Training complete

README.md

@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ig](https://huggingface.co/Helsinki-NLP/opus-mt-en-ig) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8239
-- Bleu: 0.1318
+- Loss: 1.3984
+- Bleu: 7.8676
 
 ## Model description
 
@@ -51,9 +51,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu   |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.9208        | 1.0   | 250  | 0.8704          | 0.1251 |
-| 0.8669        | 2.0   | 500  | 0.8343          | 0.1356 |
-| 0.8656        | 3.0   | 750  | 0.8239          | 0.1318 |
+| 1.6893        | 1.0   | 625  | 1.5341          | 4.2257 |
+| 1.5707        | 2.0   | 1250 | 1.4315          | 6.8328 |
+| 1.4679        | 3.0   | 1875 | 1.3984          | 7.8676 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f68c140a33430f0b0eec8724aa78303c12f61740d3086a23e8fa02bcb24e9e
+oid sha256:235e0288c0ee2d195c29f18be68e906ecf257ba93ea5ebe7e3e05c9d5e14bb34
 size 291755644