Code from BasicOptimizer.scala:75 executed in 41.39 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: 909669531534300
    Reset training subject: 909670276523000
    Adding measurement 264700ed to history. Total: 0
    LBFGS Accumulation History: 1 points
    Constructing line search parameters: GD+Trust
    th(0)=0.4888181686401367;dx=-4.3823883689058134E-8
    Armijo: th(2.154434690031884)=0.4888181686401367; dx=-4.382388336645356E-8 evalInputDelta=0.0
    Armijo: th(1.077217345015942)=0.4888181686401367; dx=-4.382388372129383E-8 evalInputDelta=0.0
    Armijo: th(0.3590724483386473)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.08976811208466183)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.017953622416932366)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.002992270402822061)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(4.2746720040315154E-4)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.0017098688016126062)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.001068668001007879)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(7.480676007055152E-4)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(5.877674005543334E-4)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(6.679175006299243E-4)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(6.278424505921289E-4)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(6.478799756110266E-4)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(6.378612131015778E-4)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(6.328518318468534E-4)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(6.353565224742156E-4)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(6.341041771605344E-4)=0.4888181686401367; dx=-4.3823883689058134E-8 ev

...skipping 1816 bytes...

    elta=0.0
    Armijo: th(0.0034112428843088)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.00307011859587792)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.00324068074009336)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.00315539966798564)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.0031980402040395)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.00317671993601257)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.003166059801999105)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.0031713898690058375)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.0031687248355024714)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.003167392318750788)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    Armijo: th(0.0031667260603749463)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.0031663929311870256)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.003166559495780986)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.003166642778077966)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.003166684419226456)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    WOLFE (weak): th(0.003166705239800701)=0.4888181686401367; dx=-4.3823883689058134E-8 evalInputDelta=0.0
    mu ~= nu (0.003166705239800701): th(0.0)=0.4888181686401367
    Fitness changed from 0.4888181686401367 to 0.4888181686401367
    Static Iteration Total: 18.4888; Orientation: 0.0073; Line Search: 17.0582
    Iteration 2 failed. Error: 0.4888181686401367
    Previous Error: 0.0 -> 0.4888181686401367
    Optimization terminated 2
    Final threshold in iteration 2: 0.4888181686401367 (> -Infinity) after 41.386s (< 720.000s)
    

Returns:

    0.4888181686401367