Training complete

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5348
-- Bleu: 1.2509
-- Gen Len: 18.6341
+- Loss: 0.4378
+- Bleu: 42.8631
+- Gen Len: 18.3111
 
 ## Model description
 
@@ -47,10 +47,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
-| No log        | 1.0   | 16   | 1.5907          | 1.2611 | 18.7073 |
-| No log        | 2.0   | 32   | 1.5348          | 1.2509 | 18.6341 |
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| No log        | 1.0   | 217  | 0.4711          | 41.9733 | 18.3111 |
+| No log        | 2.0   | 434  | 0.4378          | 42.8631 | 18.3111 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8722c684e97b6228796a45fecf95c449ca30b45aa6d975eaf16b2314fda246
+oid sha256:f3460f43c90c4aecb8956390c39abc79507323ce11cb3041e108c6e7dd0347d0
 size 990345064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe7286923b2014d69a1a0724a1c226da056fea18a31a6e5d4c94826304956935
+oid sha256:31b62591b3520bb8c35222049ca1ebf201566c6605bd32fb56cbb56108a4daea
 size 4856