423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-17 20:30:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

[misc] fix grad ckpt func (#6916)

Browse Source
This commit is contained in:
hoshi-hiyouga
2025-02-13 00:17:18 +08:00
committed by GitHub
parent b7fd1e9c00
commit e34c3c06da
3 changed files with 17 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/llamafactory/hparams/parser.py
View File

@@ -87,9 +87,10 @@ def _parse_args(
def _set_transformers_logging() -> None:
transformers.utils.logging.set_verbosity_info()
transformers.utils.logging.enable_default_handler()
transformers.utils.logging.enable_explicit_format()
if os.getenv("LLAMAFACTORY_VERBOSITY", "INFO") in ["DEBUG", "INFO"]:
transformers.utils.logging.set_verbosity_info()
transformers.utils.logging.enable_default_handler()
transformers.utils.logging.enable_explicit_format()
def _verify_model_args(

1
src/llamafactory/model/model_utils/checkpointing.py
View File

@@ -89,6 +89,7 @@ def get_custom_gradient_checkpointing_func(gradient_checkpointing_func: Callable
for arg in args:
if torch.is_tensor(arg) and torch.is_floating_point(arg):
arg.requires_grad_(True)
break # assume the first tensor is always the hidden states
return gradient_checkpointing_func(func, *args, **kwargs)