diff --git a/experiment_effect_of_dpo/README.md b/experiment_effect_of_dpo/README.md
new file mode 100644
index 0000000..951e37d
--- /dev/null
+++ b/experiment_effect_of_dpo/README.md
@@ -0,0 +1,19 @@
+## Train DPO
+
+```bash
+002-001-dpo-temp-0_3-v-all-ref.sh
+```
+
+### Configuration
+
+- BASE_MODEL: Name of Model for save.
+- DATA_PATH: Dataset Path.
+- EPOCH: Num Train Epoch.
+- LR: 2e-5 for full finetune and 2e-4 for lora.
+- GRADIENT_ACCUMULATION_STEPS: Accumulation step.
+- MAX_LEN: Max training length.
+- MAX_PROMPT_LEN: Max training prompt length.
+- MICRO_BSZ: Batch size per step.
+- VAL_SIZE: Split validation set.
+- WANDB_NAME: Wandb project name.
+- WARMUP_STEPS: Warmup step for scheduler.
\ No newline at end of file