BasicOptimizer.scala:89 executed in 39.21 seconds (0.342 gc):

    val lineSearchInstance: LineSearchStrategy = lineSearchFactory
    val trainer = new IterativeTrainer(trainable)
    trainer.setOrientation(orientation())
    trainer.setMonitor(new TrainingMonitor() {
      override def clear(): Unit = trainingMonitor.clear()
  
      override def log(msg: String): Unit = {
        trainingMonitor.log(msg)
        BasicOptimizer.this.log(msg)
      }
  
      override def onStepFail(currentPoint: Step): Boolean = {
        BasicOptimizer.this.onStepFail(trainable.addRef().asInstanceOf[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.addRef().asInstanceOf[Trainable], currentPoint)
        trainingMonitor.onStepComplete(currentPoint)
        super.onStepComplete(currentPoint)
      }
    })
    trainer.setTimeout(trainingMinutes, TimeUnit.MINUTES)
    trainer.setMaxIterations(trainingIterations)
    trainer.setLineSearchFactory((_: CharSequence) => lineSearchInstance)
    trainer.setTerminateThreshold(java.lang.Double.NEGATIVE_INFINITY)
    val result = trainer.run.asInstanceOf[lang.Double]
    trainer.freeRef()
    result
Logging 
Reset training subject: 69797012925599
Reset training subject: 69799701445800
Adding measurement 52037d29 to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD+Trust
th(0)=-21.031665769088857;dx=-7.723139036934154E-7
Armijo: th(2.154434690031884)=-21.031665769088857; dx=-6.280427453565209E-7 evalInputDelta=0.0
Armijo: th(1.077217345015942)=-21.031665769088857; dx=-6.277040636067121E-7 evalInputDelta=0.0
Armijo: th(0.3590724483386473)=-21.031665769088857; dx=-6.280409846497199E-7 evalInputDelta=0.0
Armijo: th(0.08976811208466183)=-21.031665769088857; dx=-6.278059884912545E-7 evalInputDelta=0.0
Armijo: th(0.017953622416932366)=-21.031665769088857; dx=-6.280300672253814E-7 evalInputDelta=0.0
Armijo: th(0.002992270402822061)=-21.031665769088857; dx=-6.279906832732519E-7 evalInputDelta=0.0
END: th(4.2746720040315154E-4)=-21.031665769088857; dx=-6.278586041124965E-7 evalInputDelta=0.0
Fitness changed from -21.031665769088857 to -21.031665769088857
Static Iteration Total: 28.9587; Orientation: 0.0622; Line Search: 20.8440
Iteration 1 failed. Error: -21.031665769088857
Previous Error: 0.0 -> -21.031665769088857
Retrying iteration 1
Reset training subject: 69825971829400
Adding measurement 2737b7ac to history. Total: 0
LBFGS Accumulation History: 1 points
th(0)=-21.031665769088857;dx=-7.719504529707671E-7
END: th(9.20950165399361E-4)=-21.031665769088857; dx=-6.272169000810462E-7 evalInputDelta=0.0
Fitness changed from -21.031665769088857 to -21.031665769088857
Static Iteration Total: 10.2527; Orientation: 0.0623; Line Search: 5.2405
Iteration 2 failed. Error: -21.031665769088857
Previous Error: 0.0 -> -21.031665769088857
Optimization terminated 2
Final threshold in iteration 2: -21.031665769088857 (> -Infinity) after 39.213s (< 5400.000s)

Returns

    -21.031665769088857