End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [eugenesiow/bart-paraphrase](https://huggingface.co/eugenesiow/bart-paraphrase) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2646
+- Loss: 2.3697
 
 ## Model description
 
@@ -49,11 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.2858        | 1.0   | 374  | 2.7202          |
-| 2.4028        | 2.0   | 748  | 1.8768          |
-| 1.9304        | 3.0   | 1122 | 1.5375          |
-| 1.5841        | 4.0   | 1496 | 1.3241          |
-| 1.4944        | 5.0   | 1870 | 1.2363          |
+| 5.3656        | 0.99  | 93   | 5.0322          |
+| 4.52          | 2.0   | 187  | 3.9055          |
+| 3.7139        | 2.99  | 280  | 3.1498          |
+| 3.348         | 4.0   | 374  | 2.6742          |
+| 2.9365        | 4.97  | 465  | 2.3143          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4880c32a236be7c4e61021c8703aec350d901a9b2f76fbabb67ff7e0ec58d1e6
+oid sha256:71d3660612eac61fd3c9439d13e76fc37ccc17e1bf45f76f3aa92bb328adeee3
 size 1625426996