BasicOptimizer.scala:89 executed in 91.79 seconds (1.634 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: 657311945462500
Reset training subject: 657318355425600
Adding measurement 73fd510d to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD+Trust
th(0)=-35.85777019344046;dx=-2.009821126103586E-6
Armijo: th(2.154434690031884)=-35.85777019344046; dx=-1.7709849027518668E-6 evalInputDelta=0.0
Armijo: th(1.077217345015942)=-35.85777019344046; dx=-1.7708075003743616E-6 evalInputDelta=0.0
Armijo: th(0.3590724483386473)=-35.8577680871396; dx=-1.7708008766023824E-6 evalInputDelta=-2.1063008617261403E-6
Armijo: th(0.08976811208466183)=-35.85777019344046; dx=-1.7708285726357327E-6 evalInputDelta=0.0
Armijo: th(0.017953622416932366)=-35.85777019344046; dx=-1.7706656668023437E-6 evalInputDelta=0.0
Armijo: th(0.002992270402822061)=-35.85777019344046; dx=-1.770986375442551E-6 evalInputDelta=0.0
END: th(4.2746720040315154E-4)=-35.85777019344046; dx=-1.770890342233079E-6 evalInputDelta=0.0
Fitness changed from -35.85777019344046 to -35.85777019344046
Static Iteration Total: 67.5006; Orientation: 0.1453; Line Search: 48.8665
Iteration 1 failed. Error: -35.85777019344046
Previous Error: 0.0 -> -35.85777019344046
Retrying iteration 1
Reset training subject: 657379446259500
Adding measurement 5d9daf8 to history. Total: 0
LBFGS Accumulation History: 1 points
th(0)=-35.85777019344046;dx=-2.0107498241733254E-6
END: th(9.20950165399361E-4)=-35.85777019344046; dx=-1.770519524837539E-6 evalInputDelta=0.0
Fitness changed from -35.85777019344046 to -35.85777019344046
Static Iteration Total: 24.2868; Orientation: 0.1304; Line Search: 12.2354
Iteration 2 failed. Error: -35.85777019344046
Previous Error: 0.0 -> -35.85777019344046
Optimization terminated 2
Final threshold in iteration 2: -35.85777019344046 (> -Infinity) after 91.787s (< 5400.000s)

Returns

    -35.85777019344046