Update batch size

README.md

@@ -42,7 +42,7 @@ For training, three datasets were used:
 - train_batch_size: 25 (on 2 GPUs)
 - eval_batch_size: 8
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 16x2x2=64
+- total_train_batch_size: 25x2x2=100
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500