Update README.md

README.md

@@ -3,7 +3,7 @@ tags:
 - translation
 - generated_from_trainer
 datasets:
-- cmu_hinglish_do_g
+- cmu_hinglish_dog
 metrics:
 - bleu
 model-index:
@@ -13,8 +13,8 @@ model-index:
       name: Sequence-to-sequence Language Modeling
       type: text2text-generation
     dataset:
-      name: cmu_hinglish_do_g
-      type: cmu_hinglish_do_g
+      name: cmu_hinglish_dog
+      type: cmu_hinglish_dog
       args: hi_en-en
     metrics:
     - name: Bleu
@@ -27,7 +27,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # t5-small_6_3-hi_en-to-en
 
-This model was trained from scratch on the cmu_hinglish_do_g dataset.
+This model was trained from scratch on the cmu_hinglish_dog dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.3662
 - Bleu: 18.0863
@@ -35,7 +35,9 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+Model generated using:
+```python make_student.py t5-small t5_small_6_3 6 3```
+Check this [link](https://discuss.huggingface.co/t/questions-on-distilling-from-t5/1193/9) for more information.
 
 ## Intended uses & limitations
 
@@ -43,7 +45,14 @@ More information needed
 
 ## Training and evaluation data
 
-More information needed
+Used cmu_hinglish_dog dataset. Please check this [link](https://huggingface.co/datasets/cmu_hinglish_dog) for dataset description
+ 
+## Translation:
+
+* Source: hi_en: The text in Hinglish
+* Target: en: The text in English
+
+
 
 ## Training procedure
 
@@ -166,6 +175,12 @@ The following hyperparameters were used during training:
 | 1.9924        | 99.0  | 12474 | 2.1760          | 14.7756 | 12.3832 |
 | 1.9903        | 100.0 | 12600 | 2.1761          | 14.7713 | 12.3822 |
 
+### Evaluation results
+
+| Data Split |   Bleu  |
+|:----------:|:-------:|
+| Validation | 17.8061 |
+|    Test    | 18.0863 |
 
 ### Framework versions