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 [Helsinki-NLP/opus-mt-en-hi](https://huggingface.co/Helsinki-NLP/opus-mt-en-hi) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.5094
-- Bleu: 27.3808
-- Gen Len: 11.0333
+- Loss: 3.4093
+- Bleu: 23.0254
+- Gen Len: 13.8
 
 ## 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    | 3.5752          | 26.4986 | 10.8667 |
-| No log        | 2.0   | 16   | 3.5094          | 27.3808 | 11.0333 |
+| No log        | 1.0   | 8    | 3.4604          | 23.2036 | 13.5667 |
+| No log        | 2.0   | 16   | 3.4093          | 23.0254 | 13.8    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54db5c534ae70711b1d60b2a76322682af0a04840e85df0bd091b91ef9578470
-size 303761861
+oid sha256:d6d2a91eb3c5dedacea8ab75dcca7f26fe80199917f69082ffe7baf9c4a2042b
+size 303758277

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824ff4e115f530b4e6859ed4a3faefbaaa4d51c4560448935c967498d2584e01
+oid sha256:dda7c8a8ebdd092180a0a5ec98c9979097a978499cb42e3cc19e973fdaf1d504
 size 4155