Funasr1.0 (#1362)

zhifu gao

2024-02-06 d92cd5ae037ae85ab9730499d99e5c1bd475eed2

 funasr/train_utils/trainer.py

@@ -148,6 +148,7 @@
            
            self._train_epoch(epoch)


            
            if self.use_ddp or self.use_fsdp:
                dist.barrier()
@@ -156,8 +157,8 @@

            if self.use_ddp or self.use_fsdp:
                dist.barrier()
                

           
           
            if self.rank == 0:
                self._save_checkpoint(epoch)
            
@@ -172,7 +173,8 @@
            
        if self.use_ddp or self.use_fsdp:
            dist.barrier()
      


        if self.writer:
            self.writer.close()
        
@@ -202,7 +204,25 @@
            my_context = self.model.no_sync if batch_idx % accum_grad != 0 else nullcontext
            with my_context():
                time2 = time.perf_counter()
                print("before, GPU, memory: {:.1} MB, "
                      "{:.1} MB, "
                      "{:.1} MB, "
                      "{:.1} MB".format(torch.cuda.memory_allocated()/1024/1024/1024,
                                     torch.cuda.max_memory_allocated()/1024/1024/1024,
                                     torch.cuda.memory_reserved()/1024/1024/1024,
                                     torch.cuda.max_memory_reserved()/1024/1024/1024,
                                     ))

                retval = self.model(**batch)
                torch.cuda.empty_cache()
                print("after, GPU, memory: {:.1} MB, "
                      "{:.1} MB, "
                      "{:.1} MB, "
                      "{:.1} MB".format(torch.cuda.memory_allocated()/1024/1024/1024,
                                     torch.cuda.max_memory_allocated()/1024/1024/1024,
                                     torch.cuda.memory_reserved()/1024/1024/1024,
                                     torch.cuda.max_memory_reserved()/1024/1024/1024,
                                     ))
                time3 = time.perf_counter()
                speed_stats["forward_time"] = f"{time3 - time2:0.3f}"
                loss, stats, weight = retval