Update README.md
Browse files
README.md
CHANGED
|
@@ -30,6 +30,9 @@ over sequences. This specific model is trained on a batch of about 500 span-labe
|
|
| 30 |
|
| 31 |
This is version was trained with context windows of 128 tokens. For the chunking we used a paragraph-based splitter.
|
| 32 |
|
|
|
|
|
|
|
|
|
|
| 33 |
### Expected input and output
|
| 34 |
The input should be a string with **Dutch** clinical text related to **cardiology**.
|
| 35 |
|
|
|
|
| 30 |
|
| 31 |
This is version was trained with context windows of 128 tokens. For the chunking we used a paragraph-based splitter.
|
| 32 |
|
| 33 |
+
The training was performed with 10 fold CV, with weight averaging of the best epochs per fold.
|
| 34 |
+
|
| 35 |
+
|
| 36 |
### Expected input and output
|
| 37 |
The input should be a string with **Dutch** clinical text related to **cardiology**.
|
| 38 |
|