ajokar/Flair_NER
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

edit train

Browse Source
This commit is contained in:
ajokar 2025-07-22 16:15:24 +03:30
parent 8e87550213
commit 1bbc3dd13a
1 changed files with 25 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
train.py
View File

@ -33,6 +33,11 @@ from flair.embeddings import TransformerDocumentEmbeddings
#model = "HooshvareLab/bert-base-parsbert-peymaner-uncased" # جالب نبود! #model = "HooshvareLab/bert-base-parsbert-peymaner-uncased" # جالب نبود!
#model = "HooshvareLab/bert-base-parsbert-armanner-uncased" # جالب نبود! #model = "HooshvareLab/bert-base-parsbert-armanner-uncased" # جالب نبود!
def digit_correct(input_num):
if input_num <10:
return f'0{input_num}'
return str(input_num)
def main_train(model): def main_train(model):
""" """
آموزش مدل برای تسک NER آموزش مدل برای تسک NER
@ -41,7 +46,7 @@ def main_train(model):
""" """
time = datetime.datetime.now() time = datetime.datetime.now()
model_title = f"{model}--{time.year}-{time.month}-{time.day}--{time.hour}-{time.minute}-{time.second}".replace('/','--') 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') print(f'\nMODEL:: {model}\n')
#!pip install 'flair==0.10' #!pip install 'flair==0.10'
@ -54,11 +59,11 @@ def main_train(model):
#اسم دیتاست اینجا تنظیم شود #اسم دیتاست اینجا تنظیم شود
corpus = ColumnCorpus(data_folder, columns, corpus = ColumnCorpus(data_folder, columns,
#train_file = 'peyma_train.txt') #train_file = 'peyma_train.txt')
train_file = 'DATASET140402_no_aref.txt', # qavanin 36K tokens train_file = 'DATASET140402_no_aref2.txt', # qavanin 36K tokens
test_file = 'test_ds_new.txt',) # test 110 sections - 6.7K # test_file = 'test_ds_new.txt', # test 110 sections - 6.7K
#dev_file = 'dev split 2.txt' #dev_file = 'dev split 2.txt'
#max_sentence_length=500 #max_sentence_length=500
#) )
# tag to predict # tag to predict
tag_type = 'ner' tag_type = 'ner'
@ -159,16 +164,18 @@ def main_train(model):
F1 Score: {result} F1 Score: {result}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n''' ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n'''
# final_result = f"""Model Name: {model} hyperparameters = f"""learning_rate: {learning_rate} - mini_batch_size: {mini_batch_size} - max_epochs: {max_epochs}"""
# Fine-Tune Parameters: {hyperparameters}
# {train_result} final_result = f"""Model Name: {model}
# {evaluate_result}\n Fine-Tune Parameters: {hyperparameters}
# Fine_Tune time: {operation_time} {train_result}
# ------------------------------------------------------------------------------------ {evaluate_result}\n
# ------------------------------------------------------------------------------------\n Fine_Tune time: {operation_time}
# """ ------------------------------------------------------------------------------------
# save_to_file_by_address('./data/train_log.txt', final_result) ------------------------------------------------------------------------------------\n
# print(' Saving results finished! ') """
save_to_file_by_address('./data/train_log.txt', final_result)
return True return True
models = """ models = """
@ -177,8 +184,11 @@ HooshvareLab/bert-fa-base-uncased-ner-peyma
HooshvareLab/bert-base-parsbert-armanner-uncased HooshvareLab/bert-base-parsbert-armanner-uncased
HooshvareLab/bert-fa-base-uncased-ner-arman HooshvareLab/bert-fa-base-uncased-ner-arman
HooshvareLab/bert-base-parsbert-peymaner-uncased HooshvareLab/bert-base-parsbert-peymaner-uncased
HooshvareLab/distilbert-fa-zwnj-base-ner
""" """
models = """
HooshvareLab/bert-fa-base-uncased-ner-peyma
"""
# HooshvareLab/distilbert-fa-zwnj-base-ner
models_with_error= """ models_with_error= """
nicolauduran45/affilgood-ner-multilingual-v2 - error nicolauduran45/affilgood-ner-multilingual-v2 - error
Amirmerfan/bert-base-uncased-persian-ner-50k-base - error Amirmerfan/bert-base-uncased-persian-ner-50k-base - error