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: 9.4250
-- Rouge1: 2.8304
-- Rouge2: 0.0194
-- Rougel: 2.609
-- Rougelsum: 2.7729
+- Loss: 9.4026
+- Rouge1: 3.8486
+- Rouge2: 0.0189
+- Rougel: 3.5828
+- Rougelsum: 3.7861
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 6.8151        | 1.0   | 2920 | 9.4250          | 2.8304 | 0.0194 | 2.609  | 2.7729    | 20.0    |
+| 6.4112        | 1.0   | 2920 | 9.4026          | 3.8486 | 0.0189 | 3.5828 | 3.7861    | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65684a469826d7f654b0f1b97ed1e2e6997e90a14e6b271be76918f5535f7689
+oid sha256:bc9100812cb5b019fd96cb2e9b8d0cea8024fe16d020a14bf583075be4f4a8b5
 size 558025618