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: 2.7642
-- Rouge1: 6.8541
-- Rouge2: 2.1367
-- Rougel: 6.1231
-- Rougelsum: 6.79
+- Loss: 2.6772
+- Rouge1: 7.021
+- Rouge2: 2.0116
+- Rougel: 6.1531
+- Rougelsum: 6.9345
 - 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 2.4071        | 1.0   | 22880 | 2.7642          | 6.8541 | 2.1367 | 6.1231 | 6.79      | 20.0    |
+| 2.2421        | 1.0   | 22880 | 2.6772          | 7.021  | 2.0116 | 6.1531 | 6.9345    | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463ce23b1b7abbcc2e8542d8109e3e2c5c6265bc8ec446ed594dbc09c9a4e1a3
+oid sha256:bd118ce64be280a5f5e85090220b63a9f17ec6aa8d8088367792771ec6248bf9
 size 557971229