From 824377d2aae11dc9ebbde871e3b23a0e0cadc7af Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 17 四月 2024 16:59:29 +0800
Subject: [PATCH] Dev gzf exp (#1626)
---
funasr/train_utils/trainer.py | 13 +++++++++----
1 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/funasr/train_utils/trainer.py b/funasr/train_utils/trainer.py
index 35a266f..caaef38 100644
--- a/funasr/train_utils/trainer.py
+++ b/funasr/train_utils/trainer.py
@@ -268,10 +268,12 @@
# Initialize the gradient accumulation
optim.zero_grad()
speed_stats = {}
- time5 = time.perf_counter()
+
iterator_stop = torch.tensor(0).to(self.device)
dataloader_train.batch_sampler.set_epoch(epoch)
+ 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)
@@ -279,11 +281,13 @@
break
self.batch_total += 1
time1 = time.perf_counter()
- speed_stats["data_load"] = f"{time1-time5:0.3f}"
+ speed_stats["data_load"] = f"{time1-time_beg:0.3f}"
batch = to_device(batch, self.device)
-
- my_context = model.no_sync if batch_idx % accum_grad != 0 else nullcontext
+
+ my_context = nullcontext
+ if self.use_ddp or self.use_fsdp:
+ my_context = model.no_sync if batch_idx % accum_grad != 0 else my_context
with my_context():
time2 = time.perf_counter()
with maybe_autocast(self.use_fp16):
@@ -384,6 +388,7 @@
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)
+ time_beg = time.perf_counter()
else:
if self.use_ddp or self.use_fsdp:
iterator_stop.fill_(1)
--
Gitblit v1.9.1