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: 2.8222
-- Rouge1: 12.1325
-- Rouge2: 3.1716
-- Rougel: 9.8506
-- Rougelsum: 11.7077
-- Gen Len: 19.9976
+- Loss: 2.8379
+- Rouge1: 11.6167
+- Rouge2: 3.2158
+- Rougel: 9.6009
+- Rougelsum: 11.1962
+- Gen Len: 19.9977
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.6471        | 1.0   | 14598 | 2.8222          | 12.1325 | 3.1716 | 9.8506 | 11.7077   | 19.9976 |
+| 1.6299        | 1.0   | 14598 | 2.8379          | 11.6167 | 3.2158 | 9.6009 | 11.1962   | 19.9977 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124489763e7e4b8763107e3f74fee68d80f105f4f268d98e4b97555e196f12e1
+oid sha256:4582ae01ee260adc27bdb3f992e1265cf755bb621145a75883ab408032e18ed3
 size 557971229