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: 2.8842
-- Rouge1: 11.6484
-- Rouge2: 3.0863
-- Rougel: 9.5862
-- Rougelsum: 11.1215
-- Gen Len: 19.9941
+- Loss: 2.9082
+- Rouge1: 11.6061
+- Rouge2: 3.1461
+- Rougel: 9.4492
+- Rougelsum: 11.169
+- Gen Len: 19.9931
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.5672        | 1.0   | 14598 | 2.8842          | 11.6484 | 3.0863 | 9.5862 | 11.1215   | 19.9941 |
+| 1.549         | 1.0   | 14598 | 2.9082          | 11.6061 | 3.1461 | 9.4492 | 11.169    | 19.9931 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1d0bd77fe2169e8fea18959df67a899dbcee14a330e704ad77221fef73b911
+oid sha256:d599ddb6150e285aa7b35a4e6d45b622b3e5578a73aa7e8ee22de838692ab803
 size 557971229