End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6239
-- Accuracy: 0.2494
+- Loss: 1.4127
+- Accuracy: 0.3862
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.9642        | 1.0   | 500  | 1.6810          | 0.2136   |
-| 1.8164        | 2.0   | 1000 | 1.6294          | 0.2398   |
-| 1.7964        | 3.0   | 1500 | 1.6227          | 0.2468   |
+| 2.2751        | 1.0   | 500  | 1.5125          | 0.3182   |
+| 1.5159        | 2.0   | 1000 | 1.4176          | 0.3738   |
+| 1.4635        | 3.0   | 1500 | 1.4051          | 0.3814   |
 
 
 ### Framework versions