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 [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0186
-- Accuracy: 0.9163
+- Loss: 1.1362
+- Accuracy: 0.9023
 
 ## Model description
 
@@ -43,15 +43,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 50
+- lr_scheduler_warmup_steps: 500
 - num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7476        | 1.0   | 216  | 0.5896          | 0.8279   |
-| 0.7105        | 2.0   | 432  | 1.0186          | 0.9163   |
+| 0.6541        | 1.0   | 216  | 0.5935          | 0.8512   |
+| 0.9329        | 2.0   | 432  | 1.1362          | 0.9023   |
 
 
 ### Framework versions