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: 3.4563
-- Bleu: 11.1152
-- Gen Len: 11.2
+- Loss: 3.4079
+- Bleu: 17.9043
+- Gen Len: 10.9
 
 ## 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    | 3.4736          | 11.115  | 11.1667 |
-| No log        | 2.0   | 16   | 3.4563          | 11.1152 | 11.2    |
+| No log        | 1.0   | 8    | 3.4248          | 20.3396 | 11.0333 |
+| No log        | 2.0   | 16   | 3.4079          | 17.9043 | 10.9    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ebde8585cda67a3085c400a5e112ccaccdebf9b2a4e6d54d45c26347eaff64
+oid sha256:3bf32079f2320a587710b33df4159d5d920f95d63ecc9bcd6282506c1cf25256
 size 303758277

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:448ad1508b1108d480bf816c5a8b723221a1b286ecc0ddc64bd4cd67c5d4ab0e
+oid sha256:5f5cfed86cf90cfad56f1880cf837bc50ee470fb22cc4962f13eaff3a21827cb
 size 4155