Update README.md

README.md

@@ -15,25 +15,16 @@ bass-model: pdelobelle/robbert-v2-dutch-base
 This model is a fine-tuned version of [pdelobelle/robbert-v2-dutch-base](https://huggingface.co/pdelobelle/robbert-v2-dutch-base) on [GroNLP/dutch-cola](https://huggingface.co/datasets/GroNLP/dutch-cola).
 It achieves the following results on the evaluation set:
 
-- Loss: 0.5884
-- Accuracy: 0.78
+- Accuracy: 0.7879
 
 
 #### Training Hyperparameters
 
 The following hyperparameters were used during training:
 
-- learning rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
-- num_epochs=3
-
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5359        | 1.0   | 1244 | 0.6437          | 0.7196   |
-| 0.3556        | 2.0   | 2488 | 0.5884          | 0.78     |
-| 0.2545        | 3.0   | 3732 | 0.7075          | 0.7796   |
+- num_epochs=2
+- FP16 = True