 1.0
[1:0.22:1.441062s] training loss: 0.5678404234349728, training accuracy: 0.765625, training recall: 0.6666666666666666
[1:0.24:1.700801s] training loss: 0.404297168366611, training accuracy: 0.8359375, training recall: 1.0
[1:0.26:1.393994s] training loss: 0.58980130427517, training accuracy: 0.7890625, training recall: 1.0
[1:0.28:1.717066s] training loss: 0.4328337339684367, training accuracy: 0.8359375, training recall: 0.0
[1:0.3:1.572278s] training loss: 0.36349094519391656, training accuracy: 0.8671875, training recall: 1.0
[1:0.32:1.562827s] training loss: 0.2806573938578367, training accuracy: 0.8828125, training recall: 1.0
[1:0.34:1.626999s] training loss: 0.3926287768408656, training accuracy: 0.875, training recall: 0.5
[1:0.36:1.624258s] training loss: 0.554046540055424, training accuracy: 0.8359375, training recall: 0.0
[1:0.38:1.377216s] training loss: 0.3284959208685905, training accuracy: 0.859375, training recall: 1.0
[1:0.4:1.836471s] training loss: 0.5950589356943965, training accuracy: 0.8046875, training recall: 0.0
[1:0.42:1.794727s] training loss: 0.39580009039491415, training accuracy: 0.796875, training recall: 0.5
[1:0.44:1.499227s] training loss: 0.46750780544243753, training accuracy: 0.8125, training recall: 1.0
[1:0.46:1.625941s] training loss: 0.31805950379930437, training accuracy: 0.859375, training recall: 0.0
[1:0.48:1.903980s] training loss: 0.3308745794929564, training accuracy: 0.890625, training recall: 0.0
[1:0.5:1.650262s] training loss: 0.3076979569159448, training accuracy: 0.8984375, training recall: 0.5
[1:0.52:1.682921s] training loss: 0.3239758377894759, training accuracy: 0.875, training recall: 1.0
[1:0.54:1.522296s] training loss: 0.36344807501882315, training accuracy: 0.84375, training recall: 0.5
[1:0.56:2.144951s] training loss: 0.34796341974288225, training accuracy: 0.8515625, training recall: 0.5
[1:0.58:1.698655s] training loss: 0.33196922950446606, training accuracy: 0.859375, training recall: 0.0
[1:0.6:1.654287s] training loss: 0.37578451447188854, training accuracy: 0.828125, training recall: 0.5
[1:0.62:1.525563s] training loss: 0.3108547106385231, training accuracy: 0.84375, training recall: 1.0
[1:0.64:1.610599s] training loss: 0.381292020669207, training accuracy: 0.8515625, training recall: 0.0
[1:0.66:1.624164s] training loss: 0.35726884566247463, training accuracy: 0.8515625, training recall: 1.0
[1:0.68:1.740733s] training loss: 0.34624173771589994, training accuracy: 0.8515625, training recall: 0.0
[1:0.7:1.449246s] training loss: 0.34541636146605015, training accuracy: 0.8359375, training recall: 0.5
[1:0.72:1.544621s] training loss: 0.3579387296922505, training accuracy: 0.8515625, training recall: 1.0
[1:0.74:1.924309s] training loss: 0.40871973242610693, training accuracy: 0.8125, training recall: 0.0
[1:0.76:1.428034s] training loss: 0.4606852298602462, training accuracy: 0.8203125, training recall: 0.0
[1:0.78:1.341936s] training loss: 0.34960790257900953, training accuracy: 0.8359375, training recall: 0.0
[1:0.8:1.690659s] training loss: 0.3198214606381953, training accuracy: 0.859375, training recall: 0.0
[1:0.82:1.372239s] training loss: 0.2654005184303969, training accuracy: 0.8828125, training recall: 1.0
[1:0.84:1.520710s] training loss: 0.30467129312455654, training accuracy: 0.8984375, training recall: 1.0
[1:0.86:1.324038s] training loss: 0.303582139313221, training accuracy: 0.8671875, training recall: 0.0
[1:0.88:1.642835s] training loss: 0.3516188086941838, training accuracy: 0.828125, training recall: 0.0
[1:0.9:1.611845s] training loss: 0.3758201338350773, training accuracy: 0.859375, training recall: 0.75
[1:0.92:1.712033s] training loss: 0.301265190821141, training accuracy: 0.859375, training recall: 0.0
[1:0.94:1.505953s] training loss: 0.4322487178724259, training accuracy: 0.859375, training recall: 1.0
[1:0.96:1.789186s] training loss: 0.2476060725748539, training accuracy: 0.8828125, training recall: 0.0
[1:0.98:1.756561s] training loss: 0.3324383972212672, training accuracy: 0.859375, training recall: 0.5
Running validation...
[1:0.08] loss: 0.35526988469064236, accuracy: 0.9296875, recall: 0.5
[1:0.16] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1:0.24] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1:0.32] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1:0.4] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1:0.48] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1:0.56] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1:0.64] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1:0.72] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1:0.8] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1:0.88] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1:0.96] loss: 0.3343716561794281, accuracy: 0.875, recall: 0.5
[1] mean accuracy: 0.8353124856948853
=> Saving a new best
Loading data/small
Model with dropout!
Let's use 1 GPU(s)!
Created model with 52,718,058 parameters.
Created dataset...
Num Distinct Claims 109810
Num Data Points 125050
Num Distinct Claims 109810
Num Data Points 125050
{ data batch size: 8 }
{ learning rate: 0.001 }
{ sparse_evidences: False }
{ loss: BCEWithLogitsLoss }
{ data: data/small }
{ training size: 800 }
{ batch size: 1 }
{ epochs: 2 }
{ optimizer: Adam }
Training...
[0:0.02:2.907552s] training loss: 3.2201793093263404, training accuracy: 0.7734375, training recall: 1.0
[0:0.04:2.642347s] training loss: 3.221892437468341, training accuracy: 0.734375, training recall: 0.0
[0:0.06:3.253891s] training loss: 3.210664635989815, training accuracy: 0.6640625, training recall: 0.0
[0:0.08:2.244245s] training loss: 2.748651122819865, training accuracy: 0.6875, training recall: 0.0
[0:0.1:3.440181s] training loss: 3.3229784052819014, training accuracy: 0.6484375, training recall: 0.0
[0:0.12:2.460248s] training loss: 2.3887702068313956, training accuracy: 0.7109375, training recall: 0.0
[0:0.14:3.501467s] training loss: 2.3069399325177073, training accuracy: 0.703125, training recall: 0.5
[0:0.16:2.560524s] training loss: 2.5985734269488603, training accuracy: 0.765625, training recall: 0.5
[0:0.18:3.399235s] training loss: 3.096547821885906, training accuracy: 0.71875, training recall: 0.0
[0:0.2:2.449790s] training loss: 2.380693088285625, training accuracy: 0.78125, training recall: 1.0
[0:0.22:3.458036s] training loss: 2.175698361825198, training accuracy: 0.8046875, training recall: 0.0
[0:0.24:2.755979s] training loss: 2.482026582583785, training accuracy: 0.6875, training recall: 0.0
[0:0.26:3.260757s] training loss: 2.6613409090787172, training accuracy: 0.6328125, training recall: 0.0
[0:0.28:2.507471s] training loss: 2.495532840470787, training accuracy: 0.78125, training recall: 1.0
[0:0.3:2.228002s] training loss: 4.044905906077474, training accuracy: 0.625, training recall: 0.0
[0:0.32:3.209422s] training loss: 2.20362893154379, training accuracy: 0.671875, training recall: 0.0
[0:0.34:3.506223s] training loss: 2.464168141130358, training accuracy: 0.6640625, training recall: 1.0
[0:0.36:2.760761s] training loss: 2.282376781105995, training accuracy: 0.7890625, training recall: 0.0
[0:0.38:3.227114s] training loss: 2.771688774228096, training accuracy: 0.6796875, training recall: 0.0
[0:0.4:2.618481s] training loss: 2.847048246767372, training accuracy: 0.640625, training recall: 0.0
[0:0.42:3.414023s] training loss: 2.65843005804345, training accuracy: 0.7265625, training recall: 0.0
[0:0.44:2.526261s] training loss: 1.7796866362068613, training accuracy: 0.734375, training recall: 0.0
[0:0.46:3.150177s] training loss: 1.4408193613635376, training accuracy: 0.7578125, training recall: 0.0
[0:0.48:2.570828s] training loss: 2.578956924378872, training accuracy: 0.65625, training recall: 0.0
[0:0.5:2.279073s] training loss: 1.8249185308814049, training accuracy: 0.78125, training recall: 0.0
[0:0.52:3.495307s] training loss: 1.8818762376904488, training accuracy: 0.703125, training recall: 0.0
[0:0.54:1.531745s] training loss: 2.0788686256855726, training accuracy: 0.7421875, training recall: 0.0
[0:0.56:1.558903s] training loss: 1.7664635637775064, training accuracy: 0.71875, training recall: 0.0
[0:0.58:1.828994s] training loss: 1.785342223229236, training accuracy: 0.8515625, training recall: 0.0
[0:0.6:1.788460s] training loss: 2.132957054185681, training accuracy: 0.703125, training recall: 0.0
[0:0.62:1.751368s] training loss: 1.535471105016768, training accuracy: 0.7421875, training recall: 0.0
[0:0.64:1.668330s] training loss: 1.8265665536746383, training accuracy: 0.71875, training recall: 0.5
[0:0.66:1.635805s] training loss: 1.468316076146948, training accuracy: 0.7265625, training recall: 0.0
[0:0.68:1.880821s] training loss: 1.9770766613073647, training accuracy: 0.6953125, training recall: 1.0
[0:0.7:1.588350s] training loss: 1.8985918976832181, training accuracy: 0.7265625, training recall: 1.0
[0:0.72:1.688732s] training loss: 2.206326447427273, training accuracy: 0.671875, training recall: 0.0
[0:0.74:1.820281s] training loss: 1.845008349046111, training accuracy: 0.734375, training recall: 0.0
[0:0.76:1.701261s] training loss: 2.01296617067419, training accuracy: 0.734375, training recall: 0.0
[0:0.78:1.872018s] training loss: 1.6095565115101635, training accuracy: 0.71875, training recall: 1.0
[0:0.8:1.625052s] training loss: 2.2640599138394464, training accuracy: 0.7421875, training recall: 1.0
[0:0.82:1.914879s] training loss: 2.030324272811413, training accuracy: 0.703125, training recall: 0.0
[0:0.84:1.820615s] training loss: 1.7830087318725418, training accuracy: 0.78125, training recall: 1.0
[0:0.86:1.962955s] training loss: 1.6330870371311903, training accuracy: 0.75, training recall: 0.5
[0:0.88:1.803305s] training loss: 1.5177079886198044, training accuracy: 0.71875, training recall: 0.0
[0:0.9:1.874948s] training loss: 1.9056008839979768, training accuracy: 0.703125, training recall: 1.0
[0:0.92:1.895457s] training loss: 1.2284981037955731, training accuracy: 0.65625, training recall: 0.0
[0:0.94:1.598988s] training loss: 1.448555339127779, training accuracy: 0.8359375, training recall: 1.0
[0:0.96:2.133621s] training loss: 1.3240299196913838, training accuracy: 0.703125, training recall: 0.5
[0:0.98:1.625945s] training loss: 1.7666459828615189, training accuracy: 0.6953125, training recall: 0.0
Running validation...
[0:0.08] loss: 2.2646602392196655, accuracy: 0.9296875, recall: 0.0
[0:0.16] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0:0.24] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0:0.32] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0:0.4] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0:0.48] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0:0.56] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0:0.64] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0:0.72] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0:0.8] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0:0.88] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0:0.96] loss: 2.1314449310302734, accuracy: 0.875, recall: 0.0
[0] mean accuracy: 0.7204687595367432
=> Saving a new best
[1:0.02:1.901477s] training loss: 1.1137547091639135, training accuracy: 0.890625, training recall: 1.0
[1:0.04:1.874347s] training loss: 1.2654199449170846, training accuracy: 0.734375, training recall: 0.0
[1:0.06:2.114561s] training loss: 1.4749444127082825, training accuracy: 0.765625, training recall: 0.0
[1:0.08:1.754646s] training loss: 1.0426720400355407, training accuracy: 0.7890625, training recall: 0.5
[1:0.1:1.886310s] training loss: 1.0530964864883572, training accuracy: 0.8046875, training recall: 0.0
[1:0.12:1.591209s] training loss: 1.2466447139158845, training accuracy: 0.75, training recall: 1.0
[1:0.14:1.678609s] training loss: 0.9811171852052212, training accuracy: 0.765625, training recall: 0.0
[1:0.16:1.793899s] training loss: 1.1584612429141998, training accuracy: 0.71875, training recall: 1.0
[1:0.18:1.655316s] training loss: 1.3545797164551914, training accuracy: 0.796875, training recall: 0.5
[1:0.2:1.773507s] training loss: 0.8793401047587395, training accuracy: 0.796875, training recall: 1.0
[1:0.22:1.610855s] training loss: 1.1451940285041928, training accuracy: 0.7109375, training recall: 0.0
[1:0.24:1.555208s] training loss: 1.0953840233851224, training accuracy: 0.8203125, training recall: 1.0
[1:0.26:1.745916s] training loss: 0.9060560180805624, training accuracy: 0.75, training recall: 0.0
[1:0.28:1.924163s] training loss: 0.9225911235007516, training accuracy: 0.8828125, training recall: 1.0
[1:0.3:1.756404s] training loss: 0.8500484398682602, training accuracy: 0.8515625, training recall: 0.25
[1:0.32:1.982041s] training loss: 1.1270469767041504, training accuracy: 0.7109375, training recall: 1.0
[1:0.34:1.744665s] training loss: 1.0218886211514473, training accuracy: 0.7890625, training recall: 0.0
[1:0.36:1.799723s] training loss: 0.843165829544887, training accuracy: 0.71875, training recall: 1.0
[1:0.38:1.763165s] training loss: 0.6739743375292164, training accuracy: 0.8828125, training recall: 1.0
[1:0.4:1.680393s] training loss: 0.6683949767611921, training accuracy: 0.84375, training recall: 0.0
[1:0.42:1.691595s] training loss: 0.8289162827131804, training accuracy: 0.7890625, training recall: 1.0
[1:0.44:1.781530s] training loss: 0.5593538455141243, training accuracy: 0.859375, training recall: 0.0
[1:0.46:1.961230s] training loss: 0.8750009657815099, training accuracy: 0.796875, training recall: 1.0
[1:0.48:1.896954s] training loss: 0.7754908910574159, training accuracy: 0.84375, training recall: 0.0
[1:0.5:2.076347s] training loss: 0.8714822182082571, training accuracy: 0.796875, training recall: 1.0
[1:0.52:1.737730s] training loss: 0.6686870232806541, training accuracy: 0.8046875, training recall: 0.0
[1:0.54:1.773992s] training loss: 0.7463656021864153, training accuracy: 0.8046875, training recall: 1.0
[1:0.56:1.863679s] training loss: 0.5950263919075951, training accuracy: 0.84375, training recall: 0.5
[1:0.58:1.817453s] training loss: 0.46146254800260067, training accuracy: 0.8515625, training recall: 0.0
[1:0.6:1.589539s] training loss: 0.5189191796525847, training accuracy: 0.859375, training recall: 1.0
[1:0.62:1.581773s] training loss: 0.5745497156167403, training accuracy: 0.8359375, training recall: 0.5
[1:0.64:1.886483s] training loss: 0.9339822852052748, training accuracy: 0.7890625, training recall: 1.0
[1:0.66:1.384642s] training loss: 0.7184156246366911, training accuracy: 0.7734375, training recall: 0.0
[1:0.68:1.865227s] training loss: 0.8325746378395706, training accuracy: 0.8203125, training recall: 1.0
[1:0.7:1.744332s] training loss: 0.6333266785368323, training accuracy: 0.8125, training recall: 0.0
[1:0.72:1.711574s] training loss: 0.6186854783445597, training accuracy: 0.78125, training recall: 1.0
[1:0.74:1.895996s] training loss: 0.5237115698400885, training accuracy: 0.828125, training recall: 1.0
[1:0.76:1.856746s] training loss: 0.5210837577469647, training accuracy: 0.828125, training recall: 0.0
[1:0.78:1.581324s] training loss: 0.5818733708001673, training accuracy: 0.7734375, training recall: 0.0
[1:0.8:1.887546s] training loss: 0.710818893101532, training accuracy: 0.8125, training recall: 1.0
[1:0.82:1.806897s] training loss: 0.5469755781814456, training accuracy: 0.8125, training recall: 0.0
[1:0.84:1.550565s] training loss: 0.6956516111968085, training accuracy: 0.7890625, training recall: 0.75
[1:0.86:1.729720s] training loss: 0.557975257281214, training accuracy: 0.796875, training recall: 0.0
[1:0.88:1.837265s] training loss: 0.5386152025312185, training accuracy: 0.796875, training recall: 0.0
[1:0.9:1.789729s] training loss: 0.610389078501612, training accuracy: 0.796875, training recall: 0.0
[1:0.92:1.880265s] training loss: 0.6087600160390139, training accuracy: 0.7890625, training recall: 0.0
[1:0.94:1.675622s] training loss: 0.6395999975502491, training accuracy: 0.7578125, training recall: 0.0
[1:0.96:1.883381s] training loss: 0.6383856181055307, training accuracy: 0.78125, training recall: 1.0
[1:0.98:2.069027s] training loss: 0.6708082715049386, training accuracy: 0.78125, training recall: 1.0
Running validation...
[1:0.08] loss: 0.3507625348865986, accuracy: 0.9296875, recall: 0.5
[1:0.16] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1:0.24] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1:0.32] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1:0.4] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1:0.48] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1:0.56] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1:0.64] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1:0.72] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1:0.8] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1:0.88] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1:0.96] loss: 0.3301294445991516, accuracy: 0.875, recall: 0.5
[1] mean accuracy: 0.7996875047683716
=> Saving a new best
--------------------------------------------------------------------------------
  Environment Summary
--------------------------------------------------------------------------------
PyTorch 0.4.1 compiled w/ CUDA 8.0.61
Running with Python 3.5 and 

`pip list` truncated output:
Unable to fetch
--------------------------------------------------------------------------------
  cProfile output
--------------------------------------------------------------------------------
         179921596 function calls (179728419 primitive calls) in 310.482 seconds

   Ordered by: internal time
   List reduced from 9437 to 15 due to restriction <15>

   ncalls  tottime  percall  cumtime  percall filename:lineno(function)
     4366   71.164    0.016   71.164    0.016 {built-in method numpy.core.multiarray.copyto}
     4000   21.213    0.005   92.789    0.023 /data/sls/u/urop/mnadeem/CDSSM_github/pytorch_data_loader.py:147(stack_uneven)
     3600   20.193    0.006   20.193    0.006 {method 'mean' of 'torch._C._TensorBase' objects}
     7620   20.183    0.003   20.183    0.003 {method 'cuda' of 'torch._C._TensorBase' objects}
        6   12.815    2.136   65.309   10.885 /usr/lib/python3.5/pickle.py:1014(load)
     1620    8.675    0.005    8.675    0.005 {method 'to' of 'torch._C._TensorBase' objects}
     1600    8.372    0.005    8.372    0.005 {method 'run_backward' of 'torch._C._EngineBase' objects}
 28833174    7.607    0.000   11.749    0.000 /usr/lib/python3.5/pickle.py:226(read)
        1    7.546    7.546  245.792  245.792 clsm_pytorch.py:55(run)
    66001    7.076    0.000    7.076    0.000 {built-in method numpy.core.multiarray.zeros}
   812033    5.773    0.000    5.773    0.000 {method 'reduce' of 'numpy.ufunc' objects}
 29179332    4.565    0.000    4.565    0.000 {method 'read' of '_io.BufferedReader' objects}
   346136    4.437    0.000   12.384    0.000 /data/sls/u/urop/mnadeem/my_venv/lib/python3.5/site-packages/joblib/numpy_pickle.py:106(read_array)
        2    3.805    1.903    3.805    1.903 {method 'close' of '_io.BufferedWriter' objects}
     6000    3.547    0.001    3.547    0.001 {built-in method conv1d}


--------------------------------------------------------------------------------
  autograd profiler output (CPU mode)
--------------------------------------------------------------------------------
        top 15 events sorted by cpu_time_total

------------  ---------------  ---------------  ---------------  ---------------  ---------------
Name                 CPU time        CUDA time            Calls        CPU total       CUDA total
------------  ---------------  ---------------  ---------------  ---------------  ---------------
uniform_         380120.815us          0.000us                1     380120.815us          0.000us
uniform_         295232.994us          0.000us                1     295232.994us          0.000us
uniform_         286413.407us          0.000us                1     286413.407us          0.000us
uniform_         281958.053us          0.000us                1     281958.053us          0.000us
mean              37146.238us          0.000us                1      37146.238us          0.000us
mean              35374.879us          0.000us                1      35374.879us          0.000us
mean              24248.226us          0.000us                1      24248.226us          0.000us
mean              23398.459us          0.000us                1      23398.459us          0.000us
mean              23031.473us          0.000us                1      23031.473us          0.000us
mean              22305.312us          0.000us                1      22305.312us          0.000us
mean              21449.057us          0.000us                1      21449.057us          0.000us
mean              21179.416us          0.000us                1      21179.416us          0.000us
mean              21168.822us          0.000us                1      21168.822us          0.000us
mean              20761.019us          0.000us                1      20761.019us          0.000us
mean              20713.925us          0.000us                1      20713.925us          0.000us

--------------------------------------------------------------------------------
  autograd profiler output (CUDA mode)
--------------------------------------------------------------------------------
        top 15 events sorted by cpu_time_total

	Because the autograd profiler uses the CUDA event API,
	the CUDA time column reports approximately max(cuda_time, cpu_time).
	Please ignore this output if your code does not use CUDA.

------------------  ---------------  ---------------  ---------------  ---------------  ---------------
Name                       CPU time        CUDA time            Calls        CPU total       CUDA total
------------------  ---------------  ---------------  ---------------  ---------------  ---------------
ExpBackward            864587.687us     864550.781us                1     864587.687us     864550.781us
mul                    864572.023us     864535.156us                1     864572.023us     864535.156us
add                    836805.395us     821511.719us                1     836805.395us     821511.719us
_th_get_device         836635.033us     821355.469us                1     836635.033us     821355.469us
ViewBackward           835405.869us     834093.750us                1     835405.869us     834093.750us
reshape                835363.967us     834078.125us                1     835363.967us     834078.125us
MmBackward             832343.973us     830591.797us                1     832343.973us     830591.797us
mm                     832215.349us     830550.781us                1     832215.349us     830550.781us
add                    778899.768us     765046.875us                1     778899.768us     765046.875us
_th_get_device         778725.279us     764898.438us                1     778725.279us     764898.438us
Scatter                754150.299us     754054.688us                1     754150.299us     754054.688us
_th_get_device         749047.608us     748968.750us                1     749047.608us     748968.750us
add_                   704861.748us     695902.344us                1     704861.748us     695902.344us
th_add_                704806.990us     695871.094us                1     704806.990us     695871.094us
matmul                 702950.014us     693304.688us                1     702950.014us     693304.688us