Code from BasicOptimizer.scala:75 executed in 62.65 seconds (1.111 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: 913321041451300
    Reset training subject: 913322166505200
    Adding measurement c27b040 to history. Total: 0
    LBFGS Accumulation History: 1 points
    Constructing line search parameters: GD+Trust
    th(0)=0.6434313058853149;dx=-1.0515225864751154E-7
    Armijo: th(2.154434690031884)=0.6434313058853149; dx=-1.0514068349421574E-7 evalInputDelta=0.0
    Armijo: th(1.077217345015942)=0.6434313058853149; dx=-1.0514068753194604E-7 evalInputDelta=0.0
    Armijo: th(0.3590724483386473)=0.6434313058853149; dx=-1.051406888185139E-7 evalInputDelta=0.0
    Armijo: th(0.08976811208466183)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.017953622416932366)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.002992270402822061)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(4.2746720040315154E-4)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.0017098688016126062)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.001068668001007879)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(7.480676007055152E-4)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(5.877674005543334E-4)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(5.076173004787425E-4)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(5.476923505165379E-4)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(5.276548254976402E-4)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(5.37673588007089E-4)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(5.326642067523645E-4)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(5.301595161250024E-4)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(5.289071708113214E-4)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInput

...skipping 1822 bytes...

    Armijo: th(0.002843377952305196)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.0025590401570746765)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.002701209054689936)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.0026301246058823063)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.0026656668302861212)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.0026478957180842136)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.00263901016198326)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.0026434529400337367)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.0026412315510084983)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.002640120856495879)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    Armijo: th(0.0026395655092395698)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.002639287835611415)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.0026394266724254923)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.002639496090832531)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.0026395308000360506)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    WOLFE (weak): th(0.00263954815463781)=0.6434313058853149; dx=-1.0514068960565755E-7 evalInputDelta=0.0
    mu ~= nu (0.00263954815463781): th(0.0)=0.6434313058853149
    Fitness changed from 0.6434313058853149 to 0.6434313058853149
    Static Iteration Total: 28.3457; Orientation: 0.0155; Line Search: 25.9791
    Iteration 2 failed. Error: 0.6434313058853149
    Previous Error: 0.0 -> 0.6434313058853149
    Optimization terminated 2
    Final threshold in iteration 2: 0.6434313058853149 (> -Infinity) after 62.655s (< 720.000s)
    

Returns:

    0.6434313058853149