Code from BasicOptimizer.scala:75 executed in 37.38 seconds (0.742 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: 907882949475500
    Reset training subject: 907883653888100
    Adding measurement 3752cff3 to history. Total: 0
    LBFGS Accumulation History: 1 points
    Constructing line search parameters: GD+Trust
    th(0)=-0.2706909775733948;dx=-4.3907261772427E-9
    Armijo: th(2.154434690031884)=-0.2706909775733948; dx=-4.284659886989763E-9 evalInputDelta=0.0
    Armijo: th(1.077217345015942)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.3590724483386473)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.08976811208466183)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.017953622416932366)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.002992270402822061)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.010472946409877214)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.006732608406349637)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.004862439404585849)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.005797523905467743)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.00626506615590869)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.006498837281129164)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.006381951718518927)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.0063235089372138086)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.006294287546561249)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.006308898241887529)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.006316203589550669)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.006319856263382238)=-0.2706909775733948; dx=-4

...skipping 1645 bytes...

    putDelta=0.0
    Armijo: th(0.03404774743236445)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.03064297268912801)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.03234536006074623)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.03149416637493712)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.03191976321784168)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.0317069647963894)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.031600565585663265)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.031653765191026334)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.0316271653883448)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.03161386548700403)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    Armijo: th(0.03160721553633365)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.03160389056099846)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.03160555304866605)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.03160638429249985)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.031606799914416756)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.031607007725375204)=-0.2706909775733948; dx=-4.284659903845923E-9 evalInputDelta=0.0
    mu ~= nu (0.031607007725375204): th(0.0)=-0.2706909775733948
    Fitness changed from -0.2706909775733948 to -0.2706909775733948
    Static Iteration Total: 17.1977; Orientation: 0.0074; Line Search: 15.8791
    Iteration 2 failed. Error: -0.2706909775733948
    Previous Error: 0.0 -> -0.2706909775733948
    Optimization terminated 2
    Final threshold in iteration 2: -0.2706909775733948 (> -Infinity) after 37.379s (< 720.000s)
    

Returns:

    -0.2706909775733948