From 710642827abeeab4e4b2c8596f212cff115248ca Mon Sep 17 00:00:00 2001 From: hiyouga <467089858@qq.com> Date: Mon, 27 May 2024 19:56:04 +0800 Subject: [PATCH] update dpo examples Former-commit-id: 30e1c8e7450a68ccabede245cbc09b416ef7a94d --- examples/lora_single_gpu/llama3_lora_dpo.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/examples/lora_single_gpu/llama3_lora_dpo.yaml b/examples/lora_single_gpu/llama3_lora_dpo.yaml index 958be1b5..f68244b7 100644 --- a/examples/lora_single_gpu/llama3_lora_dpo.yaml +++ b/examples/lora_single_gpu/llama3_lora_dpo.yaml @@ -6,6 +6,7 @@ stage: dpo do_train: true finetuning_type: lora lora_target: q_proj,v_proj +pref_beta: 0.1 pref_loss: sigmoid # [sigmoid (dpo), orpo, simpo] ### dataset