Code from BasicOptimizer.scala:75 executed in 336.07 seconds (3.225 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: 904081574177100
    Reset training subject: 904087782977400
    Adding measurement 21002393 to history. Total: 0
    LBFGS Accumulation History: 1 points
    Constructing line search parameters: GD+Trust
    th(0)=0.051280662417411804;dx=-1.2198082295167763E-9
    Armijo: th(2.154434690031884)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(1.077217345015942)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.3590724483386473)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.08976811208466183)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.017953622416932366)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.002992270402822061)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(4.2746720040315154E-4)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.0017098688016126062)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.0023510696022173336)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.0026716700025196972)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.002831970202670879)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.00291212030274647)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.0028720452527086745)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.0028520077276897766)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.0028419889651803277)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.0028469983464350524)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.0028444936558076903)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.002843

...skipping 1776 bytes...

    80662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.013787434880406093)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.0145534034848731)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.014170419182639596)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.014361911333756347)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.01426616525819797)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.014218292220418784)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.014242228739308378)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.014230260479863581)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.014224276350141183)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    Armijo: th(0.014221284285279984)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.014219788252849384)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.014220536269064684)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.014220910277172333)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.014221097281226159)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.014221190783253072)=0.051280662417411804; dx=-1.1787184394517529E-9 evalInputDelta=0.0
    mu ~= nu (0.014221190783253072): th(0.0)=0.051280662417411804
    Fitness changed from 0.051280662417411804 to 0.051280662417411804
    Static Iteration Total: 151.6166; Orientation: 0.0581; Line Search: 139.1962
    Iteration 2 failed. Error: 0.051280662417411804
    Previous Error: 0.0 -> 0.051280662417411804
    Optimization terminated 2
    Final threshold in iteration 2: 0.051280662417411804 (> -Infinity) after 336.072s (< 1800.000s)
    

Returns:

    0.051280662417411804