Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,10 @@ Non-embedding parameters: 10,844,160
|
|
| 14 |
|
| 15 |
Vocabulary size: 50,257
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
Total train tokens: 136,000,000
|
| 18 |
|
| 19 |
Epochs: 2
|
|
|
|
| 14 |
|
| 15 |
Vocabulary size: 50,257
|
| 16 |
|
| 17 |
+
Compute: single T4 GPU
|
| 18 |
+
|
| 19 |
+
Total train time: 2 hours and 40 minutes
|
| 20 |
+
|
| 21 |
Total train tokens: 136,000,000
|
| 22 |
|
| 23 |
Epochs: 2
|