End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the pubmed-summarization dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9949
+- Loss: 1.9835
 
 ## Model description
 
@@ -50,11 +50,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.2258        | 0.8   | 500  | 2.0382          |
-| 2.1769        | 1.6   | 1000 | 1.9865          |
-| 2.1476        | 2.4   | 1500 | 2.0094          |
-| 2.146         | 3.2   | 2000 | 2.0005          |
-| 2.1429        | 4.0   | 2500 | 1.9993          |
+| 2.2356        | 0.4   | 500  | 2.0414          |
+| 2.161         | 0.8   | 1000 | 2.0307          |
+| 2.1446        | 1.2   | 1500 | 1.9946          |
+| 2.143         | 1.6   | 2000 | 2.0254          |
+| 2.1318        | 2.0   | 2500 | 1.9951          |
+| 2.133         | 2.4   | 3000 | 2.0143          |
+| 2.1321        | 2.8   | 3500 | 1.9991          |
+| 2.1268        | 3.2   | 4000 | 1.9789          |
+| 2.1169        | 3.6   | 4500 | 1.9736          |
+| 2.1254        | 4.0   | 5000 | 1.9745          |
 
 
 ### Framework versions