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 [GuysTrans/bart-base-re-attention](https://huggingface.co/GuysTrans/bart-base-re-attention) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 9.6847
-- Rouge1: 8.0542
-- Rouge2: 0.3555
-- Rougel: 6.252
-- Rougelsum: 7.7601
+- Loss: 9.2135
+- Rouge1: 9.3721
+- Rouge2: 1.0644
+- Rougel: 6.7714
+- Rougelsum: 8.9624
 - 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 4.3076        | 1.0   | 22880 | 9.6847          | 8.0542 | 0.3555 | 6.252  | 7.7601    | 20.0    |
+| 3.934         | 1.0   | 22880 | 9.2135          | 9.3721 | 1.0644 | 6.7714 | 8.9624    | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:977750c9236c20eae1d4d36e050ce01af2d7c4c9d698f3f84929f2fcfd4ba033
+oid sha256:2a6c6c537c75afe5648810ae35ea1354c33541f83d11084856be105b6d71f39f
 size 558025109