End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gogamza/kobart-base-v2](https://huggingface.co/gogamza/kobart-base-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0349
-- Bleu: 62.0021
-- Gen Len: 18.9338
+- Loss: 0.0376
+- Bleu: 60.9717
+- Gen Len: 19.3034
 
 ## Model description
 
@@ -51,9 +51,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
-| 0.0451        | 1.0   | 5738  | 0.0415          | 65.2072 | 18.7099 |
-| 0.033         | 2.0   | 11476 | 0.0350          | 61.4245 | 18.8967 |
-| 0.0245        | 3.0   | 17214 | 0.0349          | 62.0021 | 18.9338 |
+| 0.0504        | 1.0   | 5738  | 0.0475          | 60.3699 | 19.6617 |
+| 0.0362        | 2.0   | 11476 | 0.0388          | 58.5465 | 19.6736 |
+| 0.0261        | 3.0   | 17214 | 0.0376          | 60.9717 | 19.3034 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d3b659c445dd285a281593e8d38b6c7124c748ac463de7b5babe6c725bd6db
+oid sha256:17df1b4a28a7592c8da1c85cf14b7655535e05f042bdea4dac863b8028cd389a
 size 495589768