End of training

README.md

@@ -17,12 +17,12 @@ 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: 11.2151
-- Rouge1: 0.4518
+- Loss: 11.7324
+- Rouge1: 0.2462
 - Rouge2: 0.0
-- Rougel: 0.4506
-- Rougelsum: 0.4533
-- Gen Len: 18.226
+- Rougel: 0.2444
+- Rougelsum: 0.2468
+- Gen Len: 18.7687
 
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 6.2494        | 1.0   | 2920 | 11.2151         | 0.4518 | 0.0    | 0.4506 | 0.4533    | 18.226  |
+| 6.1416        | 1.0   | 2920 | 11.7324         | 0.2462 | 0.0    | 0.2444 | 0.2468    | 18.7687 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25d88117d890d80bf5e2db1ceb0e110491c9f824f2f8ae7d147c2328a3f5901b
+oid sha256:7c6c2477c8118377b51065d69f05d1c57cae51856b95e606fbcceb633f8fb9e3
 size 558025618