Update distillation.py

distillation.py

@@ -36,8 +36,8 @@ teacher_model_name = '/Users/fujidai/sinTED/paraphrase-mpnet-base-v2'   #Our mon
 student_model_name = '/Users/fujidai/dataseigen/09-MarginMSELoss-finetuning-7-5'       #Multilingual base model we use to imitate the teacher model
 
 max_seq_length = 128                #Student model max. lengths for inputs (number of word pieces)
-train_batch_size = 128               #Batch size for training
-inference_batch_size = 128           #Batch size at inference
+train_batch_size = 64               #Batch size for training
+inference_batch_size = 64           #Batch size at inference
 max_sentences_per_language = 500000 #Maximum number of  parallel sentences for training
 train_max_sentence_length = 250     #Maximum length (characters) for parallel training sentences