End of training

README.md

@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.5147
-- Rouge1: 13.3584
-- Rouge2: 2.1549
-- Rougel: 9.8715
-- Rougelsum: 12.2357
+- Loss: 3.4617
+- Rouge1: 12.3291
+- Rouge2: 1.7466
+- Rougel: 9.1919
+- Rougelsum: 11.3026
 - Gen Len: 20.0
 
 ## Model description
@@ -53,7 +53,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 2.4322        | 1.0   | 2920 | 3.5147          | 13.3584 | 2.1549 | 9.8715 | 12.2357   | 20.0    |
+| 2.2441        | 1.0   | 2920 | 3.4617          | 12.3291 | 1.7466 | 9.1919 | 11.3026   | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443e841bdebf0c674cdea82254fe3967eeda9d3642ba6327d29eef8e91e5f6bf
+oid sha256:a963ee6e5d7ed536ee06c3788fb77aa87495811b69f046c3f574735b45a29186
 size 557971229