End of training

README.md

@@ -17,11 +17,11 @@ 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: 2.9474
-- Rouge1: 11.8046
-- Rouge2: 3.1047
-- Rougel: 9.5348
-- Rougelsum: 11.3575
+- Loss: 2.9636
+- Rouge1: 11.7289
+- Rouge2: 3.0424
+- Rougel: 9.5476
+- Rougelsum: 11.278
 - Gen Len: 19.9925
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.5997        | 1.0   | 14598 | 2.9474          | 11.8046 | 3.1047 | 9.5348 | 11.3575   | 19.9925 |
+| 1.5531        | 1.0   | 14598 | 2.9636          | 11.7289 | 3.0424 | 9.5476 | 11.278    | 19.9925 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ae9f3a273ef7b8e7596d2a74ddaaa7b3737473c123b817df2c0cdd6e43f70a
+oid sha256:0c9fea0a2e8c57bd34847b38721eeb1a2f881970f9112b8b1aa34ef3f7ee83a1
 size 557971229