End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Bleu
       type: bleu
-      value: 26.9265
+      value: 31.0896
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [DevAibest/opus-mt-en-fr-finetuned-en-to-fr](https://huggingface.co/DevAibest/opus-mt-en-fr-finetuned-en-to-fr) on the opus_books dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6538
-- Bleu: 26.9265
-- Gen Len: 34.161
+- Loss: 1.4114
+- Bleu: 31.0896
+- Gen Len: 33.5809
 
 ## Model description
 
@@ -54,32 +54,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 15
+- num_epochs: 8
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 398  | 1.6540          | 26.2729 | 34.3078 |
-| 1.764         | 2.0   | 796  | 1.6364          | 26.484  | 34.4081 |
-| 1.6142        | 3.0   | 1194 | 1.6313          | 26.533  | 34.273  |
-| 1.5079        | 4.0   | 1592 | 1.6291          | 26.6765 | 34.1672 |
-| 1.5079        | 5.0   | 1990 | 1.6323          | 26.8527 | 34.0352 |
-| 1.4218        | 6.0   | 2388 | 1.6314          | 26.8336 | 34.1142 |
-| 1.3423        | 7.0   | 2786 | 1.6316          | 26.8037 | 34.2929 |
-| 1.2812        | 8.0   | 3184 | 1.6361          | 26.9189 | 34.2471 |
-| 1.2421        | 9.0   | 3582 | 1.6369          | 26.9398 | 34.2674 |
-| 1.2421        | 10.0  | 3980 | 1.6413          | 26.9029 | 34.2462 |
-| 1.1991        | 11.0  | 4378 | 1.6445          | 26.9221 | 34.1811 |
-| 1.1562        | 12.0  | 4776 | 1.6495          | 26.8817 | 34.249  |
-| 1.1392        | 13.0  | 5174 | 1.6517          | 26.8928 | 34.1777 |
-| 1.1194        | 14.0  | 5572 | 1.6531          | 26.8547 | 34.2342 |
-| 1.1194        | 15.0  | 5970 | 1.6538          | 26.9265 | 34.161  |
+| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
+| 1.6129        | 1.0   | 6355  | 1.5278          | 27.2208 | 33.9963 |
+| 1.5075        | 2.0   | 12710 | 1.4722          | 28.9457 | 33.6748 |
+| 1.3883        | 3.0   | 19065 | 1.4439          | 30.2608 | 33.721  |
+| 1.3201        | 4.0   | 25420 | 1.4266          | 30.5004 | 33.7008 |
+| 1.2657        | 5.0   | 31775 | 1.4195          | 30.7612 | 33.6436 |
+| 1.2481        | 6.0   | 38130 | 1.4152          | 30.9278 | 33.5786 |
+| 1.1922        | 7.0   | 44485 | 1.4113          | 31.0464 | 33.641  |
+| 1.1774        | 8.0   | 50840 | 1.4114          | 31.0896 | 33.5809 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03621d91635c5d93bae4143dfbcf828cac802acc45ff54db86f824685b3b0cfa
+oid sha256:3f5ff7b54e3060e6b78e4c1d394f821ad8553c03de955e41f7d65a686d61a716
 size 298763205