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: 2.7657
-- Rouge1: 12.1249
-- Rouge2: 3.2935
-- Rougel: 9.9074
-- Rougelsum: 11.7271
-- Gen Len: 20.0
+- Loss: 2.7717
+- Rouge1: 11.9193
+- Rouge2: 3.1835
+- Rougel: 9.7943
+- Rougelsum: 11.5001
+- Gen Len: 19.9997
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.7496        | 1.0   | 14598 | 2.7657          | 12.1249 | 3.2935 | 9.9074 | 11.7271   | 20.0    |
+| 1.7167        | 1.0   | 14598 | 2.7717          | 11.9193 | 3.1835 | 9.7943 | 11.5001   | 19.9997 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee29c88c99fcc963b721f862f523f0edaac0e3f1acc050b536e819a14e917b1d
+oid sha256:7c5ee51e30d9ab6976ec0ecf47ff1295c8cb761d9df55816f35f9db2cf1169e2
 size 557971229