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: 3.4140
-- Rouge1: 11.0345
-- Rouge2: 1.4618
-- Rougel: 8.2777
-- Rougelsum: 10.1522
+- Loss: 3.4086
+- Rouge1: 10.9423
+- Rouge2: 1.4701
+- Rougel: 8.1717
+- Rougelsum: 10.0279
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.8118        | 1.0   | 2920 | 3.4140          | 11.0345 | 1.4618 | 8.2777 | 10.1522   | 20.0    |
+| 1.7802        | 1.0   | 2920 | 3.4086          | 10.9423 | 1.4701 | 8.1717 | 10.0279   | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:831e49b42aa9dae6db8517d3ed518e0a9e7ccacba9e5324b3ddf775ccef8c27f
+oid sha256:956200bed055b8b6f0a4d57d3e7dfec4fac58c5280f39970b3f3e79bccfd62b1
 size 557971229