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: 2.9052
-- Rouge1: 11.6112
-- Rouge2: 3.0626
-- Rougel: 9.401
-- Rougelsum: 11.1628
-- Gen Len: 19.9971
+- Loss: 2.9064
+- Rouge1: 11.9323
+- Rouge2: 3.1351
+- Rougel: 9.6302
+- Rougelsum: 11.4979
+- Gen Len: 19.9968
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.5374        | 1.0   | 14598 | 2.9052          | 11.6112 | 3.0626 | 9.401  | 11.1628   | 19.9971 |
+| 1.6108        | 1.0   | 14598 | 2.9064          | 11.9323 | 3.1351 | 9.6302 | 11.4979   | 19.9968 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:073438f50b7be03b25cb30e4bf1e5451c90ec8454630aff6895cf55f291fb727
+oid sha256:9669618cc9f804c4cf45e14f00ad80c7b39370873202b807a0a06a7941d28e8b
 size 557971229