java.lang.UnsupportedOperationException

Trying to predict with an unstable model. Job was aborted due to observed numerical instability (exponential growth). Either the weights or the bias values are unreasonably large or lead to large activation values. Try a different initial distribution, a bounded activation function (Tanh), adding regularization (via max_w2, l1, l2, dropout) or learning rate (either enable adaptive_rate or use a smaller learning rate or faster annealing). For more information visit: http://jira.h2o.ai/browse/TN-4

Samebug tips0

We couldn't find tips for this exception.

Don't give up yet. Paste your full stack trace to get a solution.

Solutions on the web3

  • via Unknown by Arno Candel,
  • via Unknown by Unknown author,
  • via Unknown by Unknown author,
  • Stack trace

    • java.lang.UnsupportedOperationException: Trying to predict with an unstable model. Job was aborted due to observed numerical instability (exponential growth). Either the weights or the bias values are unreasonably large or lead to large activation values. Try a different initial distribution, a bounded activation function (Tanh), adding regularization (via max_w2, l1, l2, dropout) or learning rate (either enable adaptive_rate or use a smaller learning rate or faster annealing). For more information visit: http://jira.h2o.ai/browse/TN-4 at hex.deeplearning.DeepLearningModel.score0(DeepLearningModel.java:831) at hex.Model.score0(Model.java:852) at hex.Model$BigScore.map(Model.java:820) at water.MRTask.compute2(MRTask.java:678) at water.H2O$H2OCountedCompleter.compute1(H2O.java:1060) at hex.Model$BigScore$Icer.compute1(Model$BigScore$Icer.java) at water.H2O$H2OCountedCompleter.compute(H2O.java:1056) at jsr166y.CountedCompleter.exec(CountedCompleter.java:468) at jsr166y.ForkJoinTask.doExec(ForkJoinTask.java:263) at jsr166y.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:974) at jsr166y.ForkJoinPool.runWorker(ForkJoinPool.java:1477) at jsr166y.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:104)

    Write tip

    You have a different solution? A short tip here would help you and many other users who saw this issue last week.

    Users with the same issue

    We couldn't find other users who have seen this exception.