Fine-tuning completed (fix targets being inputs itself)

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-vi](https://huggingface.co/Helsinki-NLP/opus-mt-en-vi) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2748
-- Bleu: 36.9275
+- Loss: 1.2733
+- Bleu: 37.1266
 
 ## Model description
 
@@ -40,7 +40,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 16
-- eval_batch_size: 64
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Bleu    |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|
-| 1.4944        | 1.0   | 8333  | 1.2792          | 37.1414 |
-| 1.3867        | 2.0   | 16666 | 1.2762          | 37.0670 |
-| 1.3172        | 3.0   | 24999 | 1.2748          | 36.9275 |
+| 1.4817        | 1.0   | 8333  | 1.2790          | 36.7813 |
+| 1.3955        | 2.0   | 16666 | 1.2750          | 36.9542 |
+| 1.3368        | 3.0   | 24999 | 1.2733          | 37.1266 |
 
 
 ### Framework versions