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: 3.4301
-- Rouge1: 10.9738
-- Rouge2: 1.4922
-- Rougel: 8.0468
-- Rougelsum: 9.9416
+- Loss: 3.4140
+- Rouge1: 10.9835
+- Rouge2: 1.4974
+- Rougel: 8.1037
+- Rougelsum: 10.0069
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.8094        | 1.0   | 2920 | 3.4301          | 10.9738 | 1.4922 | 8.0468 | 9.9416    | 20.0    |
+| 1.7819        | 1.0   | 2920 | 3.4140          | 10.9835 | 1.4974 | 8.1037 | 10.0069   | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf6c7e569b6a447b9ccdc43286e4aa9dd6ff697a86770a53246bf7cd4e96a1ac
+oid sha256:1de566f6499473719ee30be834dbc40482c666e6fe2d2dfe80487d71ccdebd6c
 size 557971674