Guanzheng commited on
Commit
9c8b836
·
verified ·
1 Parent(s): 70f9f78

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -140,8 +140,8 @@ train/train_longpo.py \
140
  | Qwen2.5-7B-LongPO-128K | 95.82 | 89.71 | 78.67 | 59.40 | 87.11 |
141
  | Mistral-7B-Instruct-v0.2 | 72.60 | 74.40 | 64.40 | 52.20 | 68.40 |
142
  | Mistral-7B-LongPO-128K | 96.88 | 96.49 | 71.55 | 64.81 | 88.02 |
143
- | Mistral-7B-LongPO-256K | 96.80 | 97.00 | 69.14 | 64.87 | 87.65 |
144
- | Mistral-7B-LongPO-512K | 97.28 | 97.48 | 69.22 | 64.92 | 88.00 |
145
 
146
 
147
 
@@ -151,7 +151,7 @@ train/train_longpo.py \
151
 
152
  | Model | MMLU | ARC-C | Hellaswag | Winogrande | Avg |
153
  |-------|-------|--------|------------|-------------|-----|
154
- | Mistral-7B-Instruction-v0.2 | 59.15 | 59.26 | 83.2 | 78.4 | 70.00 |
155
  | Mistral-7B-LongPO-128K | 59.99 | 59.34 | 82.99 | 78.53 | 70.21 |
156
  | Mistral-7B-LongPO-256K-EXP | 59.47 | 60.28 | 83.14 | 78.14 | 70.26 |
157
  | Mistral-7B-LongPO-512K-EXP | 59.51 | 60.58 | 82.87 | 77.66 | 70.16 |
 
140
  | Qwen2.5-7B-LongPO-128K | 95.82 | 89.71 | 78.67 | 59.40 | 87.11 |
141
  | Mistral-7B-Instruct-v0.2 | 72.60 | 74.40 | 64.40 | 52.20 | 68.40 |
142
  | Mistral-7B-LongPO-128K | 96.88 | 96.49 | 71.55 | 64.81 | 88.02 |
143
+ | Mistral-7B-LongPO-256K-EXP | 96.80 | 97.00 | 69.14 | 64.87 | 87.65 |
144
+ | Mistral-7B-LongPO-512K-EXP | 97.28 | 97.48 | 69.22 | 64.92 | 88.00 |
145
 
146
 
147
 
 
151
 
152
  | Model | MMLU | ARC-C | Hellaswag | Winogrande | Avg |
153
  |-------|-------|--------|------------|-------------|-----|
154
+ | Mistral-7B-Instruct-v0.2 | 59.15 | 59.26 | 83.2 | 78.4 | 70.00 |
155
  | Mistral-7B-LongPO-128K | 59.99 | 59.34 | 82.99 | 78.53 | 70.21 |
156
  | Mistral-7B-LongPO-256K-EXP | 59.47 | 60.28 | 83.14 | 78.14 | 70.26 |
157
  | Mistral-7B-LongPO-512K-EXP | 59.51 | 60.58 | 82.87 | 77.66 | 70.16 |