Code from BasicOptimizer.scala:75 executed in 3621.81 seconds (41.854 gc):

    val lineSearchInstance: LineSearchStrategy = lineSearchFactory
    IterativeTrainer.wrap(trainable)
      .setOrientation(orientation())
      .setMonitor(new TrainingMonitor() {
        override def clear(): Unit = trainingMonitor.clear()
  
        override def log(msg: String): Unit = trainingMonitor.log(msg)
  
        override def onStepFail(currentPoint: Step): Boolean = {
          BasicOptimizer.this.onStepFail(trainable, currentPoint)
        }
  
        override def onStepComplete(currentPoint: Step): Unit = {
          if (0 < logEvery && (0 == currentPoint.iteration % logEvery || currentPoint.iteration < logEvery)) {
            val image = currentImage
            timelineAnimation += image
            val caption = "Iteration " + currentPoint.iteration
            out.p(caption + "\n" + out.jpg(image, caption))
          }
          BasicOptimizer.this.onStepComplete(trainable, currentPoint)
          trainingMonitor.onStepComplete(currentPoint)
          super.onStepComplete(currentPoint)
        }
      })
      .setTimeout(trainingMinutes, TimeUnit.MINUTES)
      .setMaxIterations(trainingIterations)
      .setLineSearchFactory((_: CharSequence) => lineSearchInstance)
      .setTerminateThreshold(java.lang.Double.NEGATIVE_INFINITY)
      .runAndFree
      .asInstanceOf[lang.Double]

Logging:

    Reset training subject: 1515130907868100
    Reset training subject: 1515196218304900
    Adding measurement 37ccedbe to history. Total: 0
    LBFGS Accumulation History: 1 points
    Constructing line search parameters: GD+Trust
    th(0)=6.819971298398388;dx=-1.3553924210788504E-7
    Armijo: th(2.154434690031884)=6.819971298398388; dx=-1.3549236470806968E-7 evalInputDelta=0.0
    Armijo: th(1.077217345015942)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.3590724483386473)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.08976811208466183)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.017953622416932366)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.002992270402822061)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.010472946409877214)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.006732608406349637)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.004862439404585849)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.003927354903703955)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.0034598126532630075)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.003226041528042534)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.0033429270906527708)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.0032844843093476524)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.003255262918695093)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.0032698736140213728)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.003277178961684513)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.0032735262878529426)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    WOLFE

...skipping 1618 bytes...

    758)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.017647250747646497)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.01588252567288185)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.016764888210264173)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.01632370694157301)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.01654429757591859)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.0164340022587458)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.016378854600159407)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.016406428429452603)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.016392641514806003)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.016385748057482705)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.016382301328821056)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.01638402469315188)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.016383163010986468)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.016382732169903762)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.01638251674936241)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    Armijo: th(0.01638240903909173)=6.819971298398388; dx=-1.354923647080278E-7 evalInputDelta=0.0
    mu ~= nu (0.016382301328821056): th(0.0)=6.819971298398388
    Fitness changed from 6.819971298398388 to 6.819971298398388
    Static Iteration Total: 1640.7302; Orientation: 0.3143; Line Search: 1511.3073
    Iteration 2 failed. Error: 6.819971298398388
    Previous Error: 0.0 -> 6.819971298398388
    Optimization terminated 2
    Final threshold in iteration 2: 6.819971298398388 (> -Infinity) after 3621.805s (< 7200.000s)
    

Returns:

    6.819971298398388