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: 7.5197
-- Rouge1: 2.2241
-- Rouge2: 0.0615
-- Rougel: 1.9283
-- Rougelsum: 2.2242
+- Loss: 11.3390
+- Rouge1: 0.8049
+- Rouge2: 0.0059
+- Rougel: 0.764
+- Rougelsum: 0.8047
 - 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 6.3077        | 1.0   | 22880 | 7.5197          | 2.2241 | 0.0615 | 1.9283 | 2.2242    | 20.0    |
+| 6.2087        | 1.0   | 22880 | 11.3390         | 0.8049 | 0.0059 | 0.764  | 0.8047    | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34bdb573c9d72c203d1a5cfe641ac7fe76904fb3a3a5971473c4601e4a4c6663
+oid sha256:f2034e8842e0a185e18ddce09ea2e855ffba98960ae372190b4bb047ecb39161
 size 558025109