joanllop commited on
Commit
32ede28
1 Parent(s): cfdd5ba

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -148,7 +148,7 @@ The adaptation procedure is explained in [this blog post](https://medium.com/@mp
148
 
149
  The training corpus consists of 26B tokens of several corpora gathered from web crawlings and public domain data.
150
 
151
- | Dataset | Language | Tokens (per-epoch) | Epochs |
152
  |---------------------|----------|--------------------|--------------|
153
  | Wikipedia | en | 2169.97M | 1.428144485 |
154
  | C4_es | es | 53709.80M | 0.1049686196 |
 
148
 
149
  The training corpus consists of 26B tokens of several corpora gathered from web crawlings and public domain data.
150
 
151
+ | Dataset | Language | Words (per-epoch) | Epochs |
152
  |---------------------|----------|--------------------|--------------|
153
  | Wikipedia | en | 2169.97M | 1.428144485 |
154
  | C4_es | es | 53709.80M | 0.1049686196 |