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 [pdelobelle/robbert-v2-dutch-base](https://huggingface.co/pdelobelle/robbert-v2-dutch-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0097
-- Precision: 0.6609
-- Recall: 0.6121
-- F1: 0.6356
-- Accuracy: 0.8636
+- Loss: 1.0350
+- Precision: 0.6604
+- Recall: 0.6291
+- F1: 0.6444
+- Accuracy: 0.8697
 
 ## Model description
 
@@ -43,25 +43,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 290  | 0.9755          | 0.6240    | 0.5714 | 0.5965 | 0.8493   |
-| 0.0583        | 2.0   | 580  | 0.8817          | 0.6185    | 0.5828 | 0.6001 | 0.8574   |
-| 0.0583        | 3.0   | 870  | 0.8827          | 0.6567    | 0.6045 | 0.6296 | 0.8628   |
-| 0.0533        | 4.0   | 1160 | 0.9250          | 0.6517    | 0.6036 | 0.6267 | 0.8645   |
-| 0.0533        | 5.0   | 1450 | 1.0505          | 0.606     | 0.5733 | 0.5892 | 0.8493   |
-| 0.0339        | 6.0   | 1740 | 0.9916          | 0.6603    | 0.6235 | 0.6414 | 0.8634   |
-| 0.0444        | 7.0   | 2030 | 1.0201          | 0.6473    | 0.6008 | 0.6232 | 0.8591   |
-| 0.0444        | 8.0   | 2320 | 1.0097          | 0.6609    | 0.6121 | 0.6356 | 0.8636   |
+| No log        | 1.0   | 73   | 1.0577          | 0.6605    | 0.6074 | 0.6328 | 0.8632   |
+| No log        | 2.0   | 146  | 1.1133          | 0.6470    | 0.6017 | 0.6235 | 0.8606   |
+| No log        | 3.0   | 219  | 1.0416          | 0.6539    | 0.6310 | 0.6423 | 0.8675   |
+| No log        | 4.0   | 292  | 1.0350          | 0.6604    | 0.6291 | 0.6444 | 0.8697   |
 
 
 ### Framework versions