Update README.md

README.md

@@ -1,36 +1,39 @@
 # roberta-base for QA
 
-# Overview
-- Language model: deepset/roberta-base-squad2
-- Language: English
-- Downstream-task: Extractive QA
-- Training data: SQuAD 2.0
-- Eval data: SQuAD 2.0
-- Code: <TBD>
-- Infrastructure: Colab TPU 
+## Overview
+**Language model:** deepset/roberta-base-squad2 </br>
+**Language:** English </br>
+**Downstream-task:** Extractive QA </br>
+**Training data:** SQuAD 2.0 </br>
+**Eval data:** SQuAD 2.0 </br>
+**Code:** <TBD> </br>
+**Infrastructure:** Colab TPU </br>
 
-# Hyperparameters
-batch_size = 8 </br>
-n_epochs = 6 </br>
-base_LM_model = "deepset/roberta-base-squad2"</br>
-max_seq_len = 386</br>
-doc_stride=128</br>
-learning_rate = 1.5e-5 </br>
-warmup_proportion = 0.2 </br>
-batch_size=8 </br>
-n_best_size=20 </br>
-max_answer_length=30 </br>
-min_null_score=7.0 </br>
-CLS_threshold=-3 </br>
+## Hyperparameters
+```
+batch_size = 8
+n_epochs = 6
+base_LM_model = "deepset/roberta-base-squad2"
+max_seq_len = 386
+doc_stride=128
+learning_rate = 1.5e-5
+warmup_proportion = 0.2
+batch_size=8
+n_best_size=20
+max_answer_length=30
+min_null_score=7.0
+CLS_threshold=-3
+```
 
-
-# Performance
-"exact": 81.192622 </br>
-"f1": 83.95408 </br>
-"total": 11873 </br>
-"HasAns_exact": 74.190283 </br>
-"HasAns_f1": 79.721119 </br>
-"HasAns_total": 5928 </br>
-"NoAns_exact": 88.174937 </br>
-"NoAns_f1": 88.174937 </br>
-"NoAns_total": 5945 </br>
+## Performance
+```
+"exact": 81.192622
+"f1": 83.95408
+"total": 11873
+"HasAns_exact": 74.190283
+"HasAns_f1": 79.721119
+"HasAns_total": 5928
+"NoAns_exact": 88.174937
+"NoAns_f1": 88.174937
+"NoAns_total": 5945
+```