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: 3.0471
-- Rouge1: 10.5226
-- Rouge2: 2.2758
-- Rougel: 8.3934
-- Rougelsum: 10.1482
+- Loss: 3.1440
+- Rouge1: 10.9141
+- Rouge2: 2.6408
+- Rougel: 8.7867
+- Rougelsum: 10.5538
 - 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 2.6435        | 1.0   | 23165 | 3.0471          | 10.5226 | 2.2758 | 8.3934 | 10.1482   | 20.0    |
+| 2.7872        | 1.0   | 23165 | 3.1440          | 10.9141 | 2.6408 | 8.7867 | 10.5538   | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c151269a91a7629e905cc675676cf3ef17568f4679dd2a1cdeb8328b00eb1ca
+oid sha256:0c274e1d4c4331721b8227a13c9bf3cd539279b5c4af75962ffe46765acc4a9f
 size 557971229