From c21d1bd22a4ebff0c10d3069539dea595021fbaf Mon Sep 17 00:00:00 2001
From: init_mahdi <initmahdi@gmail.com>
Date: Sun, 17 Aug 2025 15:23:20 +0330
Subject: [PATCH] insert some comments in code

---
 requierments.txt |  3 ++-
 train.py         | 37 +++++++++++++++----------------------
 2 files changed, 17 insertions(+), 23 deletions(-)

diff --git a/requierments.txt b/requierments.txt
index 3f09d8d..46bf30a 100644
--- a/requierments.txt
+++ b/requierments.txt
@@ -1,2 +1,3 @@
 pip install numpy = 1.24.3
-pip show hazm = 0.10.0
\ No newline at end of file
+pip show hazm = 0.10.0
+pip show flair == 0.10
diff --git a/train.py b/train.py
index 91037c2..e8d91b7 100644
--- a/train.py
+++ b/train.py
@@ -42,21 +42,20 @@ def main_train(model):
     """
     آموزش مدل برای تسک NER
     
-    :model نام مدلی که قرار است آموزش داده شود
+    Args:
+        model(str): نام مدلی که قرار است آموزش داده شود
     """
     
     time = datetime.datetime.now()
     model_title = f"{time.year}-{digit_correct(time.month)}-{digit_correct(time.day)}--{digit_correct(time.hour)}-{digit_correct(time.minute)}-{digit_correct(time.second)}--{model}".replace('/','--')
     print(f'\nMODEL:: {model}\n')
 
-    #!pip install 'flair==0.10'
-
-    # define columns
+    # define dataset columns
     columns = {0 : 'text', 1 : 'ner'}
-    # directory where the data resides
+    # directory of data files
     data_folder = './data/'
-    # initializing the corpuscorpus = ColumnCorpus(data_folder, columns, train_file='peyma_train.txt', sequence_length=512)
-    #اسم دیتاست اینجا تنظیم شود 
+
+    #آدرس فایل دیتاست اینجا تنظیم شود 
     corpus = ColumnCorpus(data_folder, columns,
                                 #train_file = 'peyma_train.txt')
                                 train_file = 'DATASET140402_no_aref2.txt', # qavanin 36K tokens
@@ -70,8 +69,6 @@ def main_train(model):
     # make tag dictionary from the corpus
     tag_dictionary = corpus.make_label_dictionary(label_type=tag_type)
 
-    #xlm-roberta-large
-    # embeddings = TransformerWordEmbeddings(model='HooshvareLab/distilbert-fa-zwnj-base-ner',
     embeddings = TransformerWordEmbeddings(model= model,
                                         layers="-1",
                                         subtoken_pooling="first",
@@ -97,23 +94,17 @@ def main_train(model):
     except Exception as e:
         print(str(e.args[0]))
         return
-        
-
-    from flair.trainers import ModelTrainer
+    
+    print('tagger initialized successfully !')
+    
     try:
-
         trainer = ModelTrainer(tagger, corpus)
-        #resources/taggers/sota-ner-flert
-        # trainer.fine_tune('./taggers',
-        #                   learning_rate=2.0e-6,
-        #                   mini_batch_size=16,
-        #                 #   mini_batch_chunk_size=1,  # remove this parameter to speed up computation if you have a big GPU
-        #                   max_epochs=20
-        #                   )
+
     except Exception as e:
         print(str(e.args[0]))
         return
-        
+    
+    # begin training data    
     try:
         result = trainer.fine_tune(f"./taggers/{model_title}",
                                 learning_rate= learning_rate,
@@ -123,7 +114,9 @@ def main_train(model):
     except Exception as e:
         print(str(e.args[0]))
         return
-
+    print(f'training finished successfully!')
+    
+    # plot training log to evaluate process
     try:
         from train_log_plotter import plot_diagram
         plot_diagram(model_title)