update model card README.md

EN-DE-TR-TED/README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0925
-- Bleu: 13.5721
-- Gen Len: 16.934
+- Loss: 1.0640
+- Bleu: 14.4121
+- Gen Len: 16.8629
 
 ## Model description
 
@@ -39,24 +39,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5.6e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 10
+- eval_batch_size: 10
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 99   | 1.1146          | 13.2449 | 16.9239 |
-| No log        | 2.0   | 198  | 1.0925          | 13.5721 | 16.934  |
+| No log        | 1.0   | 79   | 1.1263          | 12.8366 | 16.9239 |
+| No log        | 2.0   | 158  | 1.0793          | 13.7051 | 16.8579 |
+| No log        | 3.0   | 237  | 1.0690          | 14.4571 | 16.8629 |
+| No log        | 4.0   | 316  | 1.0647          | 14.6162 | 16.8629 |
+| No log        | 5.0   | 395  | 1.0640          | 14.4121 | 16.8629 |
 
 
 ### Framework versions
 
-- Transformers 4.26.1
-- Pytorch 1.13.1+cu116
-- Datasets 2.10.1
-- Tokenizers 0.13.2
+- Transformers 4.27.4
+- Pytorch 2.0.0+cu118
+- Datasets 2.11.0
+- Tokenizers 0.13.3