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 [gshields/translate_model_error_v0.4](https://huggingface.co/gshields/translate_model_error_v0.4) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.4180
-- Bleu: 11.3247
-- Gen Len: 10.9
+- Loss: 3.4122
+- Bleu: 16.1003
+- Gen Len: 11.0333
 
 ## Model description
 
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 8    | 3.4355          | 11.0656 | 11.1    |
-| No log        | 2.0   | 16   | 3.4180          | 11.3247 | 10.9    |
+| No log        | 1.0   | 8    | 3.4362          | 15.9823 | 9.3333  |
+| No log        | 2.0   | 16   | 3.4122          | 16.1003 | 11.0333 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6746778ee1c83b2032c13b6cb644dfb4b59ec478d0cb38d20ba78fa55347c43
+oid sha256:7f4f0aa6ef7504a2e92e42dff984235c24f466db3f7e95c2c94a7319a030292a
 size 303761861

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428bd5c1ea5955531b97f39a2ddd34cb9c27353d16ad2e917d3bfbcd015c1c1c
+oid sha256:8245c6526a7d02f0fc10afc73b027325e2fbfbcb4c3f591351a343c34f17a9c0
 size 4155