Update README.md

README.md

@@ -24,19 +24,22 @@ Moreover, we provide a [detailed recipe](https://github.com/RLHFlow/Online-DPO-R
 ## Training methods
 - Iterative DPO: Following the RLHF Workflow framework (https://arxiv.org/pdf/2405.07863), in each iteration, we sample multiple responses from the last trained policy, rank them via the ruled-based reward, and construct the preference pairs.
   Then, we optimize the policy by minimizing the DPO loss and enter the next iteration.
-  Online iterative DPO can mitigate the issue of distribution shift and the limited coverage of offline data effectively.
-  More detailed can be found in our [blog](https://www.notion.so/Online-DPO-R1-1908b9a70e7b80c3bc83f4cf04b2f175)! 
+  Online iterative DPO can mitigate the issue of distribution shift and the limited coverage of offline data effectively
+- Before the DPO training, we add SFT Warm-up procedure for the base model, which is fine-tuned from [RLHFlow/qwq_gen_sft_15k](https://huggingface.co/datasets/RLHFlow/qwq_gen_sft_15k).
+
+More detailed can be found in our [blog](https://www.notion.so/Online-DPO-R1-1908b9a70e7b80c3bc83f4cf04b2f175)! 
 
 
 ## Performance
 | **Model**                  | **AIME 2024** | **MATH 500** | **AMC** | **Minerva Math** | **OlympiadBench** | **Average** |
 |----------------------------|---------------|--------------|---------|------------------|-------------------|-------------|
 | **Ours**                   |            |           |            |          |               |              |
-| RLHFlow/Qwen2.5-7B-PPO-Zero        | 43.3 **(+26.6)**       | 79.4 **(+27.0)**      | 62.5 **(+10.0)**      | 33.1 **(+20.2)**    | 40.7 **(+24.3)**   | 51.8 **(+21.6)** |
-| RLHFlow/Qwen2.5-7B-DPO-Zero        | 26.8 **(+10.1)**       | 76.8 **(+24.4)**     | 62.5 **(+10.0)**       | 30.9 **(+18.0)**    | 37.9 **(+21.5)**   | 47.0 **(+16.8)** |
-| RLHFlow/Qwen2.5-7B-RAFT-Zero       | 20.0 **(+3.3)**       | 77.6 **(+25.2)**     | 55.0 **(+2.5)**         | 30.5 **(+17.6)**    | 38.7 **(+22.3)**   | 44.4 **(+14.2)** |
+| RLHFlow/Qwen2.5-7B-PPO-Zero        | **43.3 (+26.6)**   | 79.4 (+27.0)      | **62.5 (+10.0)**      | 33.1   (+20.2)      | 40.7   (+24.3)     | **51.8 (+21.6)** |
+| RLHFlow/Qwen2.5-7B-DPO-Zero        | 30.0 (+13.3)       | **84.4 (+32.0)**  | **62.5 (+10.0)**      | **33.5 (+20.6)**    | **48.4 (+32.0)**   | **51.8 (+21.6)** |
+| RLHFlow/Qwen2.5-7B-RAFT-Zero       | 20.0 (+3.3)        | 77.6 (+25.2)      | 55.0 (+2.5)           | 30.5   (+17.6)      | 38.7   (+22.3)     | 44.4   (+14.2)   |
 | **Baselines**             |            |           |            |          |               |              |
 | Qwen2.5-Math-7B-Base       | 16.7       | 52.4      | 52.5       | 12.9     | 16.4          | 30.2         |
+| Qwen2.5-Math-7B-Base + SFT Warm-up | 20.0       | 73.2      | 62.5       | 30.5     | 35.6          | 44.4         |
 | Qwen-2.5-Math-7B-Instruct  | 13.3       | 79.8      | 50.6       | 34.6     | 40.7          | 43.8         |
 | Llama-3.1-70B-Instruct     | 16.7       | 64.6      | 30.1       | 35.3     | 31.9          | 35.7         |
 | Eurus-2-7B-PRIME           | 26.7       | 79.2      | 57.8       | 38.6     | 42.1          | 48.9         |
@@ -49,5 +52,3 @@ Moreover, we provide a [detailed recipe](https://github.com/RLHFlow/Online-DPO-R
 
 ## Citation
 
-
-