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: 3.0108
-- Rouge1: 11.6288
-- Rouge2: 3.0431
-- Rougel: 9.4421
-- Rougelsum: 11.1743
-- Gen Len: 19.9858
+- Loss: 3.0057
+- Rouge1: 11.6516
+- Rouge2: 3.0188
+- Rougel: 9.4015
+- Rougelsum: 11.2023
+- Gen Len: 19.9876
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.4901        | 1.0   | 14598 | 3.0108          | 11.6288 | 3.0431 | 9.4421 | 11.1743   | 19.9858 |
+| 1.4678        | 1.0   | 14598 | 3.0057          | 11.6516 | 3.0188 | 9.4015 | 11.2023   | 19.9876 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:543c6fa3e72c8af4f4fcbb156efd0b9b2924ef06da0171a8cbe8830644ad014d
+oid sha256:b1d50726ccf8bb2f7a7239a294b709a5e95dc4550997b2d4772365af9ca0ea7b
 size 557971229