BasicOptimizer.scala:89 executed in 42.43 seconds (0.441 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: 113179186969100
Reset training subject: 113182004082500
Adding measurement 38856790 to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD+Trust
th(0)=-28.12519130059603;dx=-1.2468244796183754E-6
Armijo: th(2.154434690031884)=-28.12519130059603; dx=-9.53754258845449E-7 evalInputDelta=0.0
Armijo: th(1.077217345015942)=-28.125189797235254; dx=-9.542609444540024E-7 evalInputDelta=-1.5033607745351674E-6
Armijo: th(0.3590724483386473)=-28.125189797235254; dx=-9.539529900263123E-7 evalInputDelta=-1.5033607745351674E-6
Armijo: th(0.08976811208466183)=-28.12519130059603; dx=-9.538652993420314E-7 evalInputDelta=0.0
Armijo: th(0.017953622416932366)=-28.12519130059603; dx=-9.540348409378777E-7 evalInputDelta=0.0
Armijo: th(0.002992270402822061)=-28.12519130059603; dx=-9.535762528932015E-7 evalInputDelta=0.0
END: th(4.2746720040315154E-4)=-28.12519130059603; dx=-9.535147077152139E-7 evalInputDelta=0.0
Fitness changed from -28.12519130059603 to -28.12519130059603
Static Iteration Total: 30.6636; Orientation: 0.0634; Line Search: 22.7227
Iteration 1 failed. Error: -28.12519130059603
Previous Error: 0.0 -> -28.12519130059603
Retrying iteration 1
Reset training subject: 113209850819400
Adding measurement 5fdb2bd4 to history. Total: 0
LBFGS Accumulation History: 1 points
th(0)=-28.12519130059603;dx=-1.2464010402970155E-6
END: th(9.20950165399361E-4)=-28.12519130059603; dx=-9.530709064145714E-7 evalInputDelta=0.0
Fitness changed from -28.12519130059603 to -28.12519130059603
Static Iteration Total: 11.7653; Orientation: 0.0618; Line Search: 5.5046
Iteration 2 failed. Error: -28.12519130059603
Previous Error: 0.0 -> -28.12519130059603
Optimization terminated 2
Final threshold in iteration 2: -28.12519130059603 (> -Infinity) after 42.429s (< 5400.000s)

Returns

    -28.12519130059603