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: 2.7752
-- Rouge1: 12.1937
-- Rouge2: 3.488
-- Rougel: 10.0203
-- Rougelsum: 11.8441
-- Gen Len: 20.0
+- Loss: 2.7702
+- Rouge1: 12.3714
+- Rouge2: 3.4491
+- Rougel: 10.0652
+- Rougelsum: 12.0093
+- Gen Len: 19.9999
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
-| 2.0958        | 1.0   | 14598 | 2.7752          | 12.1937 | 3.488  | 10.0203 | 11.8441   | 20.0    |
+| 2.0391        | 1.0   | 14598 | 2.7702          | 12.3714 | 3.4491 | 10.0652 | 12.0093   | 19.9999 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc8d3c961c4fb11cc962fa041207cf656af3d8337b8c4c90408c090a1c270d4
+oid sha256:cfe41bf1817da967a5c9d6da6c011516df54e947fc1ade48efcee42fbcc38ebb
 size 557971674