update model card README.md

README.md

@@ -19,11 +19,11 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0458
-- Precision: 0.8304
-- Recall: 0.7099
-- F1: 0.7654
-- Accuracy: 0.9881
+- Loss: 0.0651
+- Precision: 0.5643
+- Recall: 0.8464
+- F1: 0.6771
+- Accuracy: 0.9847
 
 ## Model description
 
@@ -42,24 +42,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 32
-- eval_batch_size: 32
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 8
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 36   | 0.0477          | 0.8247    | 0.6107 | 0.7018 | 0.9854   |
-| No log        | 2.0   | 72   | 0.0444          | 0.8235    | 0.6412 | 0.7210 | 0.9869   |
-| No log        | 3.0   | 108  | 0.0443          | 0.8426    | 0.6947 | 0.7615 | 0.9869   |
-| No log        | 4.0   | 144  | 0.0392          | 0.8942    | 0.7099 | 0.7915 | 0.9896   |
-| No log        | 5.0   | 180  | 0.0445          | 0.8070    | 0.7023 | 0.7510 | 0.9877   |
-| No log        | 6.0   | 216  | 0.0458          | 0.8304    | 0.7099 | 0.7654 | 0.9881   |
+| No log        | 1.0   | 160  | 0.0566          | 0.5288    | 0.8536 | 0.6530 | 0.9809   |
+| No log        | 2.0   | 320  | 0.0385          | 0.7811    | 0.8286 | 0.8042 | 0.9917   |
+| No log        | 3.0   | 480  | 0.0380          | 0.7867    | 0.8429 | 0.8138 | 0.9920   |
+| 0.0599        | 4.0   | 640  | 0.0473          | 0.7476    | 0.8464 | 0.7940 | 0.9907   |
+| 0.0599        | 5.0   | 800  | 0.0566          | 0.5939    | 0.8357 | 0.6944 | 0.9861   |
+| 0.0599        | 6.0   | 960  | 0.0562          | 0.6466    | 0.8429 | 0.7318 | 0.9878   |
+| 0.0162        | 7.0   | 1120 | 0.0575          | 0.6364    | 0.85   | 0.7278 | 0.9876   |
+| 0.0162        | 8.0   | 1280 | 0.0651          | 0.5643    | 0.8464 | 0.6771 | 0.9847   |
 
 
 ### Framework versions