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 [GuysTrans/bart-base-chat-512-seq](https://huggingface.co/GuysTrans/bart-base-chat-512-seq) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7975
-- Rouge1: 12.1664
-- Rouge2: 3.1943
-- Rougel: 9.8904
-- Rougelsum: 11.7475
-- Gen Len: 19.9975
+- Loss: 2.8066
+- Rouge1: 11.9316
+- Rouge2: 3.2397
+- Rougel: 9.7353
+- Rougelsum: 11.5092
+- Gen Len: 19.9974
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.6891        | 1.0   | 14598 | 2.7975          | 12.1664 | 3.1943 | 9.8904 | 11.7475   | 19.9975 |
+| 1.6651        | 1.0   | 14598 | 2.8066          | 11.9316 | 3.2397 | 9.7353 | 11.5092   | 19.9974 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:396861d43c7f6dc697af26710cc031ed68d69136541d7ba3e76496678b2caa60
+oid sha256:b27e15a010ac7d24d3e65b8a5cbd3eabf99797678f998a9e892da5e9e188540b
 size 557971229