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: 2.8457
-- Rouge1: 11.8016
-- Rouge2: 3.1174
-- Rougel: 9.6516
-- Rougelsum: 11.3664
-- Gen Len: 19.997
+- Loss: 2.8615
+- Rouge1: 11.8865
+- Rouge2: 3.1384
+- Rougel: 9.704
+- Rougelsum: 11.4403
+- Gen Len: 19.9958
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.6062        | 1.0   | 14598 | 2.8457          | 11.8016 | 3.1174 | 9.6516 | 11.3664   | 19.997  |
+| 1.5958        | 1.0   | 14598 | 2.8615          | 11.8865 | 3.1384 | 9.704  | 11.4403   | 19.9958 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05819ee6b69555775c118555ffa7def1ddfed1aeb06dcae17d59a3b731e9fb1c
+oid sha256:4f95003574351cda74bae86aff1e5c020dbee4389c0cc30834468e4af6d6fa53
 size 557971229