Code from BasicOptimizer.scala:75 executed in 173.51 seconds (1.274 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: 904642843866400
    Reset training subject: 904646004510900
    Adding measurement 67784537 to history. Total: 0
    LBFGS Accumulation History: 1 points
    Constructing line search parameters: GD+Trust
    th(0)=-0.09602651000022888;dx=-1.6379129470724563E-9
    Armijo: th(2.154434690031884)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(1.077217345015942)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.3590724483386473)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.08976811208466183)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.017953622416932366)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.002992270402822061)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.010472946409877214)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.006732608406349637)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.004862439404585849)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.003927354903703955)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.004394897154144902)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.004161126028924428)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.004278011591534665)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.004219568810229547)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.004248790200882106)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.004234179505555826)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.004241484853218966)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.004237832179387396)=-0.096

...skipping 1847 bytes...

    0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.020535951138785542)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.021676837313162514)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.021106394225974028)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.021391615769568273)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.021249004997771152)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.02117769961187259)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.02121335230482187)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.021195525958347228)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.021186612785109908)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    Armijo: th(0.02118215619849125)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.021179927905181917)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.02118104205183658)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.021181599125163916)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.02118187766182758)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    WOLFE (weak): th(0.021182016930159413)=-0.09602651000022888; dx=-1.6206106693934598E-9 evalInputDelta=0.0
    mu ~= nu (0.021182016930159413): th(0.0)=-0.09602651000022888
    Fitness changed from -0.09602651000022888 to -0.09602651000022888
    Static Iteration Total: 79.5595; Orientation: 0.0287; Line Search: 73.3931
    Iteration 2 failed. Error: -0.09602651000022888
    Previous Error: 0.0 -> -0.09602651000022888
    Optimization terminated 2
    Final threshold in iteration 2: -0.09602651000022888 (> -Infinity) after 173.513s (< 720.000s)
    

Returns:

    -0.09602651000022888