BasicOptimizer.scala:89 executed in 75.59 seconds (0.654 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: 2604530084479
Reset training subject: 2609517598537
Corrupt weights measurement
LBFGS Accumulation History: 0 points
Constructing line search parameters: GD+Trust
th(0)=-17.54096359014511;dx=-1.5303075711184578E-6
WOLFE (weak): th(2.154434690031884)=-17.54096692800522; dx=-1.3905612389041086E-6 evalInputDelta=3.337860107421875E-6
WOLFE (weak): th(4.308869380063768)=-17.540970742702484; dx=-1.3906104347619868E-6 evalInputDelta=7.152557373046875E-6
WOLFE (weak): th(12.926608140191302)=-17.540984869003296; dx=-1.3902574628076242E-6 evalInputDelta=2.1278858184814453E-5
WOLFE (weak): th(51.70643256076521)=-17.54104971885681; dx=-1.3902659691974673E-6 evalInputDelta=8.612871170043945E-5
WOLFE (weak): th(258.53216280382605)=-17.541394889354706; dx=-1.3898704393192305E-6 evalInputDelta=4.3129920959472656E-4
WOLFE (weak): th(1551.1929768229563)=-17.543556213378906; dx=-1.386368122200547E-6 evalInputDelta=0.002592623233795166
END: th(10858.350837760694)=-17.558834314346313; dx=-1.3446129980679009E-6 evalInputDelta=0.017870724201202393
Fitness changed from -17.61676198244095 to -17.61676198244095
Static Iteration Total: 55.6063; Orientation: 0.0197; Line Search: 40.3800
Iteration 1 failed. Error: -17.61676198244095
Previous Error: 0.0 -> -17.61676198244095
Retrying iteration 1
Reset training subject: 2660136619283
Corrupt weights measurement
LBFGS Accumulation History: 0 points
th(0)=-17.54096359014511;dx=-1.5306690273172056E-6
END: th(23393.607721408407)=-17.57859617471695; dx=-1.2781172405308253E-6 evalInputDelta=0.03763258457183838
Fitness changed from -17.61676198244095 to -17.61676198244095
Static Iteration Total: 19.9818; Orientation: 0.0206; Line Search: 9.9238
Iteration 2 failed. Error: -17.61676198244095
Previous Error: 0.0 -> -17.61676198244095
Optimization terminated 2
Final threshold in iteration 2: -17.61676198244095 (> -Infinity) after 75.589s (< 5400.000s)

Returns

    -17.61676198244095