Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 1467195066658357248
In this apply, we use a network to learn this target input, given it's pre-evaluated output:
TrainingTester.java:332 executed in 0.02 seconds (0.000 gc):
return RefArrays.stream(RefUtil.addRef(input_target)).flatMap(RefArrays::stream).map(x -> {
try {
return x.prettyPrint();
} finally {
x.freeRef();
}
}).reduce((a, b) -> a + "\n" + b).orElse("");
Returns
[
[ [ 0.636 ], [ 1.912 ], [ 1.556 ], [ 1.64 ], [ -1.424 ], [ -1.028 ], [ -0.804 ], [ 1.356 ] ],
[ [ -0.852 ], [ -0.804 ], [ 0.092 ], [ 1.612 ], [ -1.832 ], [ 0.996 ], [ -0.464 ], [ 1.512 ] ],
[ [ 0.048 ], [ 0.08 ], [ 0.148 ], [ -1.72 ], [ 0.392 ], [ 0.048 ], [ 1.652 ], [ 0.3 ] ],
[ [ 1.552 ], [ -0.712 ], [ -0.608 ], [ 1.62 ], [ -0.384 ], [ 0.7 ], [ 1.208 ], [ -0.556 ] ],
[ [ -1.228 ], [ -1.616 ], [ -1.572 ], [ -0.384 ], [ 0.496 ], [ 1.108 ], [ -0.032 ], [ -1.688 ] ],
[ [ 0.788 ], [ 1.764 ], [ -0.768 ], [ 0.028 ], [ -0.012 ], [ -0.876 ], [ -0.176 ], [ -0.408 ] ],
[ [ -1.516 ], [ -1.476 ], [ 1.032 ], [ -0.068 ], [ 1.556 ], [ -0.892 ], [ -1.856 ], [ -1.492 ] ],
[ [ -1.54 ], [ -0.128 ], [ -0.636 ], [ 1.876 ], [ 1.368 ], [ 1.048 ], [ 1.524 ], [ 1.704 ] ]
]
[
[ [ -1.492 ], [ -0.032 ], [ 1.876 ], [ -0.892 ], [ -1.476 ], [ 1.108 ], [ -1.424 ], [ -1.688 ] ],
[ [ -0.852 ], [ 1.704 ], [ -0.804 ], [ -0.804 ], [ 0.3 ], [ 1.552 ], [ 0.636 ], [ -1.856 ] ],
[ [ -1.228 ], [ -1.72 ], [ 1.912 ], [ 1.208 ], [ -1.572 ], [ 0.028 ], [ -0.408 ], [ 1.64 ] ],
[ [ 1.764 ], [ 0.148 ], [ -0.012 ], [ -0.556 ], [ -1.028 ], [ -1.616 ], [ 1.512 ], [ -0.384 ] ],
[ [ -0.176 ], [ 0.092 ], [ 0.08 ], [ 1.048 ], [ 0.7 ], [ -0.464 ], [ 0.788 ], [ 1.652 ] ],
[ [ -0.636 ], [ -0.068 ], [ -1.54 ], [ 1.556 ], [ -1.516 ], [ 1.556 ], [ 1.524 ], [ -0.876 ] ],
[ [ 0.048 ], [ 1.62 ], [ -0.128 ], [ 1.356 ], [ 1.612 ], [ 0.048 ], [ 1.032 ], [ -0.384 ] ],
[ [ -0.768 ], [ -0.712 ], [ 1.368 ], [ 0.996 ], [ -0.608 ], [ 0.392 ], [ 0.496 ], [ -1.832 ] ]
]
[
[ [ -1.54 ], [ -0.384 ], [ 1.556 ], [ 1.552 ], [ -1.228 ], [ -1.492 ], [ 1.048 ], [ -0.636 ] ],
[ [ -0.464 ], [ -1.72 ], [ 0.092 ], [ -0.804 ], [ -0.128 ], [ 1.032 ], [ 0.148 ], [ 1.524 ] ],
[ [ 0.996 ], [ -0.068 ], [ -1.516 ], [ -0.608 ], [ 0.392 ], [ 0.028 ], [ 1.356 ], [ -1.688 ] ],
[ [ 0.3 ], [ 1.876 ], [ 0.496 ], [ 0.788 ], [ -0.408 ], [ -1.476 ], [ 0.048 ], [ -0.556 ] ],
[ [ 0.048 ], [ -1.856 ], [ -0.176 ], [ -1.572 ], [ 1.368 ], [ -1.424 ], [ 1.64 ], [ 1.108 ] ],
[ [ -0.804 ], [ -0.892 ], [ 1.62 ], [ -1.616 ], [ 1.704 ], [ 1.612 ], [ -1.832 ], [ -0.032 ] ],
[ [ 1.208 ], [ 1.652 ], [ -0.712 ], [ 0.636 ], [ -0.384 ], [ 1.512 ], [ 0.7 ], [ -0.012 ] ],
[ [ 1.556 ], [ 1.912 ], [ 1.764 ], [ -1.028 ], [ -0.768 ], [ 0.08 ], [ -0.876 ], [ -0.852 ] ]
]
[
[ [ 1.368 ], [ 0.092 ], [ -0.556 ], [ 0.636 ], [ 1.108 ], [ -1.54 ], [ 1.64 ], [ 0.3 ] ],
[ [ -0.636 ], [ -0.128 ], [ -1.424 ], [ -0.384 ], [ -1.492 ], [ 1.356 ], [ -1.228 ], [ 1.552 ] ],
[ [ 1.704 ], [ 0.7 ], [ -1.856 ], [ -1.516 ], [ 1.556 ], [ -1.572 ], [ 1.62 ], [ 1.912 ] ],
[ [ -0.804 ], [ 1.048 ], [ 1.512 ], [ 0.048 ], [ 1.524 ], [ 0.028 ], [ -0.712 ], [ -0.804 ] ],
[ [ -1.616 ], [ 1.032 ], [ 1.556 ], [ -0.032 ], [ 1.208 ], [ 0.048 ], [ -0.768 ], [ -0.012 ] ],
[ [ -0.892 ], [ -0.464 ], [ 0.788 ], [ -1.72 ], [ -1.688 ], [ 1.876 ], [ -0.876 ], [ 0.08 ] ],
[ [ 0.148 ], [ -1.476 ], [ 1.612 ], [ -0.608 ], [ 1.764 ], [ -0.384 ], [ 0.392 ], [ -0.068 ] ],
[ [ -1.832 ], [ 0.996 ], [ -0.176 ], [ 0.496 ], [ -0.852 ], [ 1.652 ], [ -0.408 ], [ -1.028 ] ]
]
[
[ [ -1.572 ], [ 1.704 ], [ 0.788 ], [ -1.492 ], [ -0.012 ], [ 1.368 ], [ 1.356 ], [ -0.068 ] ],
[ [ 1.552 ], [ 1.108 ], [ -1.616 ], [ -0.128 ], [ 0.048 ], [ 1.764 ], [ -0.384 ], [ -0.176 ] ],
[ [ -1.476 ], [ 0.3 ], [ 1.556 ], [ 1.524 ], [ -1.72 ], [ 1.208 ], [ -0.608 ], [ 1.512 ] ],
[ [ -1.54 ], [ -1.028 ], [ -1.832 ], [ 1.032 ], [ -0.032 ], [ -1.516 ], [ -0.768 ], [ 1.048 ] ],
[ [ -1.688 ], [ 0.028 ], [ -0.408 ], [ 1.612 ], [ -1.424 ], [ -0.636 ], [ 0.048 ], [ -0.852 ] ],
[ [ 0.08 ], [ 1.876 ], [ -0.384 ], [ 0.496 ], [ 1.652 ], [ 0.092 ], [ -0.556 ], [ 1.64 ] ],
[ [ -0.804 ], [ -1.856 ], [ -1.228 ], [ 0.636 ], [ 1.912 ], [ -0.712 ], [ -0.892 ], [ -0.804 ] ],
[ [ 1.62 ], [ 0.392 ], [ 0.7 ], [ 0.996 ], [ -0.464 ], [ 0.148 ], [ 1.556 ], [ -0.876 ] ]
]
First, we train using basic gradient descent method apply weak line search conditions.
TrainingTester.java:480 executed in 0.69 seconds (0.000 gc):
IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
try {
iterativeTrainer.setLineSearchFactory(label -> new ArmijoWolfeSearch());
iterativeTrainer.setOrientation(new GradientDescent());
iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
iterativeTrainer.setMaxIterations(250);
iterativeTrainer.setTerminateThreshold(0);
return iterativeTrainer.run();
} finally {
iterativeTrainer.freeRef();
}
Reset training subject: 356174934639
BACKPROP_AGG_SIZE = 3
THREADS = 64
SINGLE_THREADED = false
Initialized CoreSettings = {
"backpropAggregationSize" : 3,
"jvmThreads" : 64,
"singleThreaded" : false
}
Reset training subject: 356216093859
Constructing line search parameters: GD
th(0)=54.726825944839185;dx=-5.6014848000000013E23
New Minimum: 54.726825944839185 > 0.0
Armijo: th(2.154434690031884)=0.0; dx=-5.601484800005569E11 evalInputDelta=54.726825944839185
Armijo: th(1.077217345015942)=0.02590359656412173; dx=-5.601484800005731E11 evalInputDelta=54.700922348275064
Armijo: th(0.3590724483386473)=0.13961221994753872; dx=-5.6014848000075E11 evalInputDelta=54.58721372489165
Armijo: th(0.08976811208466183)=0.3491080114309031; dx=-5.601484800015562E11 evalInputDelta=54.377717933408285
Armijo: th(0.017953622416932366)=0.4754795760379441; dx=-5.601484800027084E11 evalInputDelta=54.251346368801244
Armijo: th(0.002992270402822061)=0.5164347412167083; dx=-5.601484800033026E11 evalInputDelta=54.21039120362248
Armijo: th(4.2746720040315154E-4)=0.5244456181026621; dx=-5.601484800034369E11 evalInputDelta=54.202380326736524
Armijo: th(5.343340005039394E-5)=0.5256432078089327; dx=-5.601484800034575E11 evalInputDelta=54.20118273703025
Armijo: th(5.9370444500437714E-6)=0.5257958364354878; dx=-5.601484800034602E11 evalInputDelta=54.2010301084037
Armijo: th(5.937044450043771E-7)=0.5258130150056665; dx=-5.601484800034604E11 evalInputDelta=54.20101292983352
Armijo: th(5.397313136403428E-8)=0.5258147503031128; dx=-5.601484800034604E11 evalInputDelta=54.20101119453607
Armijo: th(4.4977609470028565E-9)=0.5258149093728564; dx=-5.601484800034604E11 evalInputDelta=54.20101103546633
Armijo: th(3.4598161130791205E-10)=0.5258149227213726; dx=-5.601484800034604E11 evalInputDelta=54.20101102211781
Armijo: th(2.4712972236279432E-11)=0.5401243828088803; dx=-5.604654753271477E11 evalInputDelta=54.1867015620303
Armijo: th(1.6475314824186289E-12)=41.015348072966894; dx=-4.2322112000056853E23 evalInputDelta=13.71147787187229
Armijo: th(1.029707176511643E-13)=54.72682594483886; dx=-5.6014848000000013E23 evalInputDelta=3.268496584496461E-13
Armijo: th(6.057101038303783E-15)=54.72682594483918; dx=-5.6014848000000013E23 evalInputDelta=7.105427357601002E-15
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.0
Fitness changed from 54.726825944839185 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.6415; Orientation: 0.0042; Line Search: 0.5731
th(0)=0.0;dx=-0.8363641600000001
Armijo: th(2.154434690031884E-15)=0.0; dx=-0.83636416 evalInputDelta=0.0
Armijo: th(1.077217345015942E-15)=0.0; dx=-0.8363641600000001 evalInputDelta=0.0
MIN ALPHA (3.5907244833864734E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.0331; Orientation: 0.0015; Line Search: 0.0270
Iteration 2 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 2
Final threshold in iteration 2: 0.0 (> 0.0) after 0.676s (< 30.000s)
Returns
0.0
First, we use a conjugate gradient descent method, which converges the fastest for purely linear functions.
TrainingTester.java:452 executed in 0.63 seconds (0.000 gc):
IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
try {
iterativeTrainer.setLineSearchFactory(label -> new QuadraticSearch());
iterativeTrainer.setOrientation(new GradientDescent());
iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
iterativeTrainer.setMaxIterations(250);
iterativeTrainer.setTerminateThreshold(0);
return iterativeTrainer.run();
} finally {
iterativeTrainer.freeRef();
}
Reset training subject: 356855236845
Reset training subject: 356857846885
Constructing line search parameters: GD
F(0.0) = LineSearchPoint{point=PointSample{avg=54.726825944839185}, derivative=-5.6014848000000013E23}
New Minimum: 54.726825944839185 > 0.5263275709688162
F(1.0E-10) = LineSearchPoint{point=PointSample{avg=0.5263275709688162}, derivative=-5.60153535193334E11}, evalInputDelta = -54.20049837387037
New Minimum: 0.5263275709688162 > 0.5258149215831569
F(7.000000000000001E-10) = LineSearchPoint{point=PointSample{avg=0.5258149215831569}, derivative=-5.601484800034604E11}, evalInputDelta = -54.20101102325603
New Minimum: 0.5258149215831569 > 0.5258149080796051
F(4.900000000000001E-9) = LineSearchPoint{point=PointSample{avg=0.5258149080796051}, derivative=-5.601484800034604E11}, evalInputDelta = -54.20101103675958
New Minimum: 0.5258149080796051 > 0.5258148135547697
F(3.430000000000001E-8) = LineSearchPoint{point=PointSample{avg=0.5258148135547697}, derivative=-5.601484800034604E11}, evalInputDelta = -54.20101113128442
New Minimum: 0.5258148135547697 > 0.525814151882269
F(2.4010000000000004E-7) = LineSearchPoint{point=PointSample{avg=0.525814151882269}, derivative=-5.601484800034604E11}, evalInputDelta = -54.20101179295692
New Minimum: 0.525814151882269 > 0.5258095202407518
F(1.6807000000000003E-6) = LineSearchPoint{point=PointSample{avg=0.5258095202407518}, derivative=-5.601484800034604E11}, evalInputDelta = -54.201016424598436
New Minimum: 0.5258095202407518 > 0.525777101983089
F(1.1764900000000001E-5) = LineSearchPoint{point=PointSample{avg=0.525777101983089}, derivative=-5.601484800034598E11}, evalInputDelta = -54.201048842856096
New Minimum: 0.525777101983089 > 0.5255503324354495
F(8.235430000000001E-5) = LineSearchPoint{point=PointSample{avg=0.5255503324354495}, derivative=-5.601484800034559E11}, evalInputDelta = -54.201275612403734
New Minimum: 0.5255503324354495 > 0.5239706460652254
F(5.764801000000001E-4) = LineSearchPoint{point=PointSample{avg=0.5239706460652254}, derivative=-5.601484800034287E11}, evalInputDelta = -54.20285529877396
New Minimum: 0.5239706460652254 > 0.513272596899055
F(0.004035360700000001) = LineSearchPoint{point=PointSample{avg=0.513272596899055}, derivative=-5.601484800032515E11}, evalInputDelta = -54.21355334794013
New Minimum: 0.513272596899055 > 0.45165735310657185
F(0.028247524900000005) = LineSearchPoint{point=PointSample{avg=0.45165735310657185}, derivative=-5.601484800024233E11}, evalInputDelta = -54.275168591732616
New Minimum: 0.45165735310657185 > 0.2405736833243089
F(0.19773267430000002) = LineSearchPoint{point=PointSample{avg=0.2405736833243089}, derivative=-5.601484800010365E11}, evalInputDelta = -54.48625226151488
New Minimum: 0.2405736833243089 > 0.009914042681668817
F(1.3841287201) = LineSearchPoint{point=PointSample{avg=0.009914042681668817}, derivative=-5.601484800005625E11}, evalInputDelta = -54.71691190215751
New Minimum: 0.009914042681668817 > 0.0
F(9.688901040700001) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(67.8223072849) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(474.7561509943) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(3323.2930569601003) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(23263.0513987207) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(162841.3597910449) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(1139889.5185373144) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(7979226.6297612) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(5.58545864083284E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(3.909821048582988E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(2.7368747340080914E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
F(1.915812313805664E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
0.0 <= 54.726825944839185
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-5.601484800005569E11}, evalInputDelta = -54.726825944839185
Right bracket at 1.0E10
Converged to right
Fitness changed from 54.726825944839185 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.5106; Orientation: 0.0012; Line Search: 0.4986
F(0.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.8363641600000001}
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.8363641600000001}, evalInputDelta = 0.0
0.0 <= 0.0
F(5.0E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.83636416}, evalInputDelta = 0.0
Right bracket at 5.0E9
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.8363641600000001}, evalInputDelta = 0.0
Right bracket at 1.0E10
F(5.0E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.83636416}, evalInputDelta = 0.0
Right bracket at 5.0E9
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.8363641600000001}, evalInputDelta = 0.0
Right bracket at 1.0E10
F(5.0E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.8363641600000001}, evalInputDelta = 0.0
Right bracket at 5.0E9
F(2.5E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.83636416}, evalInputDelta = 0.0
Right bracket at 2.5E9
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.8363641600000001}, evalInputDelta = 0.0
Right bracket at 1.0E10
F(5.0E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.83636416}, evalInputDelta = 0.0
Right bracket at 5.0E9
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-0.83636416}, evalInputDelta = 0.0
Right bracket at 1.0E10
Converged to right
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.1139; Orientation: 0.0010; Line Search: 0.1099
Iteration 2 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 2
Final threshold in iteration 2: 0.0 (> 0.0) after 0.625s (< 30.000s)
Returns
0.0
Next, we apply the same optimization using L-BFGS, which is nearly ideal for purely second-order or quadratic functions.
TrainingTester.java:509 executed in 0.60 seconds (0.000 gc):
IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
try {
iterativeTrainer.setLineSearchFactory(label -> new ArmijoWolfeSearch());
iterativeTrainer.setOrientation(new LBFGS());
iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
iterativeTrainer.setIterationsPerSample(100);
iterativeTrainer.setMaxIterations(250);
iterativeTrainer.setTerminateThreshold(0);
return iterativeTrainer.run();
} finally {
iterativeTrainer.freeRef();
}
Reset training subject: 357484204654
Reset training subject: 357487421626
Adding measurement 42b9ab4f to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD
Non-optimal measurement 54.726825944839185 < 54.726825944839185. Total: 1
th(0)=54.726825944839185;dx=-5.6014848000000013E23
Adding measurement 1107efb7 to history. Total: 1
New Minimum: 54.726825944839185 > 0.0
Armijo: th(2.154434690031884)=0.0; dx=-5.601484800005569E11 evalInputDelta=54.726825944839185
Non-optimal measurement 0.02590359656412173 < 0.0. Total: 2
Armijo: th(1.077217345015942)=0.02590359656412173; dx=-5.601484800005731E11 evalInputDelta=54.700922348275064
Non-optimal measurement 0.13961221994753872 < 0.0. Total: 2
Armijo: th(0.3590724483386473)=0.13961221994753872; dx=-5.6014848000075E11 evalInputDelta=54.58721372489165
Non-optimal measurement 0.3491080114309031 < 0.0. Total: 2
Armijo: th(0.08976811208466183)=0.3491080114309031; dx=-5.601484800015562E11 evalInputDelta=54.377717933408285
Non-optimal measurement 0.4754795760379441 < 0.0. Total: 2
Armijo: th(0.017953622416932366)=0.4754795760379441; dx=-5.601484800027084E11 evalInputDelta=54.251346368801244
Non-optimal measurement 0.5164347412167083 < 0.0. Total: 2
Armijo: th(0.002992270402822061)=0.5164347412167083; dx=-5.601484800033026E11 evalInputDelta=54.21039120362248
Non-optimal measurement 0.5244456181026621 < 0.0. Total: 2
Armijo: th(4.2746720040315154E-4)=0.5244456181026621; dx=-5.601484800034369E11 evalInputDelta=54.202380326736524
Non-optimal measurement 0.5256432078089327 < 0.0. Total: 2
Armijo: th(5.343340005039394E-5)=0.5256432078089327; dx=-5.601484800034575E11 evalInputDelta=54.20118273703025
Non-optimal measurement 0.5257958364354878 < 0.0. Total: 2
Armijo: th(5.9370444500437714E-6)=0.5257958364354878; dx=-5.601484800034602E11 evalInputDelta=54.2010301084037
Non-optimal measurement 0.5258130150056665 < 0.0. Total: 2
Armijo: th(5.937044450043771E-7)=0.5258130150056665; dx=-5.601484800034604E11 evalInputDelta=54.20101292983352
Non-optimal measurement 0.5258147503031128 < 0.0. Total: 2
Armijo: th(5.397313136403428E-8)=0.5258147503031128; dx=-5.601484800034604E11 evalInputDelta=54.20101119453607
Non-optimal measurement 0.5258149093728564 < 0.0. Total: 2
Armijo: th(4.4977609470028565E-9)=0.5258149093728564; dx=-5.601484800034604E11 evalInputDelta=54.20101103546633
Non-optimal measurement 0.5258149227213726 < 0.0. Total: 2
Armijo: th(3.4598161130791205E-10)=0.5258149227213726; dx=-5.601484800034604E11 evalInputDelta=54.20101102211781
Non-optimal measurement 0.5401243828088803 < 0.0. Total: 2
Armijo: th(2.4712972236279432E-11)=0.5401243828088803; dx=-5.604654753271477E11 evalInputDelta=54.1867015620303
Non-optimal measurement 41.015348072966894 < 0.0. Total: 2
Armijo: th(1.6475314824186289E-12)=41.015348072966894; dx=-4.2322112000056853E23 evalInputDelta=13.71147787187229
Non-optimal measurement 54.72682594483886 < 0.0. Total: 2
Armijo: th(1.029707176511643E-13)=54.72682594483886; dx=-5.6014848000000013E23 evalInputDelta=3.268496584496461E-13
Non-optimal measurement 54.72682594483918 < 0.0. Total: 2
Armijo: th(6.057101038303783E-15)=54.72682594483918; dx=-5.6014848000000013E23 evalInputDelta=7.105427357601002E-15
Non-optimal measurement 0.0 < 0.0. Total: 2
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.0
Fitness changed from 54.726825944839185 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.4455; Orientation: 0.0052; Line Search: 0.4297
Non-optimal measurement 0.0 < 0.0. Total: 2
LBFGS Accumulation History: 2 points
Non-optimal measurement 0.0 < 0.0. Total: 2
th(0)=0.0;dx=-0.8363641600000001
Non-optimal measurement 0.0 < 0.0. Total: 2
Armijo: th(2.154434690031884E-15)=0.0; dx=-0.8363641600000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 2
Armijo: th(1.077217345015942E-15)=0.0; dx=-0.8363641600000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 2
MIN ALPHA (3.5907244833864734E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.1587; Orientation: 0.0018; Line Search: 0.1539
Iteration 2 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 2
Final threshold in iteration 2: 0.0 (> 0.0) after 0.605s (< 30.000s)
Returns
0.0
TrainingTester.java:432 executed in 0.10 seconds (0.000 gc):
return TestUtil.compare(title + " vs Iteration", runs);
Plotting range=[0.0, 0.0], [2.0, 1.0]; valueStats=DoubleSummaryStatistics{count=0, sum=0.000000, min=Infinity, average=0.000000, max=-Infinity}
Only 0 points for GD
Only 0 points for CjGD
Only 0 points for LBFGS
Returns
TrainingTester.java:435 executed in 0.00 seconds (0.000 gc):
return TestUtil.compareTime(title + " vs Time", runs);
No Data
TrainingTester.java:255 executed in 0.00 seconds (0.000 gc):
return grid(inputLearning, modelLearning, completeLearning);
Returns
TrainingTester.java:258 executed in 0.00 seconds (0.000 gc):
return new ComponentResult(null == inputLearning ? null : inputLearning.value,
null == modelLearning ? null : modelLearning.value, null == completeLearning ? null : completeLearning.value);
Returns
{"input":{ "LBFGS": { "type": "Converged", "value": 0.0 }, "CjGD": { "type": "Converged", "value": 0.0 }, "GD": { "type": "Converged", "value": 0.0 } }, "model":null, "complete":null}
LayerTests.java:425 executed in 0.00 seconds (0.000 gc):
throwException(exceptions.addRef());
| details | result |
|---|---|
| {"input":{ "LBFGS": { "type": "Converged", "value": 0.0 }, "CjGD": { "type": "Converged", "value": 0.0 }, "GD": { "type": "Converged", "value": 0.0 } }, "model":null, "complete":null} | OK |
{
"result": "OK",
"performance": {
"execution_time": "2.489",
"gc_time": "0.236"
},
"created_on": 1586734943958,
"file_name": "trainingTest",
"report": {
"simpleName": "Basic",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ImgTileSelectLayerTest.Basic",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/ImgTileSelectLayerTest.java",
"javaDoc": ""
},
"training_analysis": {
"input": {
"LBFGS": {
"type": "Converged",
"value": 0.0
},
"CjGD": {
"type": "Converged",
"value": 0.0
},
"GD": {
"type": "Converged",
"value": 0.0
}
}
},
"archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/ImgTileSelectLayer/Basic/trainingTest/202004124223",
"id": "2b79dce1-29dd-4e59-a218-83939cf8fb07",
"report_type": "Components",
"display_name": "Comparative Training",
"target": {
"simpleName": "ImgTileSelectLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ImgTileSelectLayer",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/ImgTileSelectLayer.java",
"javaDoc": ""
}
}