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: 2.7836
-- Rouge1: 12.3954
-- Rouge2: 3.6536
-- Rougel: 10.2324
-- Rougelsum: 12.0594
+- Loss: 2.7565
+- Rouge1: 12.4334
+- Rouge2: 3.5931
+- Rougel: 10.2264
+- Rougelsum: 12.0732
 - Gen Len: 20.0
 
 ## 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 |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
-| 2.3126        | 1.0   | 14598 | 2.7836          | 12.3954 | 3.6536 | 10.2324 | 12.0594   | 20.0    |
+| 2.2448        | 1.0   | 14598 | 2.7565          | 12.4334 | 3.5931 | 10.2264 | 12.0732   | 20.0    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cc998dfe140e424955cb2f2d0bd64b244d53f299a8632b852f7afdcea3f0f7d
+oid sha256:d28f12d489d402393ce10a1a19d8e158dd42f0a6312badc3b383bc7ffa2bf400
 size 557971229