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: 2.9118
-- Rouge1: 11.7942
-- Rouge2: 3.1038
-- Rougel: 9.7244
-- Rougelsum: 11.2743
-- Gen Len: 19.9945
+- Loss: 2.9286
+- Rouge1: 11.4537
+- Rouge2: 3.1352
+- Rougel: 9.4138
+- Rougelsum: 11.0251
+- Gen Len: 19.9928
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.5578        | 1.0   | 14598 | 2.9118          | 11.7942 | 3.1038 | 9.7244 | 11.2743   | 19.9945 |
+| 1.5449        | 1.0   | 14598 | 2.9286          | 11.4537 | 3.1352 | 9.4138 | 11.0251   | 19.9928 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40fc78631ba454f762ed1b24cb1de14bbaef908760583e790f6fe17b621e435d
+oid sha256:386aae19a3067f306fe5ddab40c02b973a9c27d0de35007e7db12bb52695bb3f
 size 557971229