FUNASR训练
blame | 历史 | 补丁 | 提交 | 提交对比 | ignore whitespace
游雁
2024-03-26 abf5af40e934216b397c5331e0a68dc92f0a4f4e 
 funasr/train_utils/trainer.py


@@ -239,6 +239,8 @@


        Args:


            epoch (int): The current epoch number.


        """


        if self.use_ddp or self.use_fsdp:


            dist.barrier()


        logging.info(f"Train epoch: {epoch}, rank: {self.local_rank}\n")


        model.train()




@@ -248,8 +250,14 @@


        optim.zero_grad()


        speed_stats = {}


        time5 = time.perf_counter()


        


        iterator_stop = torch.tensor(0).to(self.device)




        dataloader_train.batch_sampler.set_epoch(epoch)


        for batch_idx, batch in enumerate(dataloader_train):


            if self.use_ddp or self.use_fsdp:


                dist.all_reduce(iterator_stop, dist.ReduceOp.SUM)


                if iterator_stop > 0:


                    break


            self.batch_total += 1


            time1 = time.perf_counter()


            speed_stats["data_load"] = f"{time1-time5:0.3f}"


@@ -290,13 +298,13 @@


                self.train_loss_avg = (self.train_loss_avg*batch_idx + loss.detach().cpu().item())/(batch_idx+1)


                if "acc" in stats:


                    self.train_acc_avg = (self.train_acc_avg * batch_idx + stats["acc"].detach().cpu().item()) / (batch_idx + 1)


                # if self.use_ddp or self.use_fsdp:


                #     train_loss_avg = torch.tensor(self.train_loss_avg, dtype=torch.float32).to(self.device)


                #     train_acc_avg = torch.tensor(self.train_acc_avg, dtype=torch.float32).to(self.device)


                #     dist.all_reduce(train_loss_avg, op=dist.ReduceOp.SUM)


                #     dist.all_reduce(train_acc_avg, op=dist.ReduceOp.SUM)


                #     self.train_loss_avg = train_loss_avg.detach().cpu().item() / self.world_size


                #     self.train_acc_avg = train_acc_avg.detach().cpu().item() / self.world_size


                if self.use_ddp or self.use_fsdp:


                    train_loss_avg = torch.tensor(self.train_loss_avg, dtype=torch.float32).to(self.device)


                    train_acc_avg = torch.tensor(self.train_acc_avg, dtype=torch.float32).to(self.device)


                    dist.all_reduce(train_loss_avg, op=dist.ReduceOp.SUM)


                    dist.all_reduce(train_acc_avg, op=dist.ReduceOp.SUM)


                    self.train_loss_avg = train_loss_avg.detach().cpu().item() / self.world_size


                    self.train_acc_avg = train_acc_avg.detach().cpu().item() / self.world_size


                


            


            # Perform an optimizer step only after accumulating enough gradients


@@ -332,7 +340,7 @@


    


                speed_stats["total_time"] = total_time


                lr = scheduler.get_last_lr()[0]


                batch_num_epoch = -1


                batch_num_epoch = 1


                if hasattr(dataloader_train, "__len__"):


                    batch_num_epoch = len(dataloader_train)


                self.log(epoch, batch_idx,


@@ -356,9 +364,14 @@


            if (batch_idx+1) % self.save_checkpoint_interval == 0:


                self.save_checkpoint(epoch, model=model, optim=optim, scheduler=scheduler, scaler=scaler, step=batch_idx+1)




        


        else:


            if self.use_ddp or self.use_fsdp:


                iterator_stop.fill_(1)


                dist.all_reduce(iterator_stop, dist.ReduceOp.SUM)


                


        if self.use_ddp or self.use_fsdp:


            dist.barrier()


            iterator_stop = torch.tensor(0).to(self.device)


        


        




@@ -376,6 +389,8 @@


        Args:


            epoch (int): The current epoch number.


        """


        if self.use_ddp or self.use_fsdp:


            dist.barrier()


        logging.info(f"Validate epoch: {epoch}, rank: {self.local_rank}\n")


        model.eval()


        


@@ -383,7 +398,13 @@


            


            speed_stats = {}


            time5 = time.perf_counter()


            iterator_stop = torch.tensor(0).to(self.device)


            dataloader_val.batch_sampler.set_epoch(epoch)


            for batch_idx, batch in enumerate(dataloader_val):


                if self.use_ddp or self.use_fsdp:


                    dist.all_reduce(iterator_stop, dist.ReduceOp.SUM)


                    if iterator_stop > 0:


                        break


                time1 = time.perf_counter()


                speed_stats["data_load"] = f"{time1 - time5:0.3f}"


                batch = to_device(batch, self.device)


@@ -397,7 +418,7 @@


                    # Apply weighted averaging for loss and stats


                    loss = (loss * weight.type(loss.dtype)).sum()


                    # if distributed, this method can also apply all_reduce()


                    stats, weight = recursive_average(stats, weight, distributed=True)


                    # stats, weight = recursive_average(stats, weight, distributed=True)


                    if self.use_ddp or self.use_fsdp:


                        dist.all_reduce(weight, op=dist.ReduceOp.SUM)


                    # Now weight is summation over all workers


@@ -412,15 +433,15 @@


                self.val_loss_avg = (self.val_loss_avg*batch_idx + loss.detach().cpu().item())/(batch_idx+1)


                if "acc" in stats:


                    self.val_acc_avg = (self.val_acc_avg * batch_idx + stats["acc"].detach().cpu().item()) / (batch_idx + 1)


                # if self.use_ddp or self.use_fsdp:


                #     val_loss_avg = torch.tensor(self.val_loss_avg, dtype=torch.float32).to(self.device)


                #     val_acc_avg = torch.tensor(self.val_acc_avg, dtype=torch.float32).to(self.device)


                #     dist.all_reduce(val_loss_avg, op=dist.ReduceOp.SUM)


                #     dist.all_reduce(val_acc_avg, op=dist.ReduceOp.SUM)


                #     self.val_loss_avg = val_loss_avg.detach().cpu().item() / self.world_size


                #     self.val_acc_avg = val_acc_avg.detach().cpu().item() / self.world_size


                if self.use_ddp or self.use_fsdp:


                    val_loss_avg = torch.tensor(self.val_loss_avg, dtype=torch.float32).to(self.device)


                    val_acc_avg = torch.tensor(self.val_acc_avg, dtype=torch.float32).to(self.device)


                    dist.all_reduce(val_loss_avg, op=dist.ReduceOp.SUM)


                    dist.all_reduce(val_acc_avg, op=dist.ReduceOp.SUM)


                    self.val_loss_avg = val_loss_avg.detach().cpu().item() / self.world_size


                    self.val_acc_avg = val_acc_avg.detach().cpu().item() / self.world_size


                


                batch_num_epoch = -1


                batch_num_epoch = 1


                if hasattr(dataloader_val, "__len__"):


                    batch_num_epoch = len(dataloader_val)


                self.log(epoch, batch_idx,


@@ -433,11 +454,17 @@


                         tag="val",


                         )




            else:


                if self.use_ddp or self.use_fsdp:


                    iterator_stop.fill_(1)


                    dist.all_reduce(iterator_stop, dist.ReduceOp.SUM)


                    


        self.val_acc_list.append(self.val_acc_avg)


        model.train()


        




        if self.use_ddp or self.use_fsdp:


            dist.barrier()


            iterator_stop = torch.tensor(0).to(self.device)


        


        


    def log(self,