Training complete

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1564
-- Precision: 0.75
-- Recall: 0.8045
-- F1: 0.7763
-- Accuracy: 0.9682
+- Loss: 0.1705
+- Precision: 0.7588
+- Recall: 0.8038
+- F1: 0.7806
+- Accuracy: 0.9680
 
 ## Model description
 
@@ -44,20 +44,22 @@ 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: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0439        | 1.0   | 1041 | 0.1419          | 0.7464    | 0.7918 | 0.7684 | 0.9674   |
-| 0.0458        | 2.0   | 2082 | 0.1414          | 0.7493    | 0.8028 | 0.7752 | 0.9677   |
-| 0.0261        | 3.0   | 3123 | 0.1564          | 0.75      | 0.8045 | 0.7763 | 0.9682   |
+| 0.0281        | 1.0   | 521  | 0.1800          | 0.7135    | 0.7578 | 0.7350 | 0.9610   |
+| 0.0413        | 2.0   | 1042 | 0.1418          | 0.7279    | 0.7937 | 0.7594 | 0.9657   |
+| 0.026         | 3.0   | 1563 | 0.1476          | 0.7575    | 0.8077 | 0.7818 | 0.9678   |
+| 0.0172        | 4.0   | 2084 | 0.1660          | 0.7503    | 0.8022 | 0.7753 | 0.9676   |
+| 0.0117        | 5.0   | 2605 | 0.1705          | 0.7588    | 0.8038 | 0.7806 | 0.9680   |
 
 
 ### Framework versions