aishell example

游雁

2024-02-19 1448e021accfdb03a381651cb5a8be6d1a6e8adf

 funasr/train_utils/trainer.py

@@ -204,25 +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,
                                     ))
                # print("before, GPU, memory: {:.3f} GB, "
                #       "{:.3f} GB, "
                #       "{:.3f} GB, "
                #       "{:.3f} GB".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,
                                     ))
                # print("after, GPU, memory: {:.3f} GB, "
                #       "{:.3f} GB, "
                #       "{:.3f} GB, "
                #       "{:.3f} GB".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
@@ -275,12 +275,21 @@

            pbar.update(1)
            if self.local_rank == 0:
                gpu_info = "GPU, memory: {:.3f} GB, " \
                           "{:.3f} GB, "\
                           "{:.3f} GB, "\
                           "{:.3f} GB".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,
                                             )
                description = (
                    f"Train epoch: {epoch}/{self.max_epoch}, "
                    f"step {batch_idx}/{len(self.dataloader_train)}, "
                    f"{speed_stats}, "
                    f"(loss: {loss.detach().cpu().item():.3f}), "
                    f"{[(k, round(v.cpu().item(), 3)) for k, v in stats.items()]}"
                    f"{gpu_info}"
                )
                pbar.set_description(description)
                if self.writer: