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: 0.1144
-- Sacrebleu: 21.2020
+- Loss: 0.1284
+- Sacrebleu: 17.1127
 
 ## Model description
 
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
-| 0.1683        | 1.0   | 1286 | 0.1400          | 11.6643   |
-| 0.1339        | 2.0   | 2572 | 0.1192          | 19.7399   |
-| 0.1273        | 3.0   | 3858 | 0.1144          | 21.2020   |
+| 0.1744        | 1.0   | 1285 | 0.1582          | 8.3869    |
+| 0.1417        | 2.0   | 2570 | 0.1335          | 14.8956   |
+| 0.1239        | 3.0   | 3855 | 0.1284          | 17.1127   |
 
 
 ### Framework versions
 
 - Transformers 4.57.0
 - Pytorch 2.8.0+cu126
-- Datasets 4.1.1
+- Datasets 4.2.0
 - Tokenizers 0.22.1