Update README.md
Browse files
README.md
CHANGED
|
@@ -37,7 +37,7 @@ This is the 26 categorical finetune of nomic-bert-2048's encoder.
|
|
| 37 |
|
| 38 |
The final accuracy is about 95% give or take, but it's also comparing against the actual pretrained data. The point being it needs to associate information with information more cleanly, rather than fully enforcing the various logistical and subjective elements instantiated from external elements.
|
| 39 |
|
| 40 |
-
Total samples;
|
| 41 |
|
| 42 |
The model has learned to categorize certain masked patterns with their categories and special tokens.
|
| 43 |
|
|
|
|
| 37 |
|
| 38 |
The final accuracy is about 95% give or take, but it's also comparing against the actual pretrained data. The point being it needs to associate information with information more cleanly, rather than fully enforcing the various logistical and subjective elements instantiated from external elements.
|
| 39 |
|
| 40 |
+
Total samples; 2,056,192,000
|
| 41 |
|
| 42 |
The model has learned to categorize certain masked patterns with their categories and special tokens.
|
| 43 |
|