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 [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0264
-- Accuracy: 0.8207
+- Loss: 2.0377
+- Accuracy: 0.8151
 
 ## Model description
 
@@ -50,16 +50,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 2.3559        | 1.0   | 15202 | 2.5301          | 0.7425   |
-| 2.2821        | 2.0   | 30404 | 2.2508          | 0.7737   |
-| 2.0705        | 3.0   | 45606 | 2.1307          | 0.7943   |
-| 1.9612        | 4.0   | 60808 | 2.0244          | 0.8115   |
-| 1.3880        | 5.0   | 76010 | 2.0264          | 0.8207   |
+| 2.5673        | 1.0   | 15312 | 2.5667          | 0.7330   |
+| 2.2339        | 2.0   | 30624 | 2.2996          | 0.7678   |
+| 1.9288        | 3.0   | 45936 | 2.1713          | 0.7870   |
+| 1.6486        | 4.0   | 61248 | 2.0764          | 0.8027   |
+| 1.4956        | 5.0   | 76560 | 2.0377          | 0.8151   |
 
 
 ### Framework versions
 
-- Transformers 5.0.0
+- Transformers 5.1.0
 - Pytorch 2.10.0+cu128
 - Datasets 4.5.0
 - Tokenizers 0.22.2