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: 3.4177
-- Rouge1: 11.8641
-- Rouge2: 1.4944
-- Rougel: 8.8078
-- Rougelsum: 10.8569
+- Loss: 3.4294
+- Rouge1: 11.7106
+- Rouge2: 1.4948
+- Rougel: 8.5139
+- Rougelsum: 10.6086
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 2.1309        | 1.0   | 2920 | 3.4177          | 11.8641 | 1.4944 | 8.8078 | 10.8569   | 20.0    |
+| 2.0171        | 1.0   | 2920 | 3.4294          | 11.7106 | 1.4948 | 8.5139 | 10.6086   | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae80a5fdf01f4ececfa80a1103224e22c7dd20a3fc09d191972d206fa7488e3
+oid sha256:c8b8a28f1d353c2240c5ee9f9f1c40dfca6d1d4a7bb664c0bc0a6745c2811bae
 size 557971229