End of training

README.md

@@ -20,8 +20,8 @@ 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 the swag dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7296
-- Accuracy: 0.7193
+- Loss: 0.6912
+- Accuracy: 0.7347
 
 ## Model description
 
@@ -46,16 +46,18 @@ 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: 4
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.0301        | 1.0   | 1150 | 0.8275          | 0.6817   |
-| 0.9302        | 2.0   | 2300 | 0.7588          | 0.7089   |
-| 0.898         | 3.0   | 3450 | 0.7368          | 0.7175   |
-| 0.8831        | 4.0   | 4600 | 0.7296          | 0.7193   |
+| 1.02          | 1.0   | 1150 | 0.8192          | 0.6860   |
+| 0.9222        | 2.0   | 2300 | 0.7436          | 0.7128   |
+| 0.8859        | 3.0   | 3450 | 0.7166          | 0.7247   |
+| 0.8639        | 4.0   | 4600 | 0.7008          | 0.7295   |
+| 0.8689        | 5.0   | 5750 | 0.6954          | 0.7335   |
+| 0.8639        | 6.0   | 6900 | 0.6912          | 0.7347   |
 
 
 ### Framework versions