Added yaml traning meta data

README.md

@@ -7,7 +7,14 @@ datasets:
 - squad_v2
 model-index:
 - name: distilroberta-base-squad_v2
-  results: []
+  results:
+  - task:
+      name: Question Answering
+      type: question-answering
+    dataset:
+      type: squad_v2  # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
+      name: The Stanford Question Answering Dataset
+      args: en
 ---
 
 # distilroberta-base-squad_v2
@@ -24,7 +31,7 @@ For convenience this model is prepared to be used with the frameworks `PyTorch`,
 
 This model can handle mismatched question-context pairs. Make sure to specify `handle_impossible_answer=True` when using `QuestionAnsweringPipeline`.
 
-__Example usage:___
+__Example usage:__
 
 ```python
 >>> from transformers import AutoModelForQuestionAnswering, AutoTokenizer
@@ -92,3 +99,4 @@ The following hyperparameters were used during training:
 - Datasets 1.18.3
 - Tokenizers 0.11.6
 
+