diff --git a/src/autotrain/__init__.py b/src/autotrain/__init__.py index 15bf731d86..bc3d902522 100644 --- a/src/autotrain/__init__.py +++ b/src/autotrain/__init__.py @@ -30,4 +30,4 @@ warnings.filterwarnings("ignore", category=UserWarning, module="tensorflow") -__version__ = "0.6.36.dev0" +__version__ = "0.6.37.dev0" diff --git a/src/autotrain/trainers/clm/params.py b/src/autotrain/trainers/clm/params.py index 8e61015266..40ff5b0db6 100644 --- a/src/autotrain/trainers/clm/params.py +++ b/src/autotrain/trainers/clm/params.py @@ -46,7 +46,7 @@ class LLMTrainingParams(BaseModel): merge_adapter: bool = Field(False, title="Merge adapter") username: str = Field(None, title="Hugging Face Username") use_flash_attention_2: bool = Field(False, title="Use flash attention 2") - disable_gradient_checkpointing: bool = Field(True, title="Gradient checkpointing") + disable_gradient_checkpointing: bool = Field(False, title="Gradient checkpointing") def save(self, output_dir): os.makedirs(output_dir, exist_ok=True)