Code from BasicOptimizer.scala:75 executed in 48.57 seconds (0.898 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: 906078328745500
    Reset training subject: 906079214299100
    Adding measurement 4c5379f5 to history. Total: 0
    LBFGS Accumulation History: 1 points
    Constructing line search parameters: GD+Trust
    th(0)=-0.2548050880432129;dx=-1.4451209760059008E-9
    Armijo: th(2.154434690031884)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(1.077217345015942)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.3590724483386473)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.08976811208466183)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.017953622416932366)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.0538608672507971)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.03590724483386473)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.02693043362539855)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.022442028021165458)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.020197825219048914)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.01907572381799064)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.01963677451851978)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.019356249168255207)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.019215986493122922)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.01914585515555678)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.01918092082433985)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.019198453658731386)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.019207220075927154)=-0.2548050880432129; dx=-1.438833069402729E-9 eva

...skipping 1619 bytes...

    lInputDelta=0.0
    Armijo: th(0.10344769539291596)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.09310292585362437)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.09827531062327016)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.09568911823844727)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.09698221443085872)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.09633566633465299)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.09601239228655012)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.09617402931060155)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.09609321079857583)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.09605280154256297)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    Armijo: th(0.09603259691455654)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.09602249460055333)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.09602754575755493)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.09603007133605573)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.09603133412530614)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.09603196551993134)=-0.2548050880432129; dx=-1.438833069402729E-9 evalInputDelta=0.0
    mu ~= nu (0.09603196551993134): th(0.0)=-0.2548050880432129
    Fitness changed from -0.2548050880432129 to -0.2548050880432129
    Static Iteration Total: 22.3260; Orientation: 0.0074; Line Search: 20.3682
    Iteration 2 failed. Error: -0.2548050880432129
    Previous Error: 0.0 -> -0.2548050880432129
    Optimization terminated 2
    Final threshold in iteration 2: -0.2548050880432129 (> -Infinity) after 48.568s (< 720.000s)
    

Returns:

    -0.2548050880432129