Commit
•
a13a231
1
Parent(s):
757067f
Update README.md
Browse files
README.md
CHANGED
|
@@ -46,3 +46,12 @@ The preprocessing of the data included:
|
|
| 46 |
|
| 47 |
We advice to perform the same preprocessing steps when working with the mode.
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
We advice to perform the same preprocessing steps when working with the mode.
|
| 48 |
|
| 49 |
+
## Training
|
| 50 |
+
|
| 51 |
+
After multiple test runs of finetuning the present model was further trained using the following parameters:
|
| 52 |
+
- foundation_model: [german-gpt2](https://huggingface.co/dbmdz/german-gpt2)
|
| 53 |
+
- num_train_epochs: 4
|
| 54 |
+
- learning_rate: 2e-7
|
| 55 |
+
- weight_decay: 0.1
|
| 56 |
+
- metric_for_best_model: precision
|
| 57 |
+
|