github
/
ColossalAI
mirror of https://github.com/hpcaitech/ColossalAI
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

fixed model saving bugs

pull/3905/head
Maruyama_Aya 2023-06-06 16:07:34 +08:00
parent b29e1f0722
commit d3379f0be7
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/images/dreambooth/train_dreambooth_colossalai.py
View File

@ -667,9 +667,9 @@ def main(args):
if global_step % args.save_steps == 0:
torch.cuda.synchronize()
save_path = os.path.join(args.output_dir, f"checkpoint-{global_step}")
booster.save_model(unet, os.path.join(save_path, "diffusion_pytorch_model.bin"))
if local_rank == 0:
save_path = os.path.join(args.output_dir, f"checkpoint-{global_step}")
booster.save_model(unet, os.path.join(save_path, "diffusion_pytorch_model.bin"))
if not os.path.exists(os.path.join(save_path, "config.json")):
shutil.copy(os.path.join(args.pretrained_model_name_or_path, "unet/config.json"), save_path)
logger.info(f"Saving model checkpoint to {save_path}", ranks=[0])

4
examples/images/dreambooth/train_dreambooth_colossalai_lora.py
View File

@ -693,9 +693,9 @@ def main(args):
if global_step % args.save_steps == 0:
torch.cuda.synchronize()
save_path = os.path.join(args.output_dir, f"checkpoint-{global_step}")
booster.save_model(unet, os.path.join(save_path, "diffusion_pytorch_model.bin"))
if local_rank == 0:
save_path = os.path.join(args.output_dir, f"checkpoint-{global_step}")
booster.save_model(unet, os.path.join(save_path, "diffusion_pytorch_model.bin"))
if not os.path.exists(os.path.join(save_path, "config.json")):
shutil.copy(os.path.join(args.pretrained_model_name_or_path, "unet/config.json"), save_path)
logger.info(f"Saving model checkpoint to {save_path}", ranks=[0])