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 [deepset/gelectra-base-germanquad](https://huggingface.co/deepset/gelectra-base-germanquad) on the germanquad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5866
+- Loss: 2.6043
 
 ## Model description
 
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.2613        | 1.0   | 540  | 1.8150          |
-| 0.969         | 2.0   | 1080 | 1.8128          |
-| 0.8194        | 3.0   | 1620 | 2.0897          |
-| 0.6854        | 4.0   | 2160 | 2.2031          |
-| 0.6044        | 5.0   | 2700 | 2.3345          |
-| 0.5342        | 6.0   | 3240 | 2.4783          |
-| 0.4718        | 7.0   | 3780 | 2.4594          |
-| 0.432         | 8.0   | 4320 | 2.5480          |
-| 0.4           | 9.0   | 4860 | 2.5750          |
-| 0.3786        | 10.0  | 5400 | 2.5866          |
+| No log        | 1.0   | 360  | 1.6870          |
+| 1.1915        | 2.0   | 720  | 1.9285          |
+| 0.8811        | 3.0   | 1080 | 2.0828          |
+| 0.8811        | 4.0   | 1440 | 2.3544          |
+| 0.679         | 5.0   | 1800 | 2.2105          |
+| 0.5464        | 6.0   | 2160 | 2.3901          |
+| 0.4672        | 7.0   | 2520 | 2.5754          |
+| 0.4672        | 8.0   | 2880 | 2.5976          |
+| 0.4012        | 9.0   | 3240 | 2.5547          |
+| 0.3752        | 10.0  | 3600 | 2.6043          |
 
 
 ### Framework versions