Flair_NER/train.py

learning_rate   = 0.65e-4 # 0.65e-4 - 0.4e-4
mini_batch_size = 8
max_epochs      = 200

from funcs import save_to_file_by_address
import json
import os
from pathlib import Path
from flair.data import Corpus
from flair.datasets import ColumnCorpus
from flair.embeddings import TransformerWordEmbeddings
from flair.models import SequenceTagger
from flair.trainers import ModelTrainer
from flair.models import SequenceTagger
from flair.embeddings import TransformerDocumentEmbeddings

#model = os.getcwd() + "\\data\\final-model.pt"
#model = os.getcwd() + "/data/HooshvareLab--distilbert-fa-zwnj-base-ner" # مدل اولیه که تست شد و تا حدود 70 درصد در آخرین آموزش خوب جواب می داد
#model = os.getcwd() + "/data/distilbert-base-multilingual-cased-tavasi"
# model = "HooshvareLab/bert-fa-base-uncased-ner-peyma"
# model = "PooryaPiroozfar/Flair-Persian-NER" # 111111111111111

## ---------------------------------------------------------
## --- آخرین کار مورد استفاده در سامانه قانون یار از این آموزش دیده است
#model = "orgcatorg/xlm-v-base-ner" # بهترین توکنایزر فارسی ***********************
## ---------------------------------------------------------
# model = AutoModel.from_pretrained("/home/gpu/HFHOME/hub/models--orgcatorg--xlm-v-base-ner")

#model = "pourmand1376/NER_Farsi" # 
#model = "HooshvareLab/bert-base-parsbert-ner-uncased"   # ****  خوب جواب داد
#model = "SeyedAli/Persian-Text-NER-Bert-V1"             # ***** خیلی خوب جواب داد
#model = "HooshvareLab/bert-base-parsbert-peymaner-uncased" # جالب نبود!
#model = "HooshvareLab/bert-base-parsbert-armanner-uncased" # جالب نبود!
"""
HooshvareLab/bert-base-parsbert-ner-uncased
HooshvareLab/bert-fa-base-uncased-ner-peyma
HooshvareLab/bert-base-parsbert-armanner-uncased
HooshvareLab/bert-fa-base-uncased-ner-arman
HooshvareLab/bert-base-parsbert-peymaner-uncased
HooshvareLab/distilbert-fa-zwnj-base-ner
nicolauduran45/affilgood-ner-multilingual-v2 - error
Amirmerfan/bert-base-uncased-persian-ner-50k-base - error
AliFartout/Roberta-fa-en-ner - error
"""
model = 'HooshvareLab/bert-base-parsbert-ner-uncased'

print(model)
print('#'*50)
print('#'*50)

#!pip install 'flair==0.10'

# define columns
columns = {0 : 'text', 1 : 'ner'}
# directory where the data resides
data_folder = './data/'
# initializing the corpuscorpus = ColumnCorpus(data_folder, columns, train_file='peyma_train.txt', sequence_length=512)
#اسم دیتاست اینجا تنظیم شود 
corpus = ColumnCorpus(data_folder, columns,
                            #train_file = 'peyma_train.txt')
                              train_file = 'DATASET140402_no_aref.txt', # qavanin 36K tokens
                              test_file = 'test_ds_new.txt',) # test 110 sections - 6.7K
                              #dev_file = 'dev split 2.txt'
                              #max_sentence_length=500
                              #)

# tag to predict
tag_type = 'ner'
# 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",
                                    #    pooling='mean',
                                       fine_tune=True,
                                       use_context=True,
                                       from_tf=True,
                                       allow_long_sentences=True
                                    #    model_max_length=512,
                                       )

print('model read successfully !')
print('#'*50)
print('#'*50)
try:
    tagger = SequenceTagger(hidden_size=256,
                            embeddings=embeddings,
                            tag_dictionary= tag_dictionary,
                            tag_type='ner',
                            use_crf=False,
                            use_rnn=False,
                            reproject_embeddings=False
                            )
except Exception as e:
    print(str(e.args[0]))
    exit()
    

from flair.trainers import ModelTrainer
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]))
    exit()
    
try:
    result = trainer.fine_tune('./taggers',
                               learning_rate= learning_rate,
                               mini_batch_size= mini_batch_size,
                               max_epochs= max_epochs
                               )
except Exception as e:
    print(str(e.args[0]))
    exit()
try:
    # Save the model's state dictionary (configuration + weights)
    #model_state_dict_path = Path('./trained/best-model.pt')  # Assuming best model is saved here
    #tagger.save(model_state_dict_path)

    # Optionally, save additional hyperparameters to a separate file (e.g., training.json)
    hyperparameters = {
        "learning_rate": learning_rate,
        "mini_batch_size": mini_batch_size,
        "max_epochs": max_epochs,
    }

    with open('./trained/training.json', 'w') as f:
        json.dump(hyperparameters, f, indent=4)
except Exception as e:

    exit()

try:
    from train_log_plotter import plot_diagram
    plot_diagram()
except:
    print('log diagram failed due to error!')

train_result = f'''************************************************\n
##### TRAIN RESULT #####
F1 Score: {result}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n'''

# اجرای اینفرنس جهت ارزیابی مدل
# time = datetime.datetime.now()
# tagger.save('./trained/trained-model ' + str(time) + '.pt')
print('#'*70)
print( '           ********** fine-tune operation finished **********           ')
import datetime
operation_time = datetime.datetime.now()
print(f'           **********  {operation_time}  **********           ')
print('#'*70)

# ###################################################
# تست مدل بر یک مقدار مشخص شده
print(' Try to test trained model! ')
from inference import inference_main
inference_main(model,'')
print(' Testing model finished! ')

# ###################################################
# ارزیابی مدل آموزش دیده
try:
    from evaluate_model import do_evaluate
    print(' Try to evaluating the trained model! ')
    evaluate_result = do_evaluate()
    print(' Evaluating finished! ')
except Exception as e:
    print('do_evaluate function failed')
    evaluate_result = f"do_evaluate function failed!\nerror massage:\n{str(e.args[0])}"
    
final_result = f"""Model Name: {model}
Fine-Tune Parameters: {hyperparameters}
{train_result}
{evaluate_result}\n
Fine_Tune time: {operation_time}
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------\n
"""
save_to_file_by_address('./data/train_log.txt', final_result)
print(' Saving results finished! ')