python /nx/transformers/examples/pytorch/question-answering/run_qa.py \ --model_name_or_path /models/google-bert/bert-large-uncased-whole-word-masking-finetuned-squad \ --dataset_name squad \ --do_train \ --do_eval \ --per_device_train_batch_size 12 \ --learning_rate 3e-5 \ --num_train_epochs 2 \ --max_seq_length 384 \ --doc_stride 128 \ --output_dir /nx/transformers/debug_squad/
