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: 2.7487
-- Rouge1: 12.1763
-- Rouge2: 3.3368
-- Rougel: 9.9297
-- Rougelsum: 11.7748
-- Gen Len: 20.0
+- Loss: 2.7495
+- Rouge1: 12.1785
+- Rouge2: 3.2525
+- Rougel: 9.9317
+- Rougelsum: 11.775
+- 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.8365        | 1.0   | 14598 | 2.7487          | 12.1763 | 3.3368 | 9.9297 | 11.7748   | 20.0    |
+| 1.7711        | 1.0   | 14598 | 2.7495          | 12.1785 | 3.2525 | 9.9317 | 11.775    | 19.9999 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a343765019b59c4903372b96f8572118591e418c36d7ecad79fb74306356975
+oid sha256:a87e2e076e5297c05224741a6da35ea81c068e5f2e3fc3043c888a2165f71081
 size 557971229