update examples
Former-commit-id: cce238f7d07919b79237bc9ab39265766c20f020
This commit is contained in:
@@ -7,7 +7,7 @@ do_train: true
|
||||
finetuning_type: lora
|
||||
lora_target: all
|
||||
pref_beta: 0.1
|
||||
pref_loss: sigmoid # [sigmoid (dpo), orpo, simpo]
|
||||
pref_loss: sigmoid # choices: [sigmoid (dpo), orpo, simpo]
|
||||
|
||||
### dataset
|
||||
dataset: dpo_en_demo
|
||||
|
||||
Reference in New Issue
Block a user