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 [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the swag dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8483
-- Accuracy: 0.6567
+- Loss: 0.7733
+- Accuracy: 0.6858
 
 ## Model description
 
@@ -46,15 +46,22 @@ 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: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 1.012         | 1.0   | 4597  | 0.8999          | 0.6374   |
-| 0.9634        | 2.0   | 9194  | 0.8617          | 0.6512   |
-| 0.955         | 3.0   | 13791 | 0.8483          | 0.6567   |
+| 1.0103        | 1.0   | 4597  | 0.8978          | 0.6370   |
+| 0.9591        | 2.0   | 9194  | 0.8498          | 0.6568   |
+| 0.9401        | 3.0   | 13791 | 0.8270          | 0.6626   |
+| 0.9265        | 4.0   | 18388 | 0.8105          | 0.6713   |
+| 0.9202        | 5.0   | 22985 | 0.8001          | 0.6759   |
+| 0.8921        | 6.0   | 27582 | 0.7894          | 0.6790   |
+| 0.894         | 7.0   | 32179 | 0.7836          | 0.6823   |
+| 0.8695        | 8.0   | 36776 | 0.7803          | 0.6835   |
+| 0.8684        | 9.0   | 41373 | 0.7753          | 0.6845   |
+| 0.8696        | 10.0  | 45970 | 0.7733          | 0.6858   |
 
 
 ### Framework versions