Skip to content

Commit

Permalink
nash
Browse files Browse the repository at this point in the history
  • Loading branch information
qgallouedec committed Dec 21, 2024
1 parent 9b7764e commit 3a89ee1
Showing 1 changed file with 8 additions and 1 deletion.
9 changes: 8 additions & 1 deletion trl/trainer/nash_md_config.py
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,14 @@ class NashMDConfig(OnlineDPOConfig):
epochs.
"""

mixture_coef: list[float] = field(default_factory=lambda: [0.5])
mixture_coef: list[float] = field(
default_factory=lambda: [0.5],
metadata={
"help": "Logit mixture coefficient for the model and reference model. If a list of floats is provided "
"then the mixture coefficient is selected for each new epoch and the last coefficient is used for the "
"rest of the epochs."
},
)

def __post_init__(self):
super().__post_init__()
Expand Down

0 comments on commit 3a89ee1

Please sign in to comment.