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: 3.4140
-- Rouge1: 10.9835
-- Rouge2: 1.4974
-- Rougel: 8.1037
-- Rougelsum: 10.0069
+- Loss: 3.4432
+- Rouge1: 10.8882
+- Rouge2: 1.5313
+- Rougel: 8.0077
+- Rougelsum: 9.8545
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.7819        | 1.0   | 2920 | 3.4140          | 10.9835 | 1.4974 | 8.1037 | 10.0069   | 20.0    |
+| 1.7356        | 1.0   | 2920 | 3.4432          | 10.8882 | 1.5313 | 8.0077 | 9.8545    | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de566f6499473719ee30be834dbc40482c666e6fe2d2dfe80487d71ccdebd6c
+oid sha256:4d6a7be40a8a8dee5f1d51413732fa9832e3ec4f79e9836e614c814861d70ffc
 size 557971674