End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6731
+- Loss: 3.0447
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 4.0269        | 1.0   | 8249  | 3.8562          |
-| 3.8081        | 2.0   | 16498 | 3.7141          |
-| 3.7856        | 3.0   | 24747 | 3.6731          |
+| 3.2353        | 1.0   | 12759 | 3.2105          |
+| 3.0855        | 2.0   | 25518 | 3.0827          |
+| 3.0183        | 3.0   | 38277 | 3.0447          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c651794f827d52bcdd3534409be89b3f83fee56956ae9954ce72a72c8fbd1ba
+oid sha256:71cf05e7ffe78e511c042afef63a969bd408889fce5367754ad004c2d4a92728
 size 327657928