update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Bleu
       type: bleu
-      value: 46.9185
+      value: 32.1971
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,11 +29,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # en2zh_opus_100
 
-This model is a fine-tuned version of [HAJIWEE/en2zh_opus_100](https://huggingface.co/HAJIWEE/en2zh_opus_100) on the opus100 dataset.
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the opus100 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5395
-- Bleu: 46.9185
-- Gen Len: 7.686
+- Loss: 1.0868
+- Bleu: 32.1971
+- Gen Len: 7.209
 
 ## Model description
 
@@ -52,26 +52,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0004
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 2e-05
+- train_batch_size: 6
+- eval_batch_size: 6
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 2
-- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step   | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|
-| 0.5549        | 1.0   | 62500  | 0.5596          | 46.7419 | 7.7295  |
-| 0.5389        | 2.0   | 125000 | 0.5395          | 46.9185 | 7.686   |
+| 1.2742        | 1.0   | 166667 | 1.2032          | 28.4915 | 7.303   |
+| 1.0931        | 2.0   | 333334 | 1.0868          | 32.1971 | 7.209   |
 
 
 ### Framework versions
 
-- Transformers 4.27.1
-- Pytorch 1.13.1+cu116
-- Datasets 2.10.1
+- Transformers 4.27.4
+- Pytorch 2.0.0
+- Datasets 2.11.0
 - Tokenizers 0.13.2