update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Bleu
       type: bleu
-      value: 37.5209
+      value: 54.7617
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,9 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tr-en](https://huggingface.co/Helsinki-NLP/opus-mt-tr-en) on the opus_infopankki dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3456
-- Bleu: 37.5209
-- Gen Len: 13.5457
+- Loss: 0.6924
+- Bleu: 54.7617
+- Gen Len: 13.5501
 
 ## Model description
 
@@ -56,16 +56,29 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 16
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 138  | 1.4283          | 35.8087 | 13.5806 |
-| No log        | 2.0   | 276  | 1.3649          | 36.8833 | 13.5446 |
-| No log        | 3.0   | 414  | 1.3456          | 37.5209 | 13.5457 |
+| No log        | 1.0   | 412  | 1.1776          | 43.3104 | 12.9297 |
+| 1.4032        | 2.0   | 824  | 1.0750          | 45.7912 | 12.9155 |
+| 1.2268        | 3.0   | 1236 | 1.0019          | 47.6255 | 12.9251 |
+| 1.141         | 4.0   | 1648 | 0.9411          | 49.0649 | 12.9302 |
+| 1.0651        | 5.0   | 2060 | 0.8929          | 50.4894 | 12.9066 |
+| 1.0651        | 6.0   | 2472 | 0.8519          | 51.5072 | 12.9067 |
+| 1.0025        | 7.0   | 2884 | 0.8180          | 52.5035 | 12.8875 |
+| 0.9582        | 8.0   | 3296 | 0.7893          | 51.7587 | 13.5338 |
+| 0.9173        | 9.0   | 3708 | 0.7655          | 52.3566 | 13.5376 |
+| 0.8892        | 10.0  | 4120 | 0.7449          | 53.0488 | 13.5545 |
+| 0.8639        | 11.0  | 4532 | 0.7285          | 53.5965 | 13.5539 |
+| 0.8639        | 12.0  | 4944 | 0.7152          | 53.9433 | 13.5547 |
+| 0.8424        | 13.0  | 5356 | 0.7053          | 54.2509 | 13.5502 |
+| 0.8317        | 14.0  | 5768 | 0.6981          | 54.5339 | 13.5502 |
+| 0.817         | 15.0  | 6180 | 0.6938          | 54.7068 | 13.5448 |
+| 0.8155        | 16.0  | 6592 | 0.6924          | 54.7617 | 13.5501 |
 
 
 ### Framework versions