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: 1.1720
-- Rouge1: 6.6327
-- Rouge2: 4.2107
-- Rougel: 6.4177
-- Rougelsum: 6.483
+- Loss: 1.1487
+- Rouge1: 6.637
+- Rouge2: 4.213
+- Rougel: 6.4238
+- Rougelsum: 6.4843
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 1.174         | 1.0   | 1074 | 1.1720          | 6.6327 | 4.2107 | 6.4177 | 6.483     | 20.0    |
+| 1.1351        | 1.0   | 1074 | 1.1487          | 6.637  | 4.213  | 6.4238 | 6.4843    | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:596e8b29bb099dabfe5a76e2e2402b308c720a93ca11f97a592e1eb6a4659025
+oid sha256:75bf1bb7e6cab49415d0276378a6c2b7f8d21b70bdf372bab9715ca872dca590
 size 557971229