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 [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: 2.7557
-- Rouge1: 12.2711
-- Rouge2: 3.5047
-- Rougel: 10.0467
-- Rougelsum: 11.913
+- Loss: 2.7628
+- Rouge1: 12.2581
+- Rouge2: 3.4807
+- Rougel: 10.0426
+- Rougelsum: 11.9053
 - 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
-| 2.1822        | 1.0   | 14598 | 2.7557          | 12.2711 | 3.5047 | 10.0467 | 11.913    | 20.0    |
+| 2.166         | 1.0   | 14598 | 2.7628          | 12.2581 | 3.4807 | 10.0426 | 11.9053   | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ab31b3e9a78a192014c0998bf8ca0cf3a1c6786a5c3613ca4b574c94e21f1b
+oid sha256:141735f585047318979712821e85837c4ce97e612ed61ef78090f360fe55a632
 size 557971674