Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -22,6 +22,8 @@ It is based on a BERT architecture, but trained from scratch on the SQuAD datase
22
  ## Score
23
  The score is **~20%**. (`{'exact_match': 10.387890255439924, 'f1': 19.81830726643602}`)
24
 
 
 
25
  ## Training code
26
  You can find the full training code as `train.py` in this repo :-)
27
 
 
22
  ## Score
23
  The score is **~20%**. (`{'exact_match': 10.387890255439924, 'f1': 19.81830726643602}`)
24
 
25
+ ## Benchmark
26
+ The score is **~20%**, compared to the astounding 87% on BERT SQuAD
27
  ## Training code
28
  You can find the full training code as `train.py` in this repo :-)
29