Update README.md

README.md

@@ -22,7 +22,7 @@ models.
 
 # Model Description
 
-This model is fine-tuned on the SQuAD2.0 dataset. Fine-tuning the biomedical language model on the SQuAD dataset helps improve the score on the BioASQ challenge. If you plan to work with BioASQ or biomedical QA tasks, it's better to use this model over BioM-ELECTRA-Large. This model (TensorFlow version ) took the lead in the BioASQ9b-Factoid challenge (Batch 5) under the name of (UDEL-LAB2). To see the full details of BioASQ9B results, please check this link http://participants-area.bioasq.org/results/9b/phaseB/ ( you need to register). 
+We fine-tuned BioM-ELECTRA-Large, which was pre-trained on PubMed Abstracts, on the SQuAD2.0 dataset. Fine-tuning the biomedical language model on the SQuAD dataset helps improve the score on the BioASQ challenge. If you plan to work with BioASQ or biomedical QA tasks, it's better to use this model over BioM-ELECTRA-Large. This model (TensorFlow version ) took the lead in the BioASQ9b-Factoid challenge (Batch 5) under the name of (UDEL-LAB2). To see the full details of BioASQ9B results, please check this link http://participants-area.bioasq.org/results/9b/phaseB/ ( you need to register). 
 
 Huggingface library doesn't implement Layer-Wise decay feature, which affects the performance on SQuAD task. The reported result of BioM-ELECTRA-SQuAD in our paper is 88.3 (F1) since we use ELECTRA open-source code with TF checkpoint, which uses Layer-Wise decay. 
 
@@ -43,7 +43,7 @@ run_qa.py --model_name_or_path sultan/BioM-ELECTRA-Large-Discriminator \
 --doc_stride 128 \
 --per_device_train_batch_size 8 \
 --gradient_accumulation_steps 6 \
---per_device_eval_batch_size 128 \
+--per_device_eval_batch_size 128 
 --fp16 \
 --fp16_opt_level O1 \
 --logging_steps 50 \