Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase
Using Seed 5395277204571150336
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
[
[ [ -0.068 ], [ -1.572 ], [ 0.392 ], [ 1.704 ], [ -1.492 ], [ 1.048 ], [ 1.612 ], [ 1.512 ] ],
[ [ 1.524 ], [ 1.368 ], [ 1.912 ], [ -0.032 ], [ 0.048 ], [ 1.876 ], [ -0.804 ], [ 1.552 ] ],
[ [ -1.228 ], [ -1.424 ], [ 1.556 ], [ 0.3 ], [ -1.476 ], [ 1.556 ], [ -0.408 ], [ -0.876 ] ],
[ [ 0.092 ], [ -1.54 ], [ -0.176 ], [ 1.652 ], [ -0.804 ], [ -0.608 ], [ 0.996 ], [ 0.08 ] ],
[ [ -1.856 ], [ 1.764 ], [ -0.012 ], [ -0.852 ], [ 1.64 ], [ -0.636 ], [ -0.556 ], [ -0.384 ] ],
[ [ -1.832 ], [ -1.688 ], [ -1.516 ], [ -0.128 ], [ -0.768 ], [ -1.616 ], [ 1.356 ], [ -0.384 ] ],
[ [ 0.636 ], [ 1.108 ], [ 0.028 ], [ 1.208 ], [ 0.788 ], [ 0.496 ], [ 0.048 ], [ -1.72 ] ],
[ [ 1.032 ], [ -0.712 ], [ 0.7 ], [ -0.892 ], [ -1.028 ], [ 0.148 ], [ -0.464 ], [ 1.62 ] ]
]
[
[ [ -0.712 ], [ 0.7 ], [ -0.176 ], [ -0.892 ], [ 1.876 ], [ 1.652 ], [ -1.516 ], [ 1.048 ] ],
[ [ -1.688 ], [ 1.552 ], [ -1.616 ], [ 1.612 ], [ 0.048 ], [ -0.608 ], [ -1.72 ], [ 0.148 ] ],
[ [ -0.556 ], [ -1.856 ], [ 0.496 ], [ -0.804 ], [ -0.012 ], [ -0.876 ], [ -0.768 ], [ 0.048 ] ],
[ [ 1.62 ], [ 1.356 ], [ -1.424 ], [ -0.804 ], [ 1.108 ], [ -1.54 ], [ 1.512 ], [ 0.996 ] ],
[ [ -0.384 ], [ -0.128 ], [ -1.028 ], [ -0.636 ], [ 1.704 ], [ 0.788 ], [ 1.556 ], [ 0.636 ] ],
[ [ -0.852 ], [ 0.3 ], [ 0.028 ], [ 1.524 ], [ -0.068 ], [ 1.912 ], [ 0.092 ], [ -1.832 ] ],
[ [ -0.464 ], [ -1.476 ], [ 0.08 ], [ 1.64 ], [ 1.208 ], [ 1.032 ], [ -1.492 ], [ 1.368 ] ],
[ [ 1.764 ], [ -0.384 ], [ 1.556 ], [ -1.228 ], [ 0.392 ], [ -0.032 ], [ -1.572 ], [ -0.408 ] ]
]
[
[ [ 1.048 ], [ 1.62 ], [ 0.996 ], [ 1.876 ], [ -0.608 ], [ -0.636 ], [ -1.832 ], [ 0.148 ] ],
[ [ -0.408 ], [ -1.492 ], [ -0.384 ], [ -1.028 ], [ -0.464 ], [ 1.556 ], [ 1.208 ], [ -1.476 ] ],
[ [ -1.856 ], [ -0.892 ], [ 1.652 ], [ 1.912 ], [ 0.048 ], [ -0.852 ], [ -0.556 ], [ 1.108 ] ],
[ [ -0.804 ], [ -0.032 ], [ -1.424 ], [ 0.3 ], [ 1.764 ], [ -0.384 ], [ -0.768 ], [ -1.572 ] ],
[ [ 0.092 ], [ -0.876 ], [ -1.72 ], [ 0.496 ], [ 0.636 ], [ 1.704 ], [ -1.54 ], [ -0.128 ] ],
[ [ 0.048 ], [ 1.552 ], [ 1.368 ], [ 1.64 ], [ -0.068 ], [ -0.804 ], [ -1.228 ], [ -0.012 ] ],
[ [ -0.712 ], [ 1.524 ], [ -0.176 ], [ 0.08 ], [ 1.356 ], [ -1.516 ], [ 0.392 ], [ 1.512 ] ],
[ [ 0.028 ], [ -1.616 ], [ 1.612 ], [ -1.688 ], [ 1.556 ], [ 0.7 ], [ 0.788 ], [ 1.032 ] ]
]
[
[ [ 0.048 ], [ -0.128 ], [ -0.892 ], [ -1.492 ], [ -0.636 ], [ -1.54 ], [ -0.804 ], [ 1.64 ] ],
[ [ 1.032 ], [ 1.556 ], [ -0.852 ], [ -0.032 ], [ -1.424 ], [ 0.996 ], [ 1.108 ], [ 0.392 ] ],
[ [ 1.912 ], [ 0.08 ], [ 0.148 ], [ 0.048 ], [ 1.356 ], [ 0.7 ], [ -1.572 ], [ -1.228 ] ],
[ [ -0.012 ], [ 1.556 ], [ 1.876 ], [ 1.652 ], [ -1.028 ], [ -0.384 ], [ 1.62 ], [ 1.704 ] ],
[ [ -0.804 ], [ -0.608 ], [ -1.72 ], [ -0.464 ], [ -1.832 ], [ 0.3 ], [ 0.788 ], [ 1.048 ] ],
[ [ -0.556 ], [ 0.028 ], [ 0.092 ], [ 0.636 ], [ 1.368 ], [ -0.876 ], [ 1.208 ], [ -0.712 ] ],
[ [ -1.856 ], [ 1.612 ], [ -1.516 ], [ -0.176 ], [ -0.768 ], [ 1.512 ], [ -1.476 ], [ 1.552 ] ],
[ [ -0.408 ], [ -1.688 ], [ 1.524 ], [ -0.068 ], [ -0.384 ], [ -1.616 ], [ 1.764 ], [ 0.496 ] ]
]
[
[ [ 1.764 ], [ 1.048 ], [ 1.612 ], [ 0.7 ], [ 1.876 ], [ 0.788 ], [ -0.556 ], [ 0.08 ] ],
[ [ 0.028 ], [ -0.128 ], [ 1.704 ], [ 1.356 ], [ 1.512 ], [ 1.208 ], [ 1.652 ], [ -1.424 ] ],
[ [ -0.012 ], [ -1.028 ], [ -1.516 ], [ 1.368 ], [ 0.048 ], [ -1.832 ], [ -0.768 ], [ -0.852 ] ],
[ [ -0.384 ], [ -1.572 ], [ -1.72 ], [ 0.496 ], [ -0.032 ], [ -1.228 ], [ 0.048 ], [ -0.804 ] ],
[ [ 1.524 ], [ 1.552 ], [ 0.636 ], [ 0.148 ], [ 1.912 ], [ -0.804 ], [ -1.616 ], [ 1.64 ] ],
[ [ -1.476 ], [ 0.3 ], [ -0.636 ], [ -1.856 ], [ -0.384 ], [ 0.996 ], [ -0.876 ], [ -0.408 ] ],
[ [ 1.032 ], [ 1.556 ], [ -0.608 ], [ -1.492 ], [ -1.54 ], [ 1.62 ], [ 0.392 ], [ -0.892 ] ],
[ [ 1.556 ], [ -0.068 ], [ 1.108 ], [ -0.712 ], [ -0.176 ], [ 0.092 ], [ -0.464 ], [ -1.688 ] ]
]
First, we train using basic gradient descent method apply weak line search conditions.
TrainingTester.java:480 executed in 1.22 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: 387327038534
BACKPROP_AGG_SIZE = 3
THREADS = 64
SINGLE_THREADED = false
Initialized CoreSettings = {
"backpropAggregationSize" : 3,
"jvmThreads" : 64,
"singleThreaded" : false
}
Reset training subject: 387358537115
Constructing line search parameters: GD
th(0)=435.02834880675283;dx=-4.12644224E24
New Minimum: 435.02834880675283 > 0.07158472718267048
Armijo: th(2.154434690031884)=0.07158472718267048; dx=-4.126442240028377E12 evalInputDelta=434.9567640795702
Armijo: th(1.077217345015942)=0.17256695109287423; dx=-4.1264422400284097E12 evalInputDelta=434.85578185566
Armijo: th(0.3590724483386473)=1.1760825533249735; dx=-4.126442240029433E12 evalInputDelta=433.85226625342784
Armijo: th(0.08976811208466183)=4.980921371923598; dx=-4.126442240047341E12 evalInputDelta=430.0474274348292
Armijo: th(0.017953622416932366)=10.065580171824843; dx=-4.1264422401372666E12 evalInputDelta=424.962768634928
Armijo: th(0.002992270402822061)=12.980065372544754; dx=-4.126442240316599E12 evalInputDelta=422.0482834342081
Armijo: th(4.2746720040315154E-4)=13.944440743808565; dx=-4.126442240466201E12 evalInputDelta=421.08390806294426
Armijo: th(5.343340005039394E-5)=14.125426193367417; dx=-4.12644224050831E12 evalInputDelta=420.9029226133854
Armijo: th(5.9370444500437714E-6)=14.149593596793938; dx=-4.126442240514449E12 evalInputDelta=420.8787552099589
Armijo: th(5.937044450043771E-7)=14.152330802646741; dx=-4.1264422405151533E12 evalInputDelta=420.8760180041061
Armijo: th(5.397313136403428E-8)=14.152607497344622; dx=-4.1264422405152246E12 evalInputDelta=420.8757413094082
Armijo: th(4.4977609470028565E-9)=14.152632862949122; dx=-4.1264422405152305E12 evalInputDelta=420.8757159438037
Armijo: th(3.4598161130791205E-10)=14.152634991546014; dx=-4.1264422405152314E12 evalInputDelta=420.87571381520684
Armijo: th(2.4712972236279432E-11)=18.088462017215775; dx=-2.218880004174607E21 evalInputDelta=416.93988678953707
Armijo: th(1.6475314824186289E-12)=358.8668205245191; dx=-3.2684684800034535E24 evalInputDelta=76.16152828223375
Armijo: th(1.029707176511643E-13)=426.8959166928838; dx=-4.0102976000050295E24 evalInputDelta=8.132432113869015
Armijo: th(6.057101038303783E-15)=435.0283488067497; dx=-4.12644224E24 evalInputDelta=3.126388037344441E-12
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.07158472718267048
Fitness changed from 435.02834880675283 to 0.07158472718267048
Iteration 1 complete. Error: 0.07158472718267048 Total: 0.6675; Orientation: 0.0036; Line Search: 0.6211
th(0)=0.07158472718267048;dx=-9.466287267310523
New Minimum: 0.07158472718267048 > 0.07158472718267042
WOLFE (weak): th(2.154434690031884E-15)=0.07158472718267042; dx=-9.466287267310523 evalInputDelta=5.551115123125783E-17
New Minimum: 0.07158472718267042 > 0.0715847271826704
WOLFE (weak): th(4.308869380063768E-15)=0.0715847271826704; dx=-9.466287267310523 evalInputDelta=8.326672684688674E-17
New Minimum: 0.0715847271826704 > 0.0715847271826702
WOLFE (weak): th(1.2926608140191303E-14)=0.0715847271826702; dx=-9.466287267310523 evalInputDelta=2.7755575615628914E-16
New Minimum: 0.0715847271826702 > 0.07158472718266945
WOLFE (weak): th(5.1706432560765214E-14)=0.07158472718266945; dx=-9.466287267310523 evalInputDelta=1.0269562977782698E-15
New Minimum: 0.07158472718266945 > 0.07158472718266543
WOLFE (weak): th(2.5853216280382605E-13)=0.07158472718266543; dx=-9.466287267310523 evalInputDelta=5.051514762044462E-15
New Minimum: 0.07158472718266543 > 0.07158472718264024
WOLFE (weak): th(1.5511929768229563E-12)=0.07158472718264024; dx=-9.466287267310522 evalInputDelta=3.02396996332277E-14
New Minimum: 0.07158472718264024 > 0.0715847271824589
WOLFE (weak): th(1.0858350837760695E-11)=0.0715847271824589; dx=-9.466287267310504 evalInputDelta=2.115807529179392E-13
New Minimum: 0.0715847271824589 > 0.071584727180978
WOLFE (weak): th(8.686680670208556E-11)=0.071584727180978; dx=-9.466287267310362 evalInputDelta=1.6924794898898199E-12
New Minimum: 0.071584727180978 > 0.07158472716743829
WOLFE (weak): th(7.8180126031877E-10)=0.07158472716743829; dx=-9.466287267309056 evalInputDelta=1.523219050891811E-11
New Minimum: 0.07158472716743829 > 0.07158472703034877
WOLFE (weak): th(7.818012603187701E-9)=0.07158472703034877; dx=-9.466287267295849 evalInputDelta=1.5232171080015178E-10
New Minimum: 0.07158472703034877 > 0.07158472550713199
WOLFE (weak): th(8.599813863506471E-8)=0.07158472550713199; dx=-9.4662872671491 evalInputDelta=1.6755384857347622E-9
New Minimum: 0.07158472550713199 > 0.07158470707620967
WOLFE (weak): th(1.0319776636207765E-6)=0.07158470707620967; dx=-9.46628726537344 evalInputDelta=2.0106460801860848E-8
New Minimum: 0.07158470707620967 > 0.07158446579883604
WOLFE (weak): th(1.3415709627070094E-5)=0.07158446579883604; dx=-9.466287242128468 evalInputDelta=2.6138383443785607E-7
New Minimum: 0.07158446579883604 > 0.0715810678397312
WOLFE (weak): th(1.878199347789813E-4)=0.0715810678397312; dx=-9.466286914767952 evalInputDelta=3.659342939277277E-6
New Minimum: 0.0715810678397312 > 0.07152984398982946
WOLFE (weak): th(0.0028172990216847197)=0.07152984398982946; dx=-9.466281980578508 evalInputDelta=5.488319284101262E-5
New Minimum: 0.07152984398982946 > 0.07070837816755945
WOLFE (weak): th(0.045076784346955515)=0.07070837816755945; dx=-9.466203039607331 evalInputDelta=8.76349015111022E-4
New Minimum: 0.07070837816755945 > 0.057178707905812455
WOLFE (weak): th(0.7663053338982437)=0.057178707905812455; dx=-9.464952188527052 evalInputDelta=0.014406019276858022
New Minimum: 0.057178707905812455 > 0.0027946756375692924
WOLFE (weak): th(13.793496010168386)=0.0027946756375692924; dx=-9.461534135689032 evalInputDelta=0.06879005154510118
New Minimum: 0.0027946756375692924 > 0.0
WOLFE (weak): th(262.07642419319933)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
WOLFE (weak): th(5241.528483863986)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
Armijo: th(110072.09816114372)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
Armijo: th(57656.813322503855)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
Armijo: th(31449.17090318392)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
Armijo: th(18345.349693523953)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
Armijo: th(11793.43908869397)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
Armijo: th(8517.483786278977)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
WOLFE (weak): th(6879.506135071482)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
Armijo: th(7698.49496067523)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
WOLFE (weak): th(7289.0005478733565)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
WOLFE (weak): th(7493.747754274293)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
Armijo: th(7596.121357474762)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
WOLFE (weak): th(7544.934555874527)=0.0; dx=-9.461476685157127 evalInputDelta=0.07158472718267048
mu ~= nu (7544.934555874527): th(262.07642419319933)=0.0
Fitness changed from 0.07158472718267048 to 0.0
Iteration 2 complete. Error: 0.0 Total: 0.3314; Orientation: 0.0017; Line Search: 0.3245
th(0)=0.0;dx=-9.458297600000002
Armijo: th(16310.208051716048)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(8155.104025858024)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(2718.3680086193413)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(679.5920021548353)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(135.91840043096707)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(22.653066738494513)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(3.2361523912135017)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(0.4045190489016877)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(0.044946560989076415)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(0.004494656098907641)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(4.086050999006947E-4)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(3.405042499172456E-5)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(2.619263460901889E-6)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(1.870902472072778E-7)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(1.2472683147151853E-8)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(7.795426966969908E-10)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(4.585545274688181E-11)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(2.547525152604545E-12)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(1.340802711897129E-13)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Armijo: th(6.7040135594856445E-15)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
MIN ALPHA (3.1923874092788784E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.2129; Orientation: 0.0011; Line Search: 0.2093
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 1.213s (< 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 0.26 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: 388545581167
Reset training subject: 388547446373
Constructing line search parameters: GD
F(0.0) = LineSearchPoint{point=PointSample{avg=435.02834880675283}, derivative=-4.12644224E24}
New Minimum: 435.02834880675283 > 15.284426475792149
F(1.0E-10) = LineSearchPoint{point=PointSample{avg=15.284426475792149}, derivative=-3.6864000412905164E20}, evalInputDelta = -419.7439223309607
New Minimum: 15.284426475792149 > 14.152634810042432
F(7.000000000000001E-10) = LineSearchPoint{point=PointSample{avg=14.152634810042432}, derivative=-4.1264422405152314E12}, evalInputDelta = -420.8757139967104
New Minimum: 14.152634810042432 > 14.152632656723252
F(4.900000000000001E-9) = LineSearchPoint{point=PointSample{avg=14.152632656723252}, derivative=-4.1264422405152305E12}, evalInputDelta = -420.8757161500296
New Minimum: 14.152632656723252 > 14.152617583554195
F(3.430000000000001E-8) = LineSearchPoint{point=PointSample{avg=14.152617583554195}, derivative=-4.1264422405152266E12}, evalInputDelta = -420.8757312231986
New Minimum: 14.152617583554195 > 14.152512074565555
F(2.4010000000000004E-7) = LineSearchPoint{point=PointSample{avg=14.152512074565555}, derivative=-4.1264422405151997E12}, evalInputDelta = -420.8758367321873
New Minimum: 14.152512074565555 > 14.151773668125582
F(1.6807000000000003E-6) = LineSearchPoint{point=PointSample{avg=14.151773668125582}, derivative=-4.12644224051501E12}, evalInputDelta = -420.87657513862723
New Minimum: 14.151773668125582 > 14.146612469136011
F(1.1764900000000001E-5) = LineSearchPoint{point=PointSample{avg=14.146612469136011}, derivative=-4.126442240513685E12}, evalInputDelta = -420.8817363376168
New Minimum: 14.146612469136011 > 14.110851553279485
F(8.235430000000001E-5) = LineSearchPoint{point=PointSample{avg=14.110851553279485}, derivative=-4.126442240504671E12}, evalInputDelta = -420.91749725347336
New Minimum: 14.110851553279485 > 13.876426179075533
F(5.764801000000001E-4) = LineSearchPoint{point=PointSample{avg=13.876426179075533}, derivative=-4.1264422404519434E12}, evalInputDelta = -421.1519226276773
New Minimum: 13.876426179075533 > 12.669914057287503
F(0.004035360700000001) = LineSearchPoint{point=PointSample{avg=12.669914057287503}, derivative=-4.126442240284618E12}, evalInputDelta = -422.35843474946535
New Minimum: 12.669914057287503 > 8.871352554417024
F(0.028247524900000005) = LineSearchPoint{point=PointSample{avg=8.871352554417024}, derivative=-4.1264422401038203E12}, evalInputDelta = -426.15699625233583
New Minimum: 8.871352554417024 > 2.4409539524147696
F(0.19773267430000002) = LineSearchPoint{point=PointSample{avg=2.4409539524147696}, derivative=-4.1264422400326084E12}, evalInputDelta = -432.5873948543381
New Minimum: 2.4409539524147696 > 0.12805158612219608
F(1.3841287201) = LineSearchPoint{point=PointSample{avg=0.12805158612219608}, derivative=-4.126442240028394E12}, evalInputDelta = -434.90029722063065
New Minimum: 0.12805158612219608 > 0.005879487313071772
F(9.688901040700001) = LineSearchPoint{point=PointSample{avg=0.005879487313071772}, derivative=-4.126442240028367E12}, evalInputDelta = -435.0224693194398
New Minimum: 0.005879487313071772 > 0.0
F(67.8223072849) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
F(474.7561509943) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
F(3323.2930569601003) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
F(23263.0513987207) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
F(162841.3597910449) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
F(1139889.5185373144) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
F(7979226.6297612) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
F(5.58545864083284E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
F(3.909821048582988E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
F(2.7368747340080914E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
F(1.915812313805664E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
0.0 <= 435.02834880675283
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.126442240028367E12}, evalInputDelta = -435.02834880675283
Right bracket at 1.0E10
Converged to right
Fitness changed from 435.02834880675283 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.1310; Orientation: 0.0012; Line Search: 0.1238
F(0.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
0.0 <= 0.0
F(5.0E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 5.0E9
F(2.5E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 2.5E9
F(1.25E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 1.25E9
F(6.25E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 6.25E8
F(3.125E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 3.125E8
F(1.5625E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 1.5625E8
F(7.8125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 7.8125E7
F(3.90625E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 3.90625E7
F(1.953125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 1.953125E7
F(9765625.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 9765625.0
F(4882812.5) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Right bracket at 4882812.5
F(2441406.25) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-9.458297600000002}, evalInputDelta = 0.0
Loops = 12
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.1253; Orientation: 0.0011; Line Search: 0.1220
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 0.256s (< 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 10.30 seconds (0.044 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: 388809823912
Reset training subject: 388812577869
Adding measurement 3c5f83b4 to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD
Non-optimal measurement 435.02834880675283 < 435.02834880675283. Total: 1
th(0)=435.02834880675283;dx=-4.12644224E24
Adding measurement 4ff7af72 to history. Total: 1
New Minimum: 435.02834880675283 > 0.07158472718267048
Armijo: th(2.154434690031884)=0.07158472718267048; dx=-4.126442240028377E12 evalInputDelta=434.9567640795702
Non-optimal measurement 0.17256695109287423 < 0.07158472718267048. Total: 2
Armijo: th(1.077217345015942)=0.17256695109287423; dx=-4.1264422400284097E12 evalInputDelta=434.85578185566
Non-optimal measurement 1.1760825533249735 < 0.07158472718267048. Total: 2
Armijo: th(0.3590724483386473)=1.1760825533249735; dx=-4.126442240029433E12 evalInputDelta=433.85226625342784
Non-optimal measurement 4.980921371923598 < 0.07158472718267048. Total: 2
Armijo: th(0.08976811208466183)=4.980921371923598; dx=-4.126442240047341E12 evalInputDelta=430.0474274348292
Non-optimal measurement 10.065580171824843 < 0.07158472718267048. Total: 2
Armijo: th(0.017953622416932366)=10.065580171824843; dx=-4.1264422401372666E12 evalInputDelta=424.962768634928
Non-optimal measurement 12.980065372544754 < 0.07158472718267048. Total: 2
Armijo: th(0.002992270402822061)=12.980065372544754; dx=-4.126442240316599E12 evalInputDelta=422.0482834342081
Non-optimal measurement 13.944440743808565 < 0.07158472718267048. Total: 2
Armijo: th(4.2746720040315154E-4)=13.944440743808565; dx=-4.126442240466201E12 evalInputDelta=421.08390806294426
Non-optimal measurement 14.125426193367417 < 0.07158472718267048. Total: 2
Armijo: th(5.343340005039394E-5)=14.125426193367417; dx=-4.12644224050831E12 evalInputDelta=420.9029226133854
Non-optimal measurement 14.149593596793938 < 0.07158472718267048. Total: 2
Armijo: th(5.9370444500437714E-6)=14.149593596793938; dx=-4.126442240514449E12 evalInputDelta=420.8787552099589
Non-optimal measurement 14.152330802646741 < 0.07158472718267048. Total: 2
Armijo: th(5.937044450043771E-7)=14.152330802646741; dx=-4.1264422405151533E12 evalInputDelta=420.8760180041061
Non-optimal measurement 14.152607497344622 < 0.07158472718267048. Total: 2
Armijo: th(5.397313136403428E-8)=14.152607497344622; dx=-4.1264422405152246E12 evalInputDelta=420.8757413094082
Non-optimal measurement 14.152632862949122 < 0.07158472718267048. Total: 2
Armijo: th(4.4977609470028565E-9)=14.152632862949122; dx=-4.1264422405152305E12 evalInputDelta=420.8757159438037
Non-optimal measurement 14.152634991546014 < 0.07158472718267048. Total: 2
Armijo: th(3.4598161130791205E-10)=14.152634991546014; dx=-4.1264422405152314E12 evalInputDelta=420.87571381520684
Non-optimal measurement 18.088462017215775 < 0.07158472718267048. Total: 2
Armijo: th(2.4712972236279432E-11)=18.088462017215775; dx=-2.218880004174607E21 evalInputDelta=416.93988678953707
Non-optimal measurement 358.8668205245191 < 0.07158472718267048. Total: 2
Armijo: th(1.6475314824186289E-12)=358.8668205245191; dx=-3.2684684800034535E24 evalInputDelta=76.16152828223375
Non-optimal measurement 426.8959166928838 < 0.07158472718267048. Total: 2
Armijo: th(1.029707176511643E-13)=426.8959166928838; dx=-4.01029760000503E24 evalInputDelta=8.132432113869015
Non-optimal measurement 435.0283488067497 < 0.07158472718267048. Total: 2
Armijo: th(6.057101038303783E-15)=435.0283488067497; dx=-4.12644224E24 evalInputDelta=3.126388037344441E-12
Non-optimal measurement 0.07158472718267048 < 0.07158472718267048. Total: 2
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.07158472718267048
Fitness changed from 435.02834880675283 to 0.07158472718267048
Iteration 1 complete. Error: 0.07158472718267048 Total: 0.1294; Orientation: 0.0044; Line Search: 0.1163
Non-optimal measurement 0.07158472718267048 < 0.07158472718267048. Total: 2
LBFGS Accumulation History: 2 points
Non-optimal measurement 0.07158472718267048 < 0.07158472718267048. Total: 2
th(0)=0.07158472718267048;dx=-9.466287267310523
Adding measurement 12e0daa8 to history. Total: 2
New Minimum: 0.07158472718267048 > 0.07158472718267042
WOLFE (weak): th(2.154434690031884E-15)=0.07158472718267042; dx=-9.466287267310523 evalInputDelta=5.551115123125783E-17
Adding measurement 29da7932 to history. Total: 3
New Minimum: 0.07158472718267042 > 0.0715847271826704
WOLFE (weak): th(4.308869380063768E-15)=0.0715847271826704; dx=-9.466287267310523 evalInputDelta=8.326672684688674E-17
Adding measurement 2b2da2e5 to history. Total: 4
New Minimum: 0.0715847271826704 > 0.0715847271826702
WOLFE (weak): th(1.2926608140191303E-14)=0.0715847271826702; dx=-9.466287267310523 evalInputDelta=2.7755575615628914E-16
Adding measurement 444d46ed to history. Total: 5
New Minimum: 0.0715847271826702 > 0.07158472718266945
WOLFE (weak): th(5.1706432560765214E-14)=0.07158472718266945; dx=-9.466287267310523 evalInputDelta=1.0269562977782698E-15
Adding measurement 5bf3149b to history. Total: 6
New Minimum: 0.07158472718266945 > 0.07158472718266543
WOLFE (weak): th(2.5853216280382605E-13)=0.07158472718266543; dx=-9.466287267310523 evalInputDelta=5.051514762044462E-15
Adding measurement 79211ff5 to history. Total: 7
New Minimum: 0.07158472718266543 > 0.07158472718264024
WOLFE (weak): th(1.5511929768229563E-12)=0.07158472718264024; dx=-9.466287267310522 evalInputDelta=3.02396996332277E-14
Adding measurement 1fe6ab96 to history. Total: 8
New Minimum: 0.07158472718264024 > 0.0715847271824589
WOLFE (weak): th(1.0858350837760695E-11)=0.0715847271824589; dx=-9.466287267310504 evalInputDelta=2.115807529179392E-13
Adding measurement 28b4bc00 to history. Total: 9
New Minimum: 0.0715847271824589 > 0.071584727180978
WOLFE (weak): th(8.686680670208556E-11)=0.071584727180978; dx=-9.466287267310362 evalInputDelta=1.6924794898898199E-12
Adding measurement 1e6ab252 to history. Total: 10
New Minimum: 0.071584727180978 > 0.07158472716743829
WOLFE (weak): th(7.8180126031877E-10)=0.07158472716743829; dx=-9.466287267309056 evalInputDelta=1.523219050891811E-11
Adding measurement 933d326 to history. Total: 11
New Minimum: 0.07158472716743829 > 0.07158472703034877
WOLFE (weak): th(7.818012603187701E-9)=0.07158472703034877; dx=-9.466287267295849 evalInputDelta=1.5232171080015178E-10
Adding measurement 4374f0b7 to history. Total: 12
New Minimum: 0.07158472703034877 > 0.07158472550713199
WOLFE (weak): th(8.599813863506471E-8)=0.07158472550713199; dx=-9.4662872671491 evalInputDelta=1.6755384857347622E-9
Adding measurement 53dc18fc to history. Total: 13
New Minimum: 0.07158472550713199 > 0.07158470707620967
WOLFE (weak): th(1.0319776636207765E-6)=0.07158470707620967; dx=-9.46628726537344 evalInputDelta=2.0106460801860848E-8
Adding measurement 68dc13e5 to history. Total: 14
New Minimum: 0.07158470707620967 > 0.07158446579883604
WOLFE (weak): th(1.3415709627070094E-5)=0.07158446579883604; dx=-9.466287242128468 evalInputDelta=2.6138383443785607E-7
Adding measurement 3810db1d to history. Total: 15
New Minimum: 0.07158446579883604 > 0.0715810678397312
WOLFE (weak): th(1.878199347789813E-4)=0.0715810678397312; dx=-9.466286914767952 evalInputDelta=3.659342939277277E-6
Adding measurement 43ef7d6c to history. Total: 16
New Minimum: 0.0715810678397312 > 0.07152984398982946
WOLFE (weak): th(0.0028172990216847197)=0.07152984398982946; dx=-9.466281980578508 evalInputDelta=5.488319284101262E-5
Adding measurement 10e35977 to history. Total: 17
New Minimum: 0.07152984398982946 > 0.07070837816755945
WOLFE (weak): th(0.045076784346955515)=0.07070837816755945; dx=-9.466203039607331 evalInputDelta=8.76349015111022E-4
Adding measurement 45ff3fbb to history. Total: 18
New Minimum: 0.07070837816755945 > 0.057178707905812455
WOLFE (weak): th(0.7663053338982437)=0.057178707905812455; dx=-9.464952188527052 evalInputDelta=0.014406019276858022
Adding measurement 1db4f10 to history. Total: 19
New Minimum: 0.057178707905812455 > 0.0027946756375692924
WOLFE (weak): th(13.793496010168386)=0.0027946756375692924; dx=-9.461534135689032 evalInputDelta=0.06879005154510118
Adding measurement 4bdaaf2a to history. Total: 20
New Minimum: 0.0027946756375692924 > 0.0
WOLFE (weak): th(262
...skipping 9682 bytes...
a6-0fa4-4786-a8a2-bd1f8eb1c922 = 1.000/1.000e+00, b11e95bf-cc99-4671-a23f-51f12a4088a9 = 1.000/1.000e+00, 310b20b4-d643-4f64-ba8f-98cbe553446d = 1.000/1.000e+00, aedcb97e-ffe0-463d-8e10-cfa14f6002ef = 1.000/1.000e+00, 6c936a7d-30de-4417-8007-2fbb6bce0972 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0027946756375692924, 0.057178707905812455, 0.07070837816755945, 0.07152984398982946, 0.0715810678397312, 0.07158446579883604, 0.07158470707620967, 0.07158472550713199, 0.07158472703034877, 0.07158472716743829
Rejected: LBFGS Orientation magnitude: 2.474e+04, gradient 3.075e+00, dot -0.977; [6c936a7d-30de-4417-8007-2fbb6bce0972 = 1.000/1.000e+00, 310b20b4-d643-4f64-ba8f-98cbe553446d = 1.000/1.000e+00, d7272ca6-0fa4-4786-a8a2-bd1f8eb1c922 = 1.000/1.000e+00, b11e95bf-cc99-4671-a23f-51f12a4088a9 = 1.000/1.000e+00, aedcb97e-ffe0-463d-8e10-cfa14f6002ef = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0027946756375692924, 0.057178707905812455, 0.07070837816755945, 0.07152984398982946, 0.0715810678397312, 0.07158446579883604, 0.07158470707620967, 0.07158472550713199, 0.07158472703034877
Rejected: LBFGS Orientation magnitude: 2.474e+04, gradient 3.075e+00, dot -0.977; [b11e95bf-cc99-4671-a23f-51f12a4088a9 = 1.000/1.000e+00, aedcb97e-ffe0-463d-8e10-cfa14f6002ef = 1.000/1.000e+00, 6c936a7d-30de-4417-8007-2fbb6bce0972 = 1.000/1.000e+00, 310b20b4-d643-4f64-ba8f-98cbe553446d = 1.000/1.000e+00, d7272ca6-0fa4-4786-a8a2-bd1f8eb1c922 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0027946756375692924, 0.057178707905812455, 0.07070837816755945, 0.07152984398982946, 0.0715810678397312, 0.07158446579883604, 0.07158470707620967, 0.07158472550713199
Rejected: LBFGS Orientation magnitude: 2.474e+04, gradient 3.075e+00, dot -0.977; [310b20b4-d643-4f64-ba8f-98cbe553446d = 1.000/1.000e+00, 6c936a7d-30de-4417-8007-2fbb6bce0972 = 1.000/1.000e+00, aedcb97e-ffe0-463d-8e10-cfa14f6002ef = 1.000/1.000e+00, d7272ca6-0fa4-4786-a8a2-bd1f8eb1c922 = 1.000/1.000e+00, b11e95bf-cc99-4671-a23f-51f12a4088a9 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0027946756375692924, 0.057178707905812455, 0.07070837816755945, 0.07152984398982946, 0.0715810678397312, 0.07158446579883604, 0.07158470707620967
Rejected: LBFGS Orientation magnitude: 3.442e+04, gradient 3.075e+00, dot -0.951; [d7272ca6-0fa4-4786-a8a2-bd1f8eb1c922 = 1.000/1.000e+00, aedcb97e-ffe0-463d-8e10-cfa14f6002ef = 1.000/1.000e+00, 6c936a7d-30de-4417-8007-2fbb6bce0972 = 1.000/1.000e+00, 310b20b4-d643-4f64-ba8f-98cbe553446d = 1.000/1.000e+00, b11e95bf-cc99-4671-a23f-51f12a4088a9 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0027946756375692924, 0.057178707905812455, 0.07070837816755945, 0.07152984398982946, 0.0715810678397312, 0.07158446579883604
Rejected: LBFGS Orientation magnitude: 3.097e+04, gradient 3.075e+00, dot -1.000; [b11e95bf-cc99-4671-a23f-51f12a4088a9 = 1.000/1.000e+00, 310b20b4-d643-4f64-ba8f-98cbe553446d = 1.000/1.000e+00, d7272ca6-0fa4-4786-a8a2-bd1f8eb1c922 = 1.000/1.000e+00, aedcb97e-ffe0-463d-8e10-cfa14f6002ef = 1.000/1.000e+00, 6c936a7d-30de-4417-8007-2fbb6bce0972 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0027946756375692924, 0.057178707905812455, 0.07070837816755945, 0.07152984398982946, 0.0715810678397312
Rejected: LBFGS Orientation magnitude: 3.116e+04, gradient 3.075e+00, dot -1.000; [b11e95bf-cc99-4671-a23f-51f12a4088a9 = 1.000/1.000e+00, aedcb97e-ffe0-463d-8e10-cfa14f6002ef = 1.000/1.000e+00, d7272ca6-0fa4-4786-a8a2-bd1f8eb1c922 = 1.000/1.000e+00, 310b20b4-d643-4f64-ba8f-98cbe553446d = 1.000/1.000e+00, 6c936a7d-30de-4417-8007-2fbb6bce0972 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0027946756375692924, 0.057178707905812455, 0.07070837816755945, 0.07152984398982946
Rejected: LBFGS Orientation magnitude: 3.355e+04, gradient 3.075e+00, dot -1.000; [d7272ca6-0fa4-4786-a8a2-bd1f8eb1c922 = 1.000/1.000e+00, 6c936a7d-30de-4417-8007-2fbb6bce0972 = 1.000/1.000e+00, 310b20b4-d643-4f64-ba8f-98cbe553446d = 1.000/1.000e+00, aedcb97e-ffe0-463d-8e10-cfa14f6002ef = 1.000/1.000e+00, b11e95bf-cc99-4671-a23f-51f12a4088a9 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0027946756375692924, 0.057178707905812455, 0.07070837816755945
LBFGS Accumulation History: 3 points
Removed measurement 4bdaaf2a to history. Total: 20
Removed measurement 1db4f10 to history. Total: 19
Removed measurement 45ff3fbb to history. Total: 18
Removed measurement 10e35977 to history. Total: 17
Removed measurement 43ef7d6c to history. Total: 16
Removed measurement 3810db1d to history. Total: 15
Removed measurement 68dc13e5 to history. Total: 14
Removed measurement 53dc18fc to history. Total: 13
Removed measurement 4374f0b7 to history. Total: 12
Removed measurement 933d326 to history. Total: 11
Removed measurement 1e6ab252 to history. Total: 10
Removed measurement 28b4bc00 to history. Total: 9
Removed measurement 1fe6ab96 to history. Total: 8
Removed measurement 79211ff5 to history. Total: 7
Removed measurement 5bf3149b to history. Total: 6
Removed measurement 444d46ed to history. Total: 5
Removed measurement 2b2da2e5 to history. Total: 4
Removed measurement 29da7932 to history. Total: 3
Adding measurement 1329614f to history. Total: 3
th(0)=0.0;dx=-9.458297600000002
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(16310.208051716048)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(8155.104025858024)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2718.3680086193413)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(679.5920021548353)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(135.91840043096707)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(22.653066738494513)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3.2361523912135017)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.4045190489016877)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.044946560989076415)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.004494656098907641)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(4.086050999006947E-4)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3.405042499172456E-5)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.619263460901889E-6)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.870902472072778E-7)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.2472683147151853E-8)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(7.795426966969908E-10)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(4.585545274688181E-11)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.547525152604545E-12)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.340802711897129E-13)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(6.7040135594856445E-15)=0.0; dx=-9.458297600000002 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
MIN ALPHA (3.1923874092788784E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 9.9834; Orientation: 9.8636; Line Search: 0.1179
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 10.299s (< 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, -2.1451796258459663], [2.0, -0.14517962584596633]; valueStats=DoubleSummaryStatistics{count=2, sum=0.143169, min=0.071585, average=0.071585, max=0.071585}
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, -2.1451796258459663], [0.331, -0.14517962584596633]; valueStats=DoubleSummaryStatistics{count=2, sum=0.143169, min=0.071585, average=0.071585, max=0.071585}
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": "12.511",
"gc_time": "0.279"
},
"created_on": 1586734975124,
"file_name": "trainingTest",
"report": {
"simpleName": "Contract",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ImgReshapeLayerTest.Contract",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/ImgReshapeLayerTest.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/ImgReshapeLayer/Contract/trainingTest/202004124255",
"id": "a774eb99-cc4b-4bce-b673-eb8d3bbdc8a6",
"report_type": "Components",
"display_name": "Comparative Training",
"target": {
"simpleName": "ImgReshapeLayer",
"canonicalName": "com.simiacryptus.mindseye.layers.java.ImgReshapeLayer",
"link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/ImgReshapeLayer.java",
"javaDoc": ""
}
}