From d80ac2fd2df4e7fb8a28acfa512bb11472b5cc99 Mon Sep 17 00:00:00 2001
From: liugz18 <57401541+liugz18@users.noreply.github.com>
Date: 星期四, 18 七月 2024 21:34:55 +0800
Subject: [PATCH] Rename 'res' in line 514 to avoid with naming conflict with line 365

---
 funasr/train_utils/trainer.py |   70 +++++++++++++++++++---------------
 1 files changed, 39 insertions(+), 31 deletions(-)

diff --git a/funasr/train_utils/trainer.py b/funasr/train_utils/trainer.py
index 33dd351..665a7af 100644
--- a/funasr/train_utils/trainer.py
+++ b/funasr/train_utils/trainer.py
@@ -85,7 +85,12 @@
         self.batch_total = 0
         self.use_fp16 = use_fp16
         self.save_checkpoint_interval = kwargs.get("save_checkpoint_interval", 5000)
-        self.validate_interval = kwargs.get("validate_interval", 5000)
+        self.validate_interval = kwargs.get("validate_interval", -1)
+        if self.validate_interval < 0:
+            self.validate_interval = self.save_checkpoint_interval
+        assert (
+            self.save_checkpoint_interval == self.validate_interval
+        ), f"save_checkpoint_interval must equal to validate_interval"
         self.keep_nbest_models = kwargs.get("keep_nbest_models", 500)
         self.avg_keep_nbest_models_type = kwargs.get("avg_keep_nbest_models_type", "acc")
         self.avg_nbest_model = kwargs.get("avg_nbest_model", 10)
@@ -357,10 +362,10 @@
         time_beg = time.perf_counter()
         time5 = time_beg
         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
+            # 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
             self.step_in_epoch += 1
             time1 = time.perf_counter()
@@ -376,11 +381,11 @@
                 with maybe_autocast(self.use_fp16):
                     retval = model(**batch)
 
-                    if (
-                        self.reset_gpu_cache
-                        and (torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024) > 70
-                    ):
-                        torch.cuda.empty_cache()
+                    # if (
+                    #     self.reset_gpu_cache
+                    #     and (torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024) > 70
+                    # ):
+                    #     torch.cuda.empty_cache()
 
                 loss, stats, weight = retval
                 stats = {k: v for k, v in stats.items() if v is not None}
@@ -410,24 +415,14 @@
                 speed_stats["backward_and_AllReaduce_time"] = f"{time4 - time3:0.3f}"
 
                 self.train_loss_avg = (
-                    self.train_loss_avg * (self.step_in_epoch - 1) + loss.detach().cpu().item()
-                ) / self.step_in_epoch
+                    self.train_loss_avg * (batch_idx + kwargs.get("start_step", 0))
+                    + loss.detach().cpu().item()
+                ) / (batch_idx + kwargs.get("start_step", 0) + 1)
                 if "acc" in stats:
                     self.train_acc_avg = (
-                        self.train_acc_avg * (self.step_in_epoch - 1)
+                        self.train_acc_avg * (batch_idx + kwargs.get("start_step", 0))
                         + stats["acc"].detach().cpu().item()
-                    ) / self.step_in_epoch
-                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
+                    ) / (batch_idx + kwargs.get("start_step", 0) + 1)
 
             # Perform an optimizer step only after accumulating enough gradients
             if (batch_idx + 1) % accum_grad == 0:
@@ -456,6 +451,19 @@
                 scheduler.step()
                 # Clear gradients for the next accumulation stage
                 optim.zero_grad(set_to_none=True)
+
+                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
+
                 total_time = f"{(time.perf_counter() - time5)/accum_grad:0.3f}"
                 time5 = time.perf_counter()
 
@@ -473,7 +481,7 @@
                     step_in_epoch=self.step_in_epoch,
                     batch_num_epoch=batch_num_epoch,
                     lr=lr,
-                    loss=loss.detach().cpu().item(),
+                    loss=accum_grad * loss.detach().cpu().item(),
                     speed_stats=speed_stats,
                     stats=stats,
                     writer=writer,
@@ -508,14 +516,14 @@
                 )
 
             time_beg = time.perf_counter()
-        else:
-            if self.use_ddp or self.use_fsdp:
-                iterator_stop.fill_(1)
-                dist.all_reduce(iterator_stop, dist.ReduceOp.SUM)
+        # 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)
+            # iterator_stop = torch.tensor(0).to(self.device)
 
     def validate_epoch(
         self,

--
Gitblit v1.9.1