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: 2.9937
-- Rouge1: 11.6291
-- Rouge2: 3.0297
-- Rougel: 9.4391
-- Rougelsum: 11.1692
-- Gen Len: 19.9894
+- Loss: 3.0027
+- Rouge1: 11.6245
+- Rouge2: 3.001
+- Rougel: 9.4136
+- Rougelsum: 11.1543
+- Gen Len: 19.99
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.5311        | 1.0   | 14598 | 2.9937          | 11.6291 | 3.0297 | 9.4391 | 11.1692   | 19.9894 |
+| 1.5008        | 1.0   | 14598 | 3.0027          | 11.6245 | 3.001  | 9.4136 | 11.1543   | 19.99   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988f6bad07639195536d5ce8dae71b2a0e90a18c386d43244c0995c9cbf6fdbe
+oid sha256:86d777a52bfd7b484c4ae692fecd120ed7ee4c5cd82c244f6a58419719a34472
 size 557971229