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: 1.1037
-- Precision: 0.0
-- Recall: 0.0
-- F1: 0.0
-- Accuracy: 0.7612
+- Loss: 0.0638
+- Precision: 0.9377
+- Recall: 0.9500
+- F1: 0.9438
+- Accuracy: 0.9858
 
 ## Model description
 
@@ -43,23 +43,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.02
+- 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: 5
+- num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
-| 1.0763        | 1.0   | 1756 | 1.1223          | 0.0       | 0.0    | 0.0 | 0.7612   |
-| 1.0542        | 2.0   | 3512 | 1.1039          | 0.0       | 0.0    | 0.0 | 0.7612   |
-| 1.0413        | 3.0   | 5268 | 1.1104          | 0.0       | 0.0    | 0.0 | 0.7612   |
-| 1.0241        | 4.0   | 7024 | 1.1057          | 0.0       | 0.0    | 0.0 | 0.7612   |
-| 1.0372        | 5.0   | 8780 | 1.1037          | 0.0       | 0.0    | 0.0 | 0.7612   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0737        | 1.0   | 1756 | 0.0652          | 0.9077    | 0.9335 | 0.9204 | 0.9817   |
+| 0.0358        | 2.0   | 3512 | 0.0679          | 0.9307    | 0.9450 | 0.9378 | 0.9850   |
+| 0.0209        | 3.0   | 5268 | 0.0638          | 0.9377    | 0.9500 | 0.9438 | 0.9858   |
 
 
 ### Framework versions