Code from BasicOptimizer.scala:75 executed in 39.57 seconds (2.209 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: 1191372712985
    Reset training subject: 1191977537065
    Adding measurement 78197fb0 to history. Total: 0
    LBFGS Accumulation History: 1 points
    Constructing line search parameters: GD+Trust
    th(0)=0.9172172556741806;dx=-1.9356141768195134E-8
    Armijo: th(2.154434690031884)=0.9172172556741806; dx=-1.9356144575128295E-8 evalInputDelta=0.0
    Armijo: th(1.077217345015942)=0.9172172556741806; dx=-1.935613537644761E-8 evalInputDelta=0.0
    Armijo: th(0.3590724483386473)=0.9172172556741806; dx=-1.935614250580789E-8 evalInputDelta=0.0
    Armijo: th(0.08976811208466183)=0.9172172556741806; dx=-1.935614855348359E-8 evalInputDelta=0.0
    Armijo: th(0.017953622416932366)=0.9172172556741806; dx=-1.9356152808308232E-8 evalInputDelta=0.0
    Armijo: th(0.002992270402822061)=0.9172172556741806; dx=-1.9356141764882656E-8 evalInputDelta=0.0
    WOLFE (weak): th(4.2746720040315154E-4)=0.9172172556741806; dx=-1.9356141768195134E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.0017098688016126062)=0.9172172556741806; dx=-1.9356141770256587E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.0023510696022173336)=0.9172172556741806; dx=-1.935614176898183E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.0026716700025196972)=0.9172172556741806; dx=-1.9356141768564318E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.002831970202670879)=0.9172172556741806; dx=-1.9356141766371042E-8 evalInputDelta=0.0
    Armijo: th(0.00291212030274647)=0.9172172556741806; dx=-1.9356141763402496E-8 evalInputDelta=0.0
    Armijo: th(0.0028720452527086745)=0.9172172556741806; dx=-1.935614176476472E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.0028520077276897766)=0.9172172556741806; dx=-1.935614176671841E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.0028620264901992255)=0.9172172556741806; dx=-1.935614176476472E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.0028670358714539502)=0.9172172556741806; dx=-1.935614176476472E-8 evalInputDelta=0.0
    Armijo: th(0.0028695405620813123)=0.9172172556741806; dx=-1.935614176476472E-8 evalInputDelta=0.0
    Armijo: th(0.0028682882167676313)=0.9172172556741806; dx=-1.935614176476472E-8 evalIn

...skipping 1565 bytes...

    15280833967E-8 evalInputDelta=0.0
    Armijo: th(0.015446688503196887)=0.9172172556741806; dx=-1.9356141954779846E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.013902019652877198)=0.9172172556741806; dx=-1.9356141959676024E-8 evalInputDelta=0.0
    Armijo: th(0.014674354078037043)=0.9172172556741806; dx=-1.935614195378548E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.01428818686545712)=0.9172172556741806; dx=-1.9356141956055372E-8 evalInputDelta=0.0
    Armijo: th(0.014481270471747082)=0.9172172556741806; dx=-1.9356141955378933E-8 evalInputDelta=0.0
    Armijo: th(0.0143847286686021)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.01433645776702961)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    Armijo: th(0.014360593217815855)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    Armijo: th(0.014348525492422732)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    Armijo: th(0.014342491629726171)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    Armijo: th(0.014339474698377892)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.014337966232703751)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.01433872046554082)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.014339097581959356)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.014339286140168623)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.014339380419273257)=0.9172172556741806; dx=-1.9356141956279604E-8 evalInputDelta=0.0
    mu ~= nu (0.014339380419273257): th(0.0)=0.9172172556741806
    Fitness changed from 0.9172172556741806 to 0.9172172556741806
    Static Iteration Total: 18.1786; Orientation: 0.0684; Line Search: 16.9901
    Iteration 2 failed. Error: 0.9172172556741806
    Previous Error: 0.0 -> 0.9172172556741806
    Optimization terminated 2
    Final threshold in iteration 2: 0.9172172556741806 (> -Infinity) after 39.569s (< 3600.000s)
    

Returns:

    0.9172172556741806