update model card README.md

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on the germanquad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5561
+- Loss: 2.5837
 
 ## Model description
 
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.9185        | 1.0   | 540  | 1.5012          |
-| 1.668         | 2.0   | 1080 | 1.4047          |
-| 1.119         | 3.0   | 1620 | 1.6239          |
-| 0.7685        | 4.0   | 2160 | 1.9753          |
-| 0.5211        | 5.0   | 2700 | 1.9515          |
-| 0.3593        | 6.0   | 3240 | 2.2319          |
-| 0.2462        | 7.0   | 3780 | 2.3495          |
-| 0.1858        | 8.0   | 4320 | 2.4836          |
-| 0.1338        | 9.0   | 4860 | 2.5154          |
-| 0.1056        | 10.0  | 5400 | 2.5561          |
+| No log        | 1.0   | 360  | 1.7190          |
+| 2.7136        | 2.0   | 720  | 1.6624          |
+| 1.3704        | 3.0   | 1080 | 1.6460          |
+| 1.3704        | 4.0   | 1440 | 1.9336          |
+| 0.7467        | 5.0   | 1800 | 2.0047          |
+| 0.4077        | 6.0   | 2160 | 2.1701          |
+| 0.2468        | 7.0   | 2520 | 2.3223          |
+| 0.2468        | 8.0   | 2880 | 2.4638          |
+| 0.1475        | 9.0   | 3240 | 2.5493          |
+| 0.1023        | 10.0  | 3600 | 2.5837          |
 
 
 ### Framework versions