From f97f3e8dd5b40be6faaccd9c089aea52ceba29ef Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 13 六月 2024 09:52:10 +0800
Subject: [PATCH] decoding
---
funasr/bin/train_ds.py | 62 ++++++++++--------------------
1 files changed, 21 insertions(+), 41 deletions(-)
diff --git a/funasr/bin/train_ds.py b/funasr/bin/train_ds.py
index e4db533..da99adc 100644
--- a/funasr/bin/train_ds.py
+++ b/funasr/bin/train_ds.py
@@ -66,7 +66,6 @@
# open tf32
torch.backends.cuda.matmul.allow_tf32 = kwargs.get("enable_tf32", True)
- rank = int(os.environ.get("RANK", 0))
local_rank = int(os.environ.get("LOCAL_RANK", 0))
world_size = int(os.environ.get("WORLD_SIZE", 1))
@@ -83,6 +82,8 @@
logging.info(f"use_ddp: {use_ddp}, use_fsdp: {use_fsdp}")
dist.init_process_group(backend=kwargs.get("backend", "nccl"), init_method="env://")
torch.cuda.set_device(local_rank)
+
+ rank = dist.get_rank()
logging.info("Build model, frontend, tokenizer")
device = kwargs.get("device", "cuda")
@@ -124,38 +125,17 @@
use_ddp=use_ddp,
use_fsdp=use_fsdp,
device=kwargs["device"],
+ excludes=kwargs.get("excludes", None),
output_dir=kwargs.get("output_dir", "./exp"),
**kwargs.get("train_conf"),
)
model = trainer.warp_model(model)
- kwargs["device"] = next(model.parameters()).device
- trainer.device = kwargs["device"]
+ kwargs["device"] = int(os.environ.get("LOCAL_RANK", 0))
+ trainer.device = int(os.environ.get("LOCAL_RANK", 0))
- # optim
- logging.info("Build optim")
- optim = kwargs.get("optim", "adam")
- assert optim in optim_classes
- optim_class = optim_classes.get(optim)
- optim = optim_class(model.parameters(), **kwargs.get("optim_conf"))
-
- # scheduler
- logging.info("Build scheduler")
- scheduler = kwargs.get("scheduler", "warmuplr")
- assert scheduler in scheduler_classes
- scheduler_class = scheduler_classes.get(scheduler)
- scheduler = scheduler_class(optim, **kwargs.get("scheduler_conf"))
-
- if use_deepspeed:
- args = OmegaConf.create({"deepspeed_config": kwargs.get("deepspeed_config", "")})
- model, optimizer, _, scheduler = deepspeed.initialize(
- args=args,
- model=model,
- optimizer=optim,
- lr_scheduler=scheduler,
- model_parameters=model.parameters(),
- )
+ model, optim, scheduler = trainer.warp_optim_scheduler(model, **kwargs)
# dataset
logging.info("Build dataloader")
@@ -175,20 +155,13 @@
scaler=scaler,
)
- tensorboard_dir = os.path.join(kwargs.get("output_dir"), "tensorboard")
- os.makedirs(tensorboard_dir, exist_ok=True)
- try:
- from tensorboardX import SummaryWriter
-
- writer = SummaryWriter(tensorboard_dir) # if trainer.rank == 0 else None
- except:
- writer = None
-
dataloader_tr, dataloader_val = None, None
for epoch in range(trainer.start_epoch, trainer.max_epoch):
time1 = time.perf_counter()
for data_split_i in range(trainer.start_data_split_i, dataloader.data_split_num):
+ time_slice_i = time.perf_counter()
+
dataloader_tr, dataloader_val = dataloader.build_iter(
epoch, data_split_i=data_split_i, start_step=trainer.start_step
)
@@ -201,7 +174,6 @@
dataloader_train=dataloader_tr,
dataloader_val=dataloader_val,
epoch=epoch,
- writer=writer,
data_split_i=data_split_i,
data_split_num=dataloader.data_split_num,
start_step=trainer.start_step,
@@ -210,10 +182,16 @@
torch.cuda.empty_cache()
+ time_escaped = (time.perf_counter() - time_slice_i) / 3600.0
+ logging.info(
+ f"\n\nrank: {local_rank}, "
+ f"time_escaped_epoch: {time_escaped:.3f} hours, "
+ f"estimated to finish {dataloader.data_split_num} data_slices, remaining: {dataloader.data_split_num-data_split_i} slices, {(dataloader.data_split_num-data_split_i)*time_escaped:.3f} hours, "
+ f"epoch: {trainer.max_epoch - epoch} epochs, {((trainer.max_epoch - epoch - 1)*dataloader.data_split_num + dataloader.data_split_num-data_split_i)*time_escaped:.3f} hours\n"
+ )
+
trainer.start_data_split_i = 0
- trainer.validate_epoch(
- model=model, dataloader_val=dataloader_val, epoch=epoch + 1, writer=writer
- )
+ trainer.validate_epoch(model=model, dataloader_val=dataloader_val, epoch=epoch + 1)
scheduler.step()
trainer.step_in_epoch = 0
trainer.save_checkpoint(
@@ -223,7 +201,7 @@
time2 = time.perf_counter()
time_escaped = (time2 - time1) / 3600.0
logging.info(
- f"rank: {local_rank}, "
+ f"\n\nrank: {local_rank}, "
f"time_escaped_epoch: {time_escaped:.3f} hours, "
f"estimated to finish {trainer.max_epoch} "
f"epoch: {(trainer.max_epoch - epoch) * time_escaped:.3f} hours\n"
@@ -232,7 +210,9 @@
trainer.train_loss_avg = 0.0
if trainer.rank == 0:
- average_checkpoints(trainer.output_dir, trainer.avg_nbest_model)
+ average_checkpoints(
+ trainer.output_dir, trainer.avg_nbest_model, use_deepspeed=trainer.use_deepspeed
+ )
trainer.close()
--
Gitblit v1.9.1