Training complete

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0165
-- Bleu: 96.2379
-- Gen Len: 18.7812
+- Loss: 2.7815
+- Bleu: 39.3114
+- Gen Len: 21.8462
 
 ## Model description
 
@@ -52,13 +52,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 440  | 0.0173          | 96.4182 | 26.8646 |
-| 0.2248        | 2.0   | 880  | 0.0165          | 96.2379 | 18.7812 |
+| No log        | 1.0   | 25   | 3.3111          | 29.4526 | 21.1692 |
+| No log        | 2.0   | 50   | 2.7815          | 39.3114 | 21.8462 |
 
 
 ### Framework versions
 
 - Transformers 4.49.0
-- Pytorch 2.5.1+cu124
-- Datasets 3.3.2
-- Tokenizers 0.21.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.1