added safety check on number of examples extracted to avoid disk filling

trainer/include/Trainer.hpp

@@ -9,6 +9,8 @@ class Trainer
 {
   private :
 
+  static constexpr std::size_t safetyNbExamplesMax = 10*1000*1000;
+
   struct Examples
   {
     std::vector<torch::Tensor> contexts;

trainer/src/Trainer.cpp

@@ -122,6 +122,8 @@ void Trainer::extractExamples(SubConfig & config, bool debug, std::filesystem::p
     int goldIndex = machine.getTransitionSet().getTransitionIndex(goldTransition);
 
     totalNbExamples += context.size();
+    if (totalNbExamples >= (int)safetyNbExamplesMax)
+      util::myThrow(fmt::format("Trying to extract more examples than the limit ({})", util::int2HumanStr(safetyNbExamplesMax)));
 
     examplesPerState[config.getState()].addContext(context);
     examplesPerState[config.getState()].addClass(goldIndex);