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/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the eli5_category dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.8053
+- Loss: 3.7947
 
 ## Model description
 
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.9186        | 1.0   | 1309 | 3.8234          |
-| 3.8324        | 2.0   | 2618 | 3.8096          |
-| 3.7884        | 3.0   | 3927 | 3.8053          |
+| 3.9245        | 1.0   | 1309 | 3.8115          |
+| 3.829         | 2.0   | 2618 | 3.7972          |
+| 3.7885        | 3.0   | 3927 | 3.7947          |
 
 
 ### Framework versions