End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dbmdz/bert-base-german-uncased](https://huggingface.co/dbmdz/bert-base-german-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6526
-- F1: 0.5455
+- Loss: 0.5959
+- F1: 0.4516
 
 ## Model description
 
@@ -49,16 +49,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.6879        | 1.0   | 201  | 0.6506          | 0.0    |
-| 0.6396        | 2.0   | 402  | 0.5948          | 0.3837 |
-| 0.54          | 3.0   | 603  | 0.5328          | 0.5714 |
-| 0.478         | 4.0   | 804  | 0.5224          | 0.4878 |
-| 0.4685        | 5.0   | 1005 | 0.5577          | 0.5556 |
-| 0.455         | 6.0   | 1206 | 0.5599          | 0.5    |
-| 0.4088        | 7.0   | 1407 | 0.6082          | 0.5435 |
-| 0.44          | 8.0   | 1608 | 0.6557          | 0.5476 |
-| 0.4256        | 9.0   | 1809 | 0.6618          | 0.5476 |
-| 0.4431        | 10.0  | 2010 | 0.6526          | 0.5455 |
+| 0.6742        | 1.0   | 189  | 0.6543          | 0.0    |
+| 0.6716        | 2.0   | 378  | 0.6124          | 0.0571 |
+| 0.6364        | 3.0   | 567  | 0.6232          | 0.0556 |
+| 0.6251        | 4.0   | 756  | 0.6286          | 0.2    |
+| 0.6361        | 5.0   | 945  | 0.5809          | 0.3529 |
+| 0.5249        | 6.0   | 1134 | 0.6455          | 0.3404 |
+| 0.5637        | 7.0   | 1323 | 0.5644          | 0.4444 |
+| 0.4638        | 8.0   | 1512 | 0.5942          | 0.4333 |
+| 0.4961        | 9.0   | 1701 | 0.5980          | 0.4333 |
+| 0.4892        | 10.0  | 1890 | 0.5959          | 0.4516 |
 
 
 ### Framework versions