F-Haru
/

TED2020_data_finetuning

Model card Files Files and versions Community

TED2020_data_finetuning / TED-finetuning_teacher.py

F-Haru

Upload 9 files

837ef60 10 months ago

raw history blame contribute delete

No virus

3.6 kB

	#!/usr/bin/env python3
	# -- coding: utf-8 --
	"""
	Created on Fri Jun 30 08:47:31 2023

	@author: fujidai
	"""


	import torch
	from sentence_transformers import SentenceTransformer, InputExample, losses,models
	from sentence_transformers import SentenceTransformer, SentencesDataset, LoggingHandler, losses
	from sentence_transformers.readers import InputExample
	from torch.utils.data import DataLoader
	from transformers import AutoTokenizer
	from sentence_transformers.SentenceTransformer import SentenceTransformer
	import torch
	import torch.nn.functional as F
	import numpy as np
	from sentence_transformers import SentenceTransformer, util


	word_embedding_model = models.Transformer('/paraphrase-mpnet-base-v2', max_seq_length=512)# modelの指定をする
	pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension())
	#dense_model = models.Dense(in_features=pooling_model.get_sentence_embedding_dimension(),out_features=16)
	model = SentenceTransformer(modules=[word_embedding_model, pooling_model],device='mps')
	print(model)


	with open('/cos-sim_pseudo-pseudo.txt', 'r') as f:# en-pseudo-pseudo　と　en-origin の　cos_sim

	raberu = f.read()
	raberu_lines = raberu.splitlines()#改行コードごとにリストに入れている
	data = []
	for i in range(len(raberu_lines)):
	data.append(float(raberu_lines[i]))#


	with open('/cos-sim_pseudo.txt', 'r') as f:## en-pseudo　と　en-origin の　cos_sim
	raberu2 = f.read()
	raberu2_lines = raberu2.splitlines()#改行コードごとにリストに入れている
	data2 = []
	for i in range(len(raberu2_lines)):
	data2.append(float(raberu2_lines[i]))#



	with open('/en-origin.txt', 'r') as f:#TEDのenglish
	left = f.read()
	left_lines = left.splitlines()

	with open('/en-pseudo-pseudo.txt', 'r') as f:#TEDのenglishをgoogle翻訳に入れて作った他の言語にしたものをgoogle翻訳に入れて英語にしたやつ
	senter = f.read()
	senter_lines = senter.splitlines()

	with open('/en-pseudo.txt', 'r') as f:#TEDの英語じゃないほうをgoogle翻訳に入れて作った英語
	right = f.read()
	right_lines = right.splitlines()#改行コードごとにリストに入れている


	train_examples = []
	for i in range(len(left_lines)):
	pair=[]
	pair.append(left_lines[i])#left_lines側のi行目をtextsに追加している
	pair.append(senter_lines[i])
	pair.append(right_lines[i])#right_lines側のi行目をtextsに追加している
	#print(data[i]-data2[i])
	absolutely=abs(data[i]-data2[i])#コサイン類似度を引き算したものを絶対値をつけている
	#print('zettai↓')
	#print(absolutely)
	example = InputExample(texts=pair, label=absolutely)#textsをラベル付きで追加している
	#print(example)
	#label=1-data[i]の１は positive cos_sim
	train_examples.append(example)#学習として入れるものに入れている



	print(len(train_examples))

	device = torch.device('mps')
	#print(device)

	import torch.nn.functional as F


	train_dataloader = DataLoader(train_examples, shuffle=True, batch_size=8)
	train_loss = losses.MarginMSELoss(model=model,similarity_fct=F.cosine_similarity)

	#Tune the model
	model.fit(train_objectives=[(train_dataloader, train_loss)], epochs=100, warmup_steps=100,show_progress_bar=True,
	#output_path='完成2best-6-30',
	checkpoint_path='checkpoint_savename',checkpoint_save_steps=9370,#どのくらいのイテレーションごとに保存するか
	save_best_model=True)#checkpoint_save_total_limit=5,
	model.save("save_name")




	'''
	'''









	#