From bbd300a91184d09dec56a3b06734051dbd5812e4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 20 五月 2024 15:27:24 +0800
Subject: [PATCH] ds
---
funasr/train_utils/average_nbest_models.py | 4 ++--
funasr/bin/train_ds.py | 4 +++-
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/funasr/bin/train_ds.py b/funasr/bin/train_ds.py
index 03cb184..a4ae11b 100644
--- a/funasr/bin/train_ds.py
+++ b/funasr/bin/train_ds.py
@@ -198,7 +198,9 @@
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()
diff --git a/funasr/train_utils/average_nbest_models.py b/funasr/train_utils/average_nbest_models.py
index 8553baa..20da130 100644
--- a/funasr/train_utils/average_nbest_models.py
+++ b/funasr/train_utils/average_nbest_models.py
@@ -16,7 +16,7 @@
from functools import cmp_to_key
-def _get_checkpoint_paths(output_dir: str, last_n: int = 5, use_deepspeed=False):
+def _get_checkpoint_paths(output_dir: str, last_n: int = 5, use_deepspeed=False, **kwargs):
"""
Get the paths of the last 'last_n' checkpoints by parsing filenames
in the output directory.
@@ -55,7 +55,7 @@
Average the last 'last_n' checkpoints' model state_dicts.
If a tensor is of type torch.int, perform sum instead of average.
"""
- checkpoint_paths = _get_checkpoint_paths(output_dir, last_n)
+ checkpoint_paths = _get_checkpoint_paths(output_dir, last_n, **kwargs)
print(f"average_checkpoints: {checkpoint_paths}")
state_dicts = []
--
Gitblit v1.9.1