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: 3.0329
-- Rouge1: 11.558
-- Rouge2: 3.0583
-- Rougel: 9.3744
-- Rougelsum: 11.1133
-- Gen Len: 19.9883
+- Loss: 3.0339
+- Rouge1: 11.573
+- Rouge2: 2.9395
+- Rougel: 9.3237
+- Rougelsum: 11.1091
+- Gen Len: 19.9913
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 1.4519        | 1.0   | 14598 | 3.0329          | 11.558 | 3.0583 | 9.3744 | 11.1133   | 19.9883 |
+| 1.442         | 1.0   | 14598 | 3.0339          | 11.573 | 2.9395 | 9.3237 | 11.1091   | 19.9913 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f2b4a6336d9ef31ccb8ca98684fa6591e95a1f62f5960d0e9a67a190882342
+oid sha256:17cd7ed1ac94f95b4c84ccc606ad22ce291504294dba3ba21efea69ce716028b
 size 557971229