Safetensors
qwen2
yuchenFan commited on
Commit
e078587
·
verified ·
1 Parent(s): dcc3dcc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md CHANGED
@@ -179,8 +179,23 @@ We use Best-of-64 as our evaluation metric. The weighting methods are different
179
  | | EurusPRM-Stage 1 | 82.6 | 53.0 | 16.7 | 42.7 | 45.2 | 48.0 |
180
  | | EurusPRM-Stage 2 | 84.8 | 53.0 | 16.7 | 43.2 | **45.6** | 48.7 |
181
 
 
182
 
 
 
 
183
 
 
 
 
 
 
 
 
 
 
 
 
184
  ## Citation
185
 
186
  ```latex
 
179
  | | EurusPRM-Stage 1 | 82.6 | 53.0 | 16.7 | 42.7 | 45.2 | 48.0 |
180
  | | EurusPRM-Stage 2 | 84.8 | 53.0 | 16.7 | 43.2 | **45.6** | 48.7 |
181
 
182
+ ### ProcessBench
183
 
184
+ We evaluate **EurusPRM-Stage 1** and **EurusPRM-Stage 2** on **ProcessBench**.
185
+ The threshold is obtained by converting the original score of each step using sigmoid function and iterating to find the highest F1 on GSM8k sub-benchmark. The threshold for **EurusPRM-Stage 1** and **EurusPRM-Stage 2** is 0.5015 and 0.5005 respectively.
186
+ For leveraging the capibility of **EurusPRM** better, we add ``Step K`` (where K is the actual index of the step) in front of each step in **ProcessBench**.
187
 
188
+ | Reward Model | GSM8k | MATH | OlympiadBench | Omni-Math | Avg |
189
+ | --- | --- | --- | --- | --- | --- | --- | --- |
190
+ | Math-Shepherd-PRM-7B | 47.9 | 29.5 | 24.8 | 23.8 | 31.5 |
191
+ | RLHFlow-PRM-Mistral-8B | 50.4 | 33.4 | 13.8 | 15.8 | 28.4 |
192
+ | RLHFlow-PRM-Deepseek-8B | 38.8 | 33.8 | 16.9 | 16.9 | 26.6 |
193
+ | Skywork-PRM-7B | **70.8** | **53.6** | 22.9 | 21.0 | 42.1 |
194
+ | EurusPRM-Stage 1 | 54.7 | 41.2 | 24.7 | 17.5 | 30.6 |
195
+ | EurusPRM-Stage 1-no-step | 42.1 | 33.1 | 13.2 | 15.4 | 23.1 |
196
+ | EurusPRM-Stage 2 | 67.0 | 53.2 | **35.4** | **30.7** | **42.8** |
197
+ | EurusPRM-Stage 2-no-step | 56.6 | 43.0 | 27.3 | 26.8 | 35.1 |
198
+
199
  ## Citation
200
 
201
  ```latex