README.md is added

README.md

@@ -0,0 +1,32 @@
+# BERT Base Uncased Finetuned on NewsQA
+
+Examples with `noAnswer` and `badQuestion` are not included in the training process.
+
+```shell
+$ cd ~/projects/transformers/examples/legacy/question-answering
+$ mkdir bert_base_uncased_finetuned_newsqa
+$ python run_newsqa.py \
+    --model_type bert \
+    --model_name_or_path "bert-base-uncased" \
+    --do_train \
+    --do_eval \
+    --do_lower_case \
+    --num_train_epochs 2 \
+    --per_gpu_train_batch_size 8 \
+    --per_gpu_eval_batch_size 32 \
+    --max_seq_length 384 \
+    --max_grad_norm inf \
+    --doc_stride 128 \
+    --train_file "~/projects/data/newsqa/combined-newsqa-data-v1.json" \
+    --predict_file "~/projects/data/newsqa/combined-newsqa-data-v1.json" \
+    --output_dir "./bert_base_uncased_finetuned_newsqa" \
+    --save_steps 20000
+```
+
+Results:
+
+```shell
+{'exact': 60.19350380096752, 'f1': 73.29371985128037, 'total': 4341, 'HasAns_exact': 60.19350380096752, 'HasAns_f1': 73.29371985128037, 'HasAns_total': 4341, 'best_exact': 60.19350380096752, 'best_exact_thresh': 0.0, 'best_f1': 73.29371985128037, 'best_f1_thresh': 0.0}
+```
+
+To prepare the database, follow the instructions on the [NewsQA](https://github.com/Maluuba/newsqa) repository.