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: 11.0071
-- Rouge1: 10.4738
-- Rouge2: 0.8
-- Rougel: 7.4205
-- Rougelsum: 9.6662
+- Loss: 9.2889
+- Rouge1: 10.2401
+- Rouge2: 0.5184
+- Rougel: 7.2688
+- Rougelsum: 9.66
 - 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 2.3299        | 1.0   | 22880 | 11.0071         | 10.4738 | 0.8    | 7.4205 | 9.6662    | 20.0    |
+| 2.1926        | 1.0   | 22880 | 9.2889          | 10.2401 | 0.5184 | 7.2688 | 9.66      | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:610997157ab55795990c092eb416f22aa3e7428f7889639d507e0ef6db54380b
+oid sha256:688585ae32f345eeb326f2724992ed9e5dce9099dadeeee61de6010d37dc49e2
 size 558025109