BasicOptimizer.scala:89 executed in 41.45 seconds (0.893 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: 68698836016800
Reset training subject: 68701594855100
Adding measurement 10980560 to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD+Trust
th(0)=-27.972600904288942;dx=-5.95118353813241E-7
Armijo: th(2.154434690031884)=-27.972600904288942; dx=-5.330928748131611E-7 evalInputDelta=0.0
Armijo: th(1.077217345015942)=-27.972600904288942; dx=-5.33113087296665E-7 evalInputDelta=0.0
Armijo: th(0.3590724483386473)=-27.972600904288942; dx=-5.332025163722391E-7 evalInputDelta=0.0
Armijo: th(0.08976811208466183)=-27.972600904288942; dx=-5.329118403695416E-7 evalInputDelta=0.0
Armijo: th(0.017953622416932366)=-27.972600904288942; dx=-5.33291028203853E-7 evalInputDelta=0.0
Armijo: th(0.002992270402822061)=-27.972600904288942; dx=-5.333440072682546E-7 evalInputDelta=0.0
END: th(4.2746720040315154E-4)=-27.972600904288942; dx=-5.33196009484781E-7 evalInputDelta=0.0
Fitness changed from -27.972600904288942 to -27.972600904288942
Static Iteration Total: 30.8909; Orientation: 0.1310; Line Search: 22.9229
Iteration 1 failed. Error: -27.972600904288942
Previous Error: 0.0 -> -27.972600904288942
Retrying iteration 1
Reset training subject: 68729727357600
Adding measurement 6e3b2dd3 to history. Total: 0
LBFGS Accumulation History: 1 points
th(0)=-27.972600904288942;dx=-5.950765405083712E-7
END: th(9.20950165399361E-4)=-27.972600904288942; dx=-5.329632559806215E-7 evalInputDelta=0.0
Fitness changed from -27.972600904288942 to -27.972600904288942
Static Iteration Total: 10.5433; Orientation: 0.0451; Line Search: 5.4510
Iteration 2 failed. Error: -27.972600904288942
Previous Error: 0.0 -> -27.972600904288942
Optimization terminated 2
Final threshold in iteration 2: -27.972600904288942 (> -Infinity) after 41.434s (< 5400.000s)

Returns

    -27.972600904288942