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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3873
-- Precision: 0.1119
-- Recall: 0.1176
-- F1: 0.1147
-- Accuracy: 0.4910
+- Loss: 1.2382
+- Precision: 0.2445
+- Recall: 0.3046
+- F1: 0.2712
+- Accuracy: 0.5420
 
 ## Model description
 
@@ -48,15 +48,16 @@ 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
-- num_epochs: 3
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 7    | 1.5010          | 0.0703    | 0.0863 | 0.0775 | 0.4580   |
-| No log        | 2.0   | 14   | 1.4077          | 0.1039    | 0.1150 | 0.1092 | 0.4821   |
-| No log        | 3.0   | 21   | 1.3873          | 0.1119    | 0.1176 | 0.1147 | 0.4910   |
+| No log        | 1.0   | 7    | 1.2382          | 0.2445    | 0.3046 | 0.2712 | 0.5420   |
+| No log        | 2.0   | 14   | 1.2382          | 0.2445    | 0.3046 | 0.2712 | 0.5420   |
+| No log        | 3.0   | 21   | 1.2382          | 0.2445    | 0.3046 | 0.2712 | 0.5420   |
+| No log        | 4.0   | 28   | 1.2382          | 0.2445    | 0.3046 | 0.2712 | 0.5420   |
 
 
 ### Framework versions