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: 0.1460
-- Sacrebleu: 23.3065
+- Loss: 0.1491
+- Sacrebleu: 19.2023
 
 ## Model description
 
@@ -49,11 +49,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Sacrebleu |
-|:-------------:|:-----:|:-----:|:---------------:|:---------:|
-| 0.1441        | 1.0   | 4475  | 0.1506          | 18.0787   |
-| 0.0959        | 2.0   | 8950  | 0.1429          | 21.5479   |
-| 0.0761        | 3.0   | 13425 | 0.1460          | 23.3065   |
+| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|
+| 0.1716        | 1.0   | 2828 | 0.1629          | 15.9954   |
+| 0.1344        | 2.0   | 5656 | 0.1499          | 18.3597   |
+| 0.1103        | 3.0   | 8484 | 0.1491          | 19.2023   |
 
 
 ### Framework versions