support dpo-ftx

Former-commit-id: 86dfa04f9821556019fa777106787f73eb70b452
This commit is contained in:
hiyouga
2023-12-16 19:21:41 +08:00
parent 9f77e8b025
commit d81ad2d4bc
6 changed files with 103 additions and 25 deletions

View File

@@ -47,6 +47,8 @@ def run_dpo(
# Initialize our Trainer
trainer = CustomDPOTrainer(
beta=finetuning_args.dpo_beta,
loss_type=finetuning_args.dpo_loss,
ftx_gamma=finetuning_args.dpo_ftx,
model=model,
ref_model=ref_model,
args=training_args,