irodkin commited on
Commit
3b6eb34
1 Parent(s): 16cd842

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -9,8 +9,7 @@ metrics:
9
  - cross_entropy
10
  ---
11
 
12
- **(!) _Don't forget to preprocess unknown_tokens and substitute them with <|endoftext|>_**
13
-
14
  **Dependence of the cross entropy loss on the length of the context for prediction**
15
 
16
  - x-axis*128 = context length
 
9
  - cross_entropy
10
  ---
11
 
12
+ **(!) _Don't forget to preprocess unknown_tokens and substitute them with <|endoftext|>. Otherwise the <unk> tokens in dataset will be split into the '<', 'unk' and '>' tokens_**
 
13
  **Dependence of the cross entropy loss on the length of the context for prediction**
14
 
15
  - x-axis*128 = context length