End of training

README.md

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [GuysTrans/bart-base-re-attention-mini-seq-512](https://huggingface.co/GuysTrans/bart-base-re-attention-mini-seq-512) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 12.6198
-- Rouge1: 0.0732
+- Loss: 11.9510
+- Rouge1: 0.0774
 - Rouge2: 0.0
-- Rougel: 0.0726
-- Rougelsum: 0.0737
-- Gen Len: 18.6752
+- Rougel: 0.0777
+- Rougelsum: 0.0782
+- Gen Len: 17.9933
 
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 5.8323        | 1.0   | 2920 | 12.6198         | 0.0732 | 0.0    | 0.0726 | 0.0737    | 18.6752 |
+| 5.7969        | 1.0   | 2920 | 11.9510         | 0.0774 | 0.0    | 0.0777 | 0.0782    | 17.9933 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d01a3baa45b092caed06f53e414f35e1174a758725dada39669ab7b23f7dd58
+oid sha256:60dbdc39c00b199b50627405d3f2f125ad327986a1370d0461f4020b6dd0f905
 size 558025618