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: 9.8084
-- Rouge1: 2.4846
-- Rouge2: 0.0342
-- Rougel: 2.1923
-- Rougelsum: 2.4836
+- Loss: 9.5185
+- Rouge1: 2.1676
+- Rouge2: 0.0996
+- Rougel: 1.8564
+- Rougelsum: 2.1632
 - 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 6.1971        | 1.0   | 22880 | 9.8084          | 2.4846 | 0.0342 | 2.1923 | 2.4836    | 20.0    |
+| 6.2997        | 1.0   | 22880 | 9.5185          | 2.1676 | 0.0996 | 1.8564 | 2.1632    | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe74dc4b4576a03414bdfc8f38adcca2cef02b5a2ea28a469de4e787efc27ed
+oid sha256:f009e8cb5c927c5e5e726d23e4411902491075c3f03c5364e7e0b191ea7197d8
 size 558025109