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 [FiveC/BartTay](https://huggingface.co/FiveC/BartTay) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1344
-- Sacrebleu: 17.5715
+- Loss: 0.1580
+- Sacrebleu: 15.0715
 
 ## Model description
 
@@ -51,9 +51,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
-| 0.1504        | 1.0   | 3126 | 0.1386          | 14.9983   |
-| 0.1134        | 2.0   | 6252 | 0.1320          | 16.3984   |
-| 0.0932        | 3.0   | 9378 | 0.1344          | 17.5715   |
+| 0.1441        | 1.0   | 2208 | 0.1552          | 11.7299   |
+| 0.0952        | 2.0   | 4416 | 0.1559          | 14.4601   |
+| 0.0812        | 3.0   | 6624 | 0.1580          | 15.0715   |
 
 
 ### Framework versions