Raincleared commited on
Commit
4b55046
1 Parent(s): 178909c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -64,8 +64,8 @@ The 7B model is trained on 8 A100 GPUs. The learning rate (LR) is controlled by
64
  | 1 | \\(5e-3\\) | 6,000 | 12.58 |
65
  | 2 | \\(5e-2\\) | 10,000 | 20.97 |
66
  | 3 | \\(5e-2\\) | 12,000 | 25.17 |
67
- | 4 | \\(5e-1\\) | 16,000 | 33.55 |
68
- | 5 | \\(5e-1\\) | 16,500 | 34.60 |
69
 
70
  ### Evaluation Results
71
 
 
64
  | 1 | \\(5e-3\\) | 6,000 | 12.58 |
65
  | 2 | \\(5e-2\\) | 10,000 | 20.97 |
66
  | 3 | \\(5e-2\\) | 12,000 | 25.17 |
67
+ | 4 | \\(2e-1\\) | 16,000 | 33.55 |
68
+ | 5 | \\(2e-1\\) | 16,500 | 34.60 |
69
 
70
  ### Evaluation Results
71