from fasNLP_dataloader import Semeval_task_8_corpus_Pipe
from fastNLP.core import AccuracyMetric,CrossEntropyLoss,Adam
import json
from fastNLP.core.const import Const as C
from fastNLP import Trainer
config =BertConfig.from_json_file(bert_config_txt_path)
bert_word_dims =config.hidden_size
bert_model_real =BertModel.from_pretrained(pretrained_model_name_or_path=english_bert_base_dir_)
if __name__ == '__main__':
print('##'*10)
data_pipe = Semeval_task_8_corpus_Pipe().process_from_file({'train': train_data_path, 'test': test_data_path})
print('##'*10)
with open(relation2id_dict_path, mode='rt', encoding='utf-8') as dict_inp:
relation2id_dict = json.load(dict_inp)
c_bert_model =C_Bert_for_RE_model(bert_dims=bert_word_dims,n_class=len(relation2id_dict),bert_model=bert_model_real,dropout=0.1)
metric =AccuracyMetric(pred=C.OUTPUT,target=C.TARGET)
loss =CrossEntropyLoss(pred=C.OUTPUT,target=C.TARGET)
optimizer =Adam(lr=learning_rate,model_params=c_bert_model.parameters())
trainer =Trainer(train_data=data_pipe.get_dataset('train'),dev_data=data_pipe.get_dataset('test'),model=c_bert_model,optimizer=optimizer, \
metrics=metric,batch_size=BATCH_SIZE,n_epochs=EPOCHES_NUM,save_path='c_bert_model_save_dir',loss=loss \
)
result =trainer.train(load_best_model=True)
print('训练完毕，全局信息:')
for i,j in result.items():
print(i,':',j)
bert_tokenizer=arg.bert_dir, cut_text=512,
get_index=True, concat='bert',
)
else:
raise RuntimeError(f'NOT support {arg.task} task yet!')
# define model
model = BertForNLI(class_num=len(data_info.vocabs[Const.TARGET]), bert_dir=arg.bert_dir)
# define trainer
trainer = Trainer(train_data=data_info.datasets[arg.train_dataset_name], model=model,
optimizer=Adam(lr=arg.lr, model_params=model.parameters()),
batch_size=torch.cuda.device_count() * arg.batch_size_per_gpu,
n_epochs=arg.n_epochs, print_every=-1,
dev_data=data_info.datasets[arg.dev_dataset_name],
metrics=AccuracyMetric(), metric_key='acc',
device=[i for i in range(torch.cuda.device_count())],
check_code_level=-1,
save_path=arg.save_path)
# train model
trainer.train(load_best_model=True)
# define tester
tester = Tester(
data=data_info.datasets[arg.test_dataset_name],
model=model,
metrics=AccuracyMetric(),
batch_size=torch.cuda.device_count() * arg.batch_size_per_gpu,
device=[i for i in range(torch.cuda.device_count())],
)
FitlogCallback(
{
'dev_matched': data_info.datasets['dev_matched'],
'dev_mismatched': data_info.datasets['dev_mismatched']
},
verbose=1))
trainer = Trainer(train_data=data_info.datasets['train'],
model=model,
optimizer=optimizer,
num_workers=0,
batch_size=arg.batch_size,
n_epochs=arg.n_epochs,
print_every=-1,
dev_data=data_info.datasets[arg.devset_name],
metrics=AccuracyMetric(pred="pred", target="target"),
metric_key='acc',
device=[i for i in range(torch.cuda.device_count())],
check_code_level=-1,
callbacks=callbacks,
loss=CrossEntropyLoss(pred="pred", target="target"))
trainer.train(load_best_model=True)
tester = Tester(
data=data_info.datasets[arg.testset_name],
model=model,
metrics=AccuracyMetric(),
batch_size=arg.batch_size,
device=[i for i in range(torch.cuda.device_count())],
)
tester.test()
raise RuntimeError(f'NOT support {arg.task} task yet!')
# define model
model = BertForNLI(class_num=len(data_info.vocabs[Const.TARGET]),
bert_dir=arg.bert_dir)
# define trainer
trainer = Trainer(train_data=data_info.datasets[arg.train_dataset_name],
model=model,
optimizer=Adam(lr=arg.lr, model_params=model.parameters()),
batch_size=torch.cuda.device_count() *
arg.batch_size_per_gpu,
n_epochs=arg.n_epochs,
print_every=-1,
dev_data=data_info.datasets[arg.dev_dataset_name],
metrics=AccuracyMetric(),
metric_key='acc',
device=[i for i in range(torch.cuda.device_count())],
check_code_level=-1,
save_path=arg.save_path)
# train model
trainer.train(load_best_model=True)
# define tester
tester = Tester(
data=data_info.datasets[arg.test_dataset_name],
model=model,
metrics=AccuracyMetric(),
batch_size=torch.cuda.device_count() * arg.batch_size_per_gpu,
device=[i for i in range(torch.cuda.device_count())],