zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-06-26 18:51:18 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

nits

Browse Source
This commit is contained in:
Goekdeniz-Guelmez 2025-01-22 21:03:21 +01:00
parent b0ece88909
commit e1d549bcd3
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llms/mlx_lm/tuner/dpo_trainer.py
View File

@ -371,7 +371,7 @@ def train_dpo(
if rank == 0: if rank == 0:
print( print(
f"Iter {it}: " f"Iter {it}: "
f"Val loss {val_loss:.3f}, " f"Val loss {val_loss:.8f}, "
f"Val chosen reward {val_rewards[0]:.3f}, " f"Val chosen reward {val_rewards[0]:.3f}, "
f"Val rejected reward {val_rewards[1]:.3f}, " f"Val rejected reward {val_rewards[1]:.3f}, "
f"Val took {val_time:.3f}s", f"Val took {val_time:.3f}s",
@ -414,7 +414,7 @@ def train_dpo(
if rank == 0: if rank == 0:
print( print(
f"Iter {it}: Train loss {train_loss:.3f}, " f"Iter {it}: Train loss {train_loss:.8f}, "
f"Chosen reward {train_rewards[0]:.3f}, " f"Chosen reward {train_rewards[0]:.3f}, "
f"Rejected reward {train_rewards[1]:.3f}, " f"Rejected reward {train_rewards[1]:.3f}, "
f"Learning Rate {learning_rate:.3e}, " f"Learning Rate {learning_rate:.3e}, "