Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 9222810275790336000
In this apply, we use a network to learn this target input, given it's pre-evaluated output:
TrainingTester.java:332 executed in 0.01 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
[
[ [ 1.556 ], [ 1.048 ], [ -0.712 ], [ -0.068 ], [ 1.032 ], [ 1.764 ] ],
[ [ 1.108 ], [ 1.556 ], [ -1.688 ], [ 1.512 ], [ 0.788 ], [ -0.768 ] ],
[ [ 0.496 ], [ 0.028 ], [ 0.3 ], [ 1.524 ], [ -0.852 ], [ 0.392 ] ],
[ [ 1.208 ], [ -0.804 ], [ -1.616 ], [ 0.7 ], [ 0.092 ], [ -0.384 ] ],
[ [ 1.64 ], [ -1.028 ], [ 0.048 ], [ -0.128 ], [ 1.612 ], [ 1.356 ] ],
[ [ 1.912 ], [ -0.176 ], [ 0.636 ], [ -1.72 ], [ -0.608 ], [ 0.08 ] ]
]
[
[ [ -0.384 ], [ 1.556 ], [ 1.032 ], [ 0.048 ], [ -0.768 ], [ -0.608 ] ],
[ [ -0.068 ], [ 0.08 ], [ 1.048 ], [ 0.092 ], [ -1.688 ], [ 0.7 ] ],
[ [ 1.356 ], [ 1.108 ], [ 0.028 ], [ 1.764 ], [ -1.72 ], [ -1.616 ] ],
[ [ -0.852 ], [ 1.64 ], [ -0.176 ], [ 0.636 ], [ 1.524 ], [ 1.208 ] ],
[ [ -1.028 ], [ 0.3 ], [ 0.392 ], [ 1.556 ], [ 1.912 ], [ 0.496 ] ],
[ [ -0.128 ], [ 1.512 ], [ 1.612 ], [ -0.804 ], [ -0.712 ], [ 0.788 ] ]
]
[
[ [ 1.764 ], [ -0.128 ], [ 1.612 ], [ -1.688 ], [ 0.048 ], [ 0.496 ] ],
[ [ 1.208 ], [ -0.068 ], [ 0.092 ], [ -0.768 ], [ 1.556 ], [ -0.608 ] ],
[ [ -1.028 ], [ 0.636 ], [ 1.524 ], [ -1.72 ], [ 0.788 ], [ -0.712 ] ],
[ [ 1.912 ], [ 0.028 ], [ 1.032 ], [ 1.108 ], [ -0.384 ], [ 1.356 ] ],
[ [ 1.556 ], [ 0.392 ], [ 0.3 ], [ 1.512 ], [ -1.616 ], [ 0.08 ] ],
[ [ -0.176 ], [ -0.804 ], [ 1.048 ], [ -0.852 ], [ 0.7 ], [ 1.64 ] ]
]
[
[ [ 0.092 ], [ -1.688 ], [ -1.028 ], [ -1.616 ], [ 0.3 ], [ 1.556 ] ],
[ [ -0.608 ], [ 1.64 ], [ -0.128 ], [ 0.788 ], [ 1.612 ], [ 1.524 ] ],
[ [ 1.032 ], [ 1.512 ], [ 0.08 ], [ 0.392 ], [ -0.176 ], [ 1.048 ] ],
[ [ 1.356 ], [ 0.496 ], [ -0.068 ], [ 0.028 ], [ 1.556 ], [ 0.7 ] ],
[ [ 0.048 ], [ -0.804 ], [ 1.912 ], [ -0.768 ], [ -1.72 ], [ -0.852 ] ],
[ [ -0.712 ], [ -0.384 ], [ 0.636 ], [ 1.764 ], [ 1.108 ], [ 1.208 ] ]
]
[
[ [ 1.612 ], [ -1.688 ], [ 0.392 ], [ 1.64 ], [ 0.7 ], [ -0.068 ] ],
[ [ 1.912 ], [ 1.764 ], [ 1.356 ], [ 1.032 ], [ 1.556 ], [ 0.636 ] ],
[ [ -1.72 ], [ 1.524 ], [ 0.3 ], [ -0.176 ], [ -0.608 ], [ 0.08 ] ],
[ [ -0.852 ], [ -0.804 ], [ -1.028 ], [ 0.028 ], [ 0.092 ], [ -0.712 ] ],
[ [ 0.496 ], [ 1.108 ], [ 1.556 ], [ 1.208 ], [ -0.768 ], [ 0.048 ] ],
[ [ -1.616 ], [ 1.512 ], [ 1.048 ], [ -0.128 ], [ 0.788 ], [ -0.384 ] ]
]
First, we train using basic gradient descent method apply weak line search conditions.
TrainingTester.java:480 executed in 0.89 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: 4530964285848
BACKPROP_AGG_SIZE = 3
THREADS = 64
SINGLE_THREADED = false
Initialized CoreSettings = {
"backpropAggregationSize" : 3,
"jvmThreads" : 64,
"singleThreaded" : false
}
Reset training subject: 4531009434090
Constructing line search parameters: GD
th(0)=211.45981396800693;dx=-1.82978944E24
New Minimum: 211.45981396800693 > 0.050633502237490725
Armijo: th(2.154434690031884)=0.050633502237490725; dx=-1.8297894400318062E12 evalInputDelta=211.40918046576942
Armijo: th(1.077217345015942)=0.19756861701393885; dx=-1.8297894400318604E12 evalInputDelta=211.262245350993
Armijo: th(0.3590724483386473)=1.0062327388241799; dx=-1.8297894400324438E12 evalInputDelta=210.45358122918276
Armijo: th(0.08976811208466183)=3.1993533399279634; dx=-1.8297894400438945E12 evalInputDelta=208.26046062807896
Armijo: th(0.017953622416932366)=8.110337992197858; dx=-1.8297894401488662E12 evalInputDelta=203.34947597580907
Armijo: th(0.002992270402822061)=11.611627702383657; dx=-1.8297894404271255E12 evalInputDelta=199.84818626562327
Armijo: th(4.2746720040315154E-4)=12.991025547431814; dx=-1.8297894407069985E12 evalInputDelta=198.46878842057512
Armijo: th(5.343340005039394E-5)=13.269693482722825; dx=-1.8297894407915044E12 evalInputDelta=198.1901204852841
Armijo: th(5.9370444500437714E-6)=13.307471067585377; dx=-1.8297894408040059E12 evalInputDelta=198.15234290042156
Armijo: th(5.937044450043771E-7)=13.311758487444877; dx=-1.829789440805442E12 evalInputDelta=198.14805548056205
Armijo: th(5.397313136403428E-8)=13.3121919871714; dx=-1.8297894408055872E12 evalInputDelta=198.14762198083554
Armijo: th(4.4977609470028565E-9)=13.312231728572765; dx=-1.8297894408056006E12 evalInputDelta=198.14758223943417
Armijo: th(3.4598161130791205E-10)=13.320778256186241; dx=-1.829902266686956E12 evalInputDelta=198.1390357118207
Armijo: th(2.4712972236279432E-11)=15.07860626630816; dx=-6.66880001872095E20 evalInputDelta=196.38120770169877
Armijo: th(1.6475314824186289E-12)=145.08096816719367; dx=-1.1254848000094743E24 evalInputDelta=66.37884580081325
Armijo: th(1.029707176511643E-13)=211.45981396792422; dx=-1.82978944E24 evalInputDelta=8.270717444247566E-11
Armijo: th(6.057101038303783E-15)=211.45981396800207; dx=-1.82978944E24 evalInputDelta=4.860112312599085E-12
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.050633502237490725
Fitness changed from 211.45981396800693 to 0.050633502237490725
Iteration 1 complete. Error: 0.050633502237490725 Total: 0.3975; Orientation: 0.0048; Line Search: 0.3271
th(0)=0.050633502237490725;dx=-6.048770830310463
New Minimum: 0.050633502237490725 > 0.05063350223749068
WOLFE (weak): th(2.154434690031884E-15)=0.05063350223749068; dx=-6.048770830310463 evalInputDelta=4.85722573273506E-17
New Minimum: 0.05063350223749068 > 0.050633502237490656
WOLFE (weak): th(4.308869380063768E-15)=0.050633502237490656; dx=-6.048770830310463 evalInputDelta=6.938893903907228E-17
New Minimum: 0.050633502237490656 > 0.050633502237490524
WOLFE (weak): th(1.2926608140191303E-14)=0.050633502237490524; dx=-6.048770830310463 evalInputDelta=2.0122792321330962E-16
New Minimum: 0.050633502237490524 > 0.0506335022374899
WOLFE (weak): th(5.1706432560765214E-14)=0.0506335022374899; dx=-6.048770830310463 evalInputDelta=8.257283745649602E-16
New Minimum: 0.0506335022374899 > 0.05063350223748657
WOLFE (weak): th(2.5853216280382605E-13)=0.05063350223748657; dx=-6.048770830310462 evalInputDelta=4.15639744844043E-15
New Minimum: 0.05063350223748657 > 0.05063350223746581
WOLFE (weak): th(1.5511929768229563E-12)=0.05063350223746581; dx=-6.0487708303104615 evalInputDelta=2.4917568008930857E-14
New Minimum: 0.05063350223746581 > 0.05063350223731633
WOLFE (weak): th(1.0858350837760695E-11)=0.05063350223731633; dx=-6.048770830310449 evalInputDelta=1.7439522048690037E-13
New Minimum: 0.05063350223731633 > 0.05063350223609555
WOLFE (weak): th(8.686680670208556E-11)=0.05063350223609555; dx=-6.048770830310346 evalInputDelta=1.3951756416830108E-12
New Minimum: 0.05063350223609555 > 0.05063350222493416
WOLFE (weak): th(7.8180126031877E-10)=0.05063350222493416; dx=-6.048770830309406 evalInputDelta=1.255656689735929E-11
New Minimum: 0.05063350222493416 > 0.05063350211192506
WOLFE (weak): th(7.818012603187701E-9)=0.05063350211192506; dx=-6.048770830299892 evalInputDelta=1.25565662034699E-10
New Minimum: 0.05063350211192506 > 0.050633500856268575
WOLFE (weak): th(8.599813863506471E-8)=0.050633500856268575; dx=-6.048770830194179 evalInputDelta=1.3812221505427047E-9
New Minimum: 0.050633500856268575 > 0.05063348566282564
WOLFE (weak): th(1.0319776636207765E-6)=0.05063348566282564; dx=-6.048770828915064 evalInputDelta=1.657466508486749E-8
New Minimum: 0.05063348566282564 > 0.05063328676695682
WOLFE (weak): th(1.3415709627070094E-5)=0.05063328676695682; dx=-6.048770812170297 evalInputDelta=2.1547053390830184E-7
New Minimum: 0.05063328676695682 > 0.050630485672161885
WOLFE (weak): th(1.878199347789813E-4)=0.050630485672161885; dx=-6.048770576352049 evalInputDelta=3.0165653288408145E-6
New Minimum: 0.050630485672161885 > 0.05058825876509347
WOLFE (weak): th(0.0028172990216847197)=0.05058825876509347; dx=-6.048767021817962 evalInputDelta=4.5243472397253626E-5
New Minimum: 0.05058825876509347 > 0.049910890941020025
WOLFE (weak): th(0.045076784346955515)=0.049910890941020025; dx=-6.048710120750096 evalInputDelta=7.226112964707002E-4
New Minimum: 0.049910890941020025 > 0.03870581267339743
WOLFE (weak): th(0.7663053338982437)=0.03870581267339743; dx=-6.047800188776264 evalInputDelta=0.011927689564093298
New Minimum: 0.03870581267339743 > 0.0
WOLFE (weak): th(13.793496010168386)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
WOLFE (weak): th(262.07642419319933)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
WOLFE (weak): th(5241.528483863986)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
Armijo: th(110072.09816114372)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
Armijo: th(57656.813322503855)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
Armijo: th(31449.17090318392)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
Armijo: th(18345.349693523953)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
Armijo: th(11793.43908869397)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
Armijo: th(8517.483786278977)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
WOLFE (weak): th(6879.506135071482)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
WOLFE (weak): th(7698.49496067523)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
WOLFE (weak): th(8107.989373477103)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
WOLFE (weak): th(8312.736579878041)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
Armijo: th(8415.110183078508)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
WOLFE (weak): th(8363.923381478275)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
mu ~= nu (8363.923381478275): th(13.793496010168386)=0.0
Fitness changed from 0.050633502237490725 to 0.0
Iteration 2 complete. Error: 0.0 Total: 0.3028; Orientation: 0.0013; Line Search: 0.2931
th(0)=0.0;dx=-6.043728
Armijo: th(18074.665988345234)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(9037.332994172617)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(3012.4443313908723)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(753.1110828477181)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(150.6222165695436)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(25.1037027615906)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(3.5862432516558003)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(0.44828040645697503)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(0.049808934050775)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(0.0049808934050775)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(4.5280849137068185E-4)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(3.773404094755682E-5)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(2.902618534427448E-6)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(2.073298953162463E-7)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(1.3821993021083086E-8)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(8.638745638176929E-10)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(5.081615081280546E-11)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(2.823119489600303E-12)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(1.485852362947528E-13)=0.0; dx=-6.043728 evalInputDelta=0.0
Armijo: th(7.42926181473764E-15)=0.0; dx=-6.043728 evalInputDelta=0.0
MIN ALPHA (3.537743721303638E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.1849; Orientation: 0.0009; Line Search: 0.1784
Iteration 3 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 3
Final threshold in iteration 3: 0.0 (> 0.0) after 0.886s (< 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 0.61 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: 4531859490393
Reset training subject: 4531864043891
Constructing line search parameters: GD
F(0.0) = LineSearchPoint{point=PointSample{avg=211.45981396800693}, derivative=-1.82978944E24}
New Minimum: 211.45981396800693 > 14.08142123086073
F(1.0E-10) = LineSearchPoint{point=PointSample{avg=14.08142123086073}, derivative=-3.1872000182980785E20}, evalInputDelta = -197.37839273714619
New Minimum: 14.08142123086073 > 13.312234779175302
F(7.000000000000001E-10) = LineSearchPoint{point=PointSample{avg=13.312234779175302}, derivative=-1.8297894408056016E12}, evalInputDelta = -198.14757918883163
New Minimum: 13.312234779175302 > 13.312231405469069
F(4.900000000000001E-9) = LineSearchPoint{point=PointSample{avg=13.312231405469069}, derivative=-1.8297894408056006E12}, evalInputDelta = -198.14758256253785
New Minimum: 13.312231405469069 > 13.312207789658483
F(3.430000000000001E-8) = LineSearchPoint{point=PointSample{avg=13.312207789658483}, derivative=-1.8297894408055925E12}, evalInputDelta = -198.14760617834844
New Minimum: 13.312207789658483 > 13.312042485504701
F(2.4010000000000004E-7) = LineSearchPoint{point=PointSample{avg=13.312042485504701}, derivative=-1.829789440805537E12}, evalInputDelta = -198.14777148250224
New Minimum: 13.312042485504701 > 13.310885675780876
F(1.6807000000000003E-6) = LineSearchPoint{point=PointSample{avg=13.310885675780876}, derivative=-1.8297894408051494E12}, evalInputDelta = -198.14892829222606
New Minimum: 13.310885675780876 > 13.302803607551002
F(1.1764900000000001E-5) = LineSearchPoint{point=PointSample{avg=13.302803607551002}, derivative=-1.8297894408024468E12}, evalInputDelta = -198.15701036045593
New Minimum: 13.302803607551002 > 13.246977329779394
F(8.235430000000001E-5) = LineSearchPoint{point=PointSample{avg=13.246977329779394}, derivative=-1.8297894407841147E12}, evalInputDelta = -198.21283663822754
New Minimum: 13.246977329779394 > 12.888148945951745
F(5.764801000000001E-4) = LineSearchPoint{point=PointSample{avg=12.888148945951745}, derivative=-1.8297894406788984E12}, evalInputDelta = -198.57166502205519
New Minimum: 12.888148945951745 > 11.1986514235773
F(0.004035360700000001) = LineSearchPoint{point=PointSample{avg=11.1986514235773}, derivative=-1.829789440372232E12}, evalInputDelta = -200.26116254442962
New Minimum: 11.1986514235773 > 6.847773062122113
F(0.028247524900000005) = LineSearchPoint{point=PointSample{avg=6.847773062122113}, derivative=-1.8297894401062705E12}, evalInputDelta = -204.6120409058848
New Minimum: 6.847773062122113 > 1.6042756439315131
F(0.19773267430000002) = LineSearchPoint{point=PointSample{avg=1.6042756439315131}, derivative=-1.8297894400337861E12}, evalInputDelta = -209.8555383240754
New Minimum: 1.6042756439315131 > 0.11995883108706465
F(1.3841287201) = LineSearchPoint{point=PointSample{avg=0.11995883108706465}, derivative=-1.82978944003183E12}, evalInputDelta = -211.33985513691985
New Minimum: 0.11995883108706465 > 0.0039109479069900045
F(9.688901040700001) = LineSearchPoint{point=PointSample{avg=0.0039109479069900045}, derivative=-1.8297894400317998E12}, evalInputDelta = -211.45590302009992
New Minimum: 0.0039109479069900045 > 0.0
F(67.8223072849) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
F(474.7561509943) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
F(3323.2930569601003) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
F(23263.0513987207) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
F(162841.3597910449) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
F(1139889.5185373144) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
F(7979226.6297612) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
F(5.58545864083284E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
F(3.909821048582988E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317998E12}, evalInputDelta = -211.45981396800693
F(2.7368747340080914E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
F(1.915812313805664E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
0.0 <= 211.45981396800693
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8297894400317996E12}, evalInputDelta = -211.45981396800693
Right bracket at 1.0E10
Converged to right
Fitness changed from 211.45981396800693 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.4025; Orientation: 0.0007; Line Search: 0.3879
F(0.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
0.0 <= 0.0
F(5.0E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 5.0E9
F(2.5E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 2.5E9
F(1.25E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 1.25E9
F(6.25E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 6.25E8
F(3.125E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 3.125E8
F(1.5625E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 1.5625E8
F(7.8125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 7.8125E7
F(3.90625E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 3.90625E7
F(1.953125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 1.953125E7
F(9765625.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 9765625.0
F(4882812.5) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Right bracket at 4882812.5
F(2441406.25) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728}, evalInputDelta = 0.0
Loops = 12
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.2030; Orientation: 0.0008; Line Search: 0.1974
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
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 5.98 seconds (0.091 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: 4532469690336
Reset training subject: 4532474377069
Adding measurement 2fe585f8 to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD
Non-optimal measurement 211.45981396800693 < 211.45981396800693. Total: 1
th(0)=211.45981396800693;dx=-1.82978944E24
Adding measurement 7e422ae6 to history. Total: 1
New Minimum: 211.45981396800693 > 0.050633502237490725
Armijo: th(2.154434690031884)=0.050633502237490725; dx=-1.8297894400318062E12 evalInputDelta=211.40918046576942
Non-optimal measurement 0.19756861701393885 < 0.050633502237490725. Total: 2
Armijo: th(1.077217345015942)=0.19756861701393885; dx=-1.8297894400318604E12 evalInputDelta=211.262245350993
Non-optimal measurement 1.0062327388241799 < 0.050633502237490725. Total: 2
Armijo: th(0.3590724483386473)=1.0062327388241799; dx=-1.8297894400324438E12 evalInputDelta=210.45358122918276
Non-optimal measurement 3.1993533399279634 < 0.050633502237490725. Total: 2
Armijo: th(0.08976811208466183)=3.1993533399279634; dx=-1.8297894400438945E12 evalInputDelta=208.26046062807896
Non-optimal measurement 8.110337992197858 < 0.050633502237490725. Total: 2
Armijo: th(0.017953622416932366)=8.110337992197858; dx=-1.8297894401488662E12 evalInputDelta=203.34947597580907
Non-optimal measurement 11.611627702383657 < 0.050633502237490725. Total: 2
Armijo: th(0.002992270402822061)=11.611627702383657; dx=-1.8297894404271255E12 evalInputDelta=199.84818626562327
Non-optimal measurement 12.991025547431814 < 0.050633502237490725. Total: 2
Armijo: th(4.2746720040315154E-4)=12.991025547431814; dx=-1.8297894407069985E12 evalInputDelta=198.46878842057512
Non-optimal measurement 13.269693482722825 < 0.050633502237490725. Total: 2
Armijo: th(5.343340005039394E-5)=13.269693482722825; dx=-1.8297894407915042E12 evalInputDelta=198.1901204852841
Non-optimal measurement 13.307471067585377 < 0.050633502237490725. Total: 2
Armijo: th(5.9370444500437714E-6)=13.307471067585377; dx=-1.8297894408040059E12 evalInputDelta=198.15234290042156
Non-optimal measurement 13.311758487444877 < 0.050633502237490725. Total: 2
Armijo: th(5.937044450043771E-7)=13.311758487444877; dx=-1.829789440805442E12 evalInputDelta=198.14805548056205
Non-optimal measurement 13.3121919871714 < 0.050633502237490725. Total: 2
Armijo: th(5.397313136403428E-8)=13.3121919871714; dx=-1.8297894408055872E12 evalInputDelta=198.14762198083554
Non-optimal measurement 13.312231728572765 < 0.050633502237490725. Total: 2
Armijo: th(4.4977609470028565E-9)=13.312231728572765; dx=-1.8297894408056006E12 evalInputDelta=198.14758223943417
Non-optimal measurement 13.320778256186241 < 0.050633502237490725. Total: 2
Armijo: th(3.4598161130791205E-10)=13.320778256186241; dx=-1.829902266686956E12 evalInputDelta=198.1390357118207
Non-optimal measurement 15.07860626630816 < 0.050633502237490725. Total: 2
Armijo: th(2.4712972236279432E-11)=15.07860626630816; dx=-6.66880001872095E20 evalInputDelta=196.38120770169877
Non-optimal measurement 145.08096816719367 < 0.050633502237490725. Total: 2
Armijo: th(1.6475314824186289E-12)=145.08096816719367; dx=-1.1254848000094743E24 evalInputDelta=66.37884580081325
Non-optimal measurement 211.45981396792422 < 0.050633502237490725. Total: 2
Armijo: th(1.029707176511643E-13)=211.45981396792422; dx=-1.82978944E24 evalInputDelta=8.270717444247566E-11
Non-optimal measurement 211.45981396800207 < 0.050633502237490725. Total: 2
Armijo: th(6.057101038303783E-15)=211.45981396800207; dx=-1.82978944E24 evalInputDelta=4.860112312599085E-12
Non-optimal measurement 0.050633502237490725 < 0.050633502237490725. Total: 2
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.050633502237490725
Fitness changed from 211.45981396800693 to 0.050633502237490725
Iteration 1 complete. Error: 0.050633502237490725 Total: 0.1968; Orientation: 0.0039; Line Search: 0.1792
Non-optimal measurement 0.050633502237490725 < 0.050633502237490725. Total: 2
LBFGS Accumulation History: 2 points
Non-optimal measurement 0.050633502237490725 < 0.050633502237490725. Total: 2
th(0)=0.050633502237490725;dx=-6.048770830310463
Adding measurement 719f3bfa to history. Total: 2
New Minimum: 0.050633502237490725 > 0.05063350223749068
WOLFE (weak): th(2.154434690031884E-15)=0.05063350223749068; dx=-6.048770830310463 evalInputDelta=4.85722573273506E-17
Adding measurement 98cc5e8 to history. Total: 3
New Minimum: 0.05063350223749068 > 0.050633502237490656
WOLFE (weak): th(4.308869380063768E-15)=0.050633502237490656; dx=-6.048770830310463 evalInputDelta=6.938893903907228E-17
Adding measurement 162c16d2 to history. Total: 4
New Minimum: 0.050633502237490656 > 0.050633502237490524
WOLFE (weak): th(1.2926608140191303E-14)=0.050633502237490524; dx=-6.048770830310463 evalInputDelta=2.0122792321330962E-16
Adding measurement 382e0bc1 to history. Total: 5
New Minimum: 0.050633502237490524 > 0.0506335022374899
WOLFE (weak): th(5.1706432560765214E-14)=0.0506335022374899; dx=-6.048770830310463 evalInputDelta=8.257283745649602E-16
Adding measurement 469345ff to history. Total: 6
New Minimum: 0.0506335022374899 > 0.05063350223748657
WOLFE (weak): th(2.5853216280382605E-13)=0.05063350223748657; dx=-6.048770830310462 evalInputDelta=4.15639744844043E-15
Adding measurement 5668cd5e to history. Total: 7
New Minimum: 0.05063350223748657 > 0.05063350223746581
WOLFE (weak): th(1.5511929768229563E-12)=0.05063350223746581; dx=-6.0487708303104615 evalInputDelta=2.4917568008930857E-14
Adding measurement 347dd660 to history. Total: 8
New Minimum: 0.05063350223746581 > 0.05063350223731633
WOLFE (weak): th(1.0858350837760695E-11)=0.05063350223731633; dx=-6.048770830310449 evalInputDelta=1.7439522048690037E-13
Adding measurement 503a25bf to history. Total: 9
New Minimum: 0.05063350223731633 > 0.05063350223609555
WOLFE (weak): th(8.686680670208556E-11)=0.05063350223609555; dx=-6.048770830310346 evalInputDelta=1.3951756416830108E-12
Adding measurement 7cc282d5 to history. Total: 10
New Minimum: 0.05063350223609555 > 0.05063350222493416
WOLFE (weak): th(7.8180126031877E-10)=0.05063350222493416; dx=-6.048770830309406 evalInputDelta=1.255656689735929E-11
Adding measurement 1a40c68e to history. Total: 11
New Minimum: 0.05063350222493416 > 0.05063350211192506
WOLFE (weak): th(7.818012603187701E-9)=0.05063350211192506; dx=-6.048770830299892 evalInputDelta=1.25565662034699E-10
Adding measurement 783d3400 to history. Total: 12
New Minimum: 0.05063350211192506 > 0.050633500856268575
WOLFE (weak): th(8.599813863506471E-8)=0.050633500856268575; dx=-6.048770830194179 evalInputDelta=1.3812221505427047E-9
Adding measurement 46809ea to history. Total: 13
New Minimum: 0.050633500856268575 > 0.05063348566282564
WOLFE (weak): th(1.0319776636207765E-6)=0.05063348566282564; dx=-6.048770828915064 evalInputDelta=1.657466508486749E-8
Adding measurement 1d66556a to history. Total: 14
New Minimum: 0.05063348566282564 > 0.05063328676695682
WOLFE (weak): th(1.3415709627070094E-5)=0.05063328676695682; dx=-6.048770812170297 evalInputDelta=2.1547053390830184E-7
Adding measurement 3ac28fd5 to history. Total: 15
New Minimum: 0.05063328676695682 > 0.050630485672161885
WOLFE (weak): th(1.878199347789813E-4)=0.050630485672161885; dx=-6.048770576352049 evalInputDelta=3.0165653288408145E-6
Adding measurement 604e2 to history. Total: 16
New Minimum: 0.050630485672161885 > 0.05058825876509347
WOLFE (weak): th(0.0028172990216847197)=0.05058825876509347; dx=-6.048767021817962 evalInputDelta=4.5243472397253626E-5
Adding measurement 37d7467d to history. Total: 17
New Minimum: 0.05058825876509347 > 0.049910890941020025
WOLFE (weak): th(0.045076784346955515)=0.049910890941020025; dx=-6.048710120750096 evalInputDelta=7.226112964707002E-4
Adding measurement 41b0cf82 to history. Total: 18
New Minimum: 0.049910890941020025 > 0.03870581267339743
WOLFE (weak): th(0.7663053338982437)=0.03870581267339743; dx=-6.047800188776264 evalInputDelta=0.011927689564093298
Adding measurement 41cefca0 to history. Total: 19
New Minimum: 0.03870581267339743 > 0.0
WOLFE (weak): th(13.793496010168386)=0.0; dx=-6.045760970994195 evalInputDelta=0.050633502237490725
Non-optimal measurement 0.0 < 0.0. Total: 20
WOLFE (weak): th(262.076424193
...skipping 8652 bytes...
30485672161885, 0.05063328676695682, 0.05063348566282564, 0.050633500856268575, 0.05063350211192506, 0.05063350222493416, 0.05063350223609555, 0.05063350223731633
Rejected: LBFGS Orientation magnitude: 1.714e+04, gradient 2.458e+00, dot -0.987; [2a2c80aa-1492-4172-919a-f92befb8dd4a = 1.000/1.000e+00, 2fb3deb8-97e5-4e1f-8465-d0d9abf3fa1a = 1.000/1.000e+00, 2de5c482-a8ab-4716-800a-73a6a97e98e3 = 1.000/1.000e+00, 72efb82b-429a-49b2-9da2-b0f3357623ab = 1.000/1.000e+00, 4b79cf9b-76a1-4fec-9ba3-eab3863dbe4a = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.03870581267339743, 0.049910890941020025, 0.05058825876509347, 0.050630485672161885, 0.05063328676695682, 0.05063348566282564, 0.050633500856268575, 0.05063350211192506, 0.05063350222493416, 0.05063350223609555
Rejected: LBFGS Orientation magnitude: 1.714e+04, gradient 2.458e+00, dot -0.987; [4b79cf9b-76a1-4fec-9ba3-eab3863dbe4a = 1.000/1.000e+00, 72efb82b-429a-49b2-9da2-b0f3357623ab = 1.000/1.000e+00, 2de5c482-a8ab-4716-800a-73a6a97e98e3 = 1.000/1.000e+00, 2fb3deb8-97e5-4e1f-8465-d0d9abf3fa1a = 1.000/1.000e+00, 2a2c80aa-1492-4172-919a-f92befb8dd4a = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.03870581267339743, 0.049910890941020025, 0.05058825876509347, 0.050630485672161885, 0.05063328676695682, 0.05063348566282564, 0.050633500856268575, 0.05063350211192506, 0.05063350222493416
Rejected: LBFGS Orientation magnitude: 1.714e+04, gradient 2.458e+00, dot -0.987; [4b79cf9b-76a1-4fec-9ba3-eab3863dbe4a = 1.000/1.000e+00, 2a2c80aa-1492-4172-919a-f92befb8dd4a = 1.000/1.000e+00, 2fb3deb8-97e5-4e1f-8465-d0d9abf3fa1a = 1.000/1.000e+00, 72efb82b-429a-49b2-9da2-b0f3357623ab = 1.000/1.000e+00, 2de5c482-a8ab-4716-800a-73a6a97e98e3 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.03870581267339743, 0.049910890941020025, 0.05058825876509347, 0.050630485672161885, 0.05063328676695682, 0.05063348566282564, 0.050633500856268575, 0.05063350211192506
Rejected: LBFGS Orientation magnitude: 1.714e+04, gradient 2.458e+00, dot -0.987; [4b79cf9b-76a1-4fec-9ba3-eab3863dbe4a = 1.000/1.000e+00, 2de5c482-a8ab-4716-800a-73a6a97e98e3 = 1.000/1.000e+00, 2a2c80aa-1492-4172-919a-f92befb8dd4a = 1.000/1.000e+00, 72efb82b-429a-49b2-9da2-b0f3357623ab = 1.000/1.000e+00, 2fb3deb8-97e5-4e1f-8465-d0d9abf3fa1a = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.03870581267339743, 0.049910890941020025, 0.05058825876509347, 0.050630485672161885, 0.05063328676695682, 0.05063348566282564, 0.050633500856268575
Rejected: LBFGS Orientation magnitude: 1.714e+04, gradient 2.458e+00, dot -0.987; [72efb82b-429a-49b2-9da2-b0f3357623ab = 1.000/1.000e+00, 2de5c482-a8ab-4716-800a-73a6a97e98e3 = 1.000/1.000e+00, 4b79cf9b-76a1-4fec-9ba3-eab3863dbe4a = 1.000/1.000e+00, 2fb3deb8-97e5-4e1f-8465-d0d9abf3fa1a = 1.000/1.000e+00, 2a2c80aa-1492-4172-919a-f92befb8dd4a = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.03870581267339743, 0.049910890941020025, 0.05058825876509347, 0.050630485672161885, 0.05063328676695682, 0.05063348566282564
Rejected: LBFGS Orientation magnitude: 2.073e+04, gradient 2.458e+00, dot -0.976; [2fb3deb8-97e5-4e1f-8465-d0d9abf3fa1a = 1.000/1.000e+00, 72efb82b-429a-49b2-9da2-b0f3357623ab = 1.000/1.000e+00, 4b79cf9b-76a1-4fec-9ba3-eab3863dbe4a = 1.000/1.000e+00, 2a2c80aa-1492-4172-919a-f92befb8dd4a = 1.000/1.000e+00, 2de5c482-a8ab-4716-800a-73a6a97e98e3 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.03870581267339743, 0.049910890941020025, 0.05058825876509347, 0.050630485672161885, 0.05063328676695682
Rejected: LBFGS Orientation magnitude: 2.207e+04, gradient 2.458e+00, dot -1.000; [4b79cf9b-76a1-4fec-9ba3-eab3863dbe4a = 1.000/1.000e+00, 2fb3deb8-97e5-4e1f-8465-d0d9abf3fa1a = 1.000/1.000e+00, 2a2c80aa-1492-4172-919a-f92befb8dd4a = 1.000/1.000e+00, 72efb82b-429a-49b2-9da2-b0f3357623ab = 1.000/1.000e+00, 2de5c482-a8ab-4716-800a-73a6a97e98e3 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.03870581267339743, 0.049910890941020025, 0.05058825876509347, 0.050630485672161885
Rejected: LBFGS Orientation magnitude: 2.208e+04, gradient 2.458e+00, dot -1.000; [2fb3deb8-97e5-4e1f-8465-d0d9abf3fa1a = 1.000/1.000e+00, 4b79cf9b-76a1-4fec-9ba3-eab3863dbe4a = 1.000/1.000e+00, 2a2c80aa-1492-4172-919a-f92befb8dd4a = 1.000/1.000e+00, 72efb82b-429a-49b2-9da2-b0f3357623ab = 1.000/1.000e+00, 2de5c482-a8ab-4716-800a-73a6a97e98e3 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.03870581267339743, 0.049910890941020025, 0.05058825876509347
LBFGS Accumulation History: 3 points
Removed measurement 41cefca0 to history. Total: 19
Removed measurement 41b0cf82 to history. Total: 18
Removed measurement 37d7467d to history. Total: 17
Removed measurement 604e2 to history. Total: 16
Removed measurement 3ac28fd5 to history. Total: 15
Removed measurement 1d66556a to history. Total: 14
Removed measurement 46809ea to history. Total: 13
Removed measurement 783d3400 to history. Total: 12
Removed measurement 1a40c68e to history. Total: 11
Removed measurement 7cc282d5 to history. Total: 10
Removed measurement 503a25bf to history. Total: 9
Removed measurement 347dd660 to history. Total: 8
Removed measurement 5668cd5e to history. Total: 7
Removed measurement 469345ff to history. Total: 6
Removed measurement 382e0bc1 to history. Total: 5
Removed measurement 162c16d2 to history. Total: 4
Removed measurement 98cc5e8 to history. Total: 3
Adding measurement 2f7aacb6 to history. Total: 3
th(0)=0.0;dx=-6.043728
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(18074.665988345234)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(9037.332994172617)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3012.4443313908723)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(753.1110828477181)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(150.6222165695436)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(25.1037027615906)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3.5862432516558003)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.44828040645697503)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.049808934050775)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.0049808934050775)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(4.5280849137068185E-4)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3.773404094755682E-5)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.902618534427448E-6)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.073298953162463E-7)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.3821993021083086E-8)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(8.638745638176929E-10)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(5.081615081280546E-11)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.823119489600303E-12)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.485852362947528E-13)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(7.42926181473764E-15)=0.0; dx=-6.043728 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
MIN ALPHA (3.537743721303638E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 5.1969; Orientation: 4.9651; Line Search: 0.2271
Iteration 3 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 3
Final threshold in iteration 3: 0.0 (> 0.0) after 5.983s (< 30.000s)
Returns
0.0
TrainingTester.java:432 executed in 0.11 seconds (0.000 gc):
return TestUtil.compare(title + " vs Iteration", runs);
Plotting range=[1.0, -2.2955620321270307], [2.0, -0.2955620321270307]; valueStats=DoubleSummaryStatistics{count=2, sum=0.101267, min=0.050634, average=0.050634, max=0.050634}
Plotting 2 points for GD
Only 1 points for CjGD
Plotting 2 points for LBFGS
Returns
TrainingTester.java:435 executed in 0.01 seconds (0.000 gc):
return TestUtil.compareTime(title + " vs Time", runs);
Plotting range=[0.0, -2.2955620321270307], [0.589, -0.2955620321270307]; valueStats=DoubleSummaryStatistics{count=2, sum=0.101267, min=0.050634, average=0.050634, max=0.050634}
Plotting 2 points for GD
Only 1 points for CjGD
Plotting 2 points for LBFGS
Returns
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": "8.182",
"gc_time": "0.362"
},
"created_on": 1586739118761,
"file_name": "trainingTest",
"report": {
"simpleName": "Basic",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ImgTileSubnetLayerTest.Basic",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/ImgTileSubnetLayerTest.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/ImgTileSubnetLayer/Basic/trainingTest/202004135158",
"id": "fec98b59-6ce4-4d92-9d8d-dafd4b5b30bc",
"report_type": "Components",
"display_name": "Comparative Training",
"target": {
"simpleName": "ImgTileSubnetLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ImgTileSubnetLayer",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/ImgTileSubnetLayer.java",
"javaDoc": ""
}
}