github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-06-23 14:10:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #6029 from hpcaitech/flybird11111-patch-1

Browse Source 
Update train_dpo.py
This commit is contained in:
Wang Binluo 2024-08-23 13:50:04 +08:00 committed by GitHub
commit 0bf46c54af
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
applications/ColossalChat/examples/training_scripts/train_dpo.py
View File

@ -279,10 +279,7 @@ def train(args):
beta=args.beta, beta=args.beta,
gamma=args.gamma, gamma=args.gamma,
length_normalization=args.length_normalization, length_normalization=args.length_normalization,
<<<<<<< HEAD
=======
apply_loss_mask=not args.disable_loss_mask, apply_loss_mask=not args.disable_loss_mask,
>>>>>>> main
) )
trainer.fit( trainer.fit(
@ -351,10 +348,7 @@ if __name__ == "__main__":
default=False, default=False,
help="Disable the reference model (enabled by default)", help="Disable the reference model (enabled by default)",
) )
<<<<<<< HEAD
=======
parser.add_argument("--disable_loss_mask", default=False, action="store_true") parser.add_argument("--disable_loss_mask", default=False, action="store_true")
>>>>>>> main
parser.add_argument("--mixed_precision", type=str, default="fp16", choices=["fp16", "bf16"], help="Mixed precision") parser.add_argument("--mixed_precision", type=str, default="fp16", choices=["fp16", "bf16"], help="Mixed precision")
parser.add_argument("--lora_config", type=str, default=None, help="low-rank adaptation config file path") parser.add_argument("--lora_config", type=str, default=None, help="low-rank adaptation config file path")
parser.add_argument("--save_interval", type=int, default=1000, help="number of step between two checkpoints") parser.add_argument("--save_interval", type=int, default=1000, help="number of step between two checkpoints")