The esca_code from wanghn95

code

你好作者，我对你的研究很感兴趣，希望能够复现论文中的模型，是否可以放出完整代码呢，非常感谢！

咨询pretrain extractor时的问题，以及如果正确运行应该会输出什么

您好！我现在正在尝试使用您的代码复现模型，现在遇到了这个bug：
RuntimeError: MAGMA getrf : U(4,4) is 0, U is singular at /opt/conda/conda-bld/pytorch_1556653099582/work/aten/src/THC/generic/THCTensorMathMagma.cu:363
在NVIDIA/waveglow#63 这个issue中我看到了类似的问题，这里面说修改其他cudnn版本可能可以解决这个问题。我现在是在Linux云服务器上运行，cudnn版本是7.6.5，system cuda version是CUDA Version 10.0.130 (命令行cat /usr/local/cuda/version.txt)。
我想请问您是否了解类似问题的解决方式呢？如果您也不清楚的话，我想问问您这边使用的环境是什么呢？我看看换环境是否是问题所在。

我的调用命令：
nohup python -u mypath/Esca_Code/BERT/src/train.py --pairwise -task ext -mode train -bert_data_path mypath/bert_data_cnndm_final/cnndm -ext_dropout 0.1 -model_path mypath/test_models/ -lr 0.01 -visible_gpus 1,2,3 -report_every 10 -save_checkpoint_steps 100 -batch_size 300 -train_steps 1000 -accum_count 2 -log_file mypath/logs/bert_extractor.log -use_interval true -warmup_steps 1000 -max_pos 512 -temp_dir mypath/bertcache/ -result_path mypath/test_results/ >> mypath/logs/nohup3.log 2>&1 &

我按照您的README文件配的代码环境。比较相关的包版本：
Python 3.6.13
pip 21.3.1
wheel 0.37.0
torch 1.1.0
torchvision 0.3.0
pytorch-transformers 1.2.0
numpy 1.16.4
multiprocess 0.70.12.2
pyrouge 0.1.3
tensorboard 2.7.0
tensorboard-data-server 0.6.1
tensorboard-plugin-wit 1.8.0
tensorboardX 2.4.1

完整的报错内容（我不知道在此之前的报告内容是否还需要）：

Traceback (most recent call last):
  File "mypath/Esca_Code/BERT/src/train.py", line 182, in <module>
    train_ext(args, device_id)
  File "mypath/Esca_Code/BERT/src/train_extractive.py", line 206, in train_ext
    train_multi_ext(args)
  File "mypath/Esca_Code/BERT/src/train_extractive.py", line 49, in train_multi_ext
    p.join()
  File "mypath/anaconda3/envs/envesca/lib/python3.6/multiprocessing/process.py", line 124, in join
    res = self._popen.wait(timeout)
  File "mypath/anaconda3/envs/envesca/lib/python3.6/multiprocessing/popen_fork.py", line 50, in wait
    return self.poll(os.WNOHANG if timeout == 0.0 else 0)
  File "mypath/anaconda3/envs/envesca/lib/python3.6/multiprocessing/popen_fork.py", line 28, in poll
    pid, sts = os.waitpid(self.pid, flag)
  File "mypath/Esca_Code/BERT/src/train_extractive.py", line 106, in signal_handler
    raise Exception(msg)
Exception: 

-- Tracebacks above this line can probably
                 be ignored --

Traceback (most recent call last):
  File "mypath/Esca_Code/BERT/src/train_extractive.py", line 64, in run
    train_single_ext(args, device_id)
  File "mypath/Esca_Code/BERT/src/train_extractive.py", line 264, in train_single_ext
    trainer.train(train_iter_fct, args.train_steps)
  File "mypath/Esca_Code/BERT/src/models/trainer_ext.py", line 148, in train
    report_stats)
  File "mypath/Esca_Code/BERT/src/models/trainer_ext.py", line 313, in _gradient_accumulation
    sent_scores, mask = self.model(src, segs, clss, mask, mask_cls)
  File "mypath/anaconda3/envs/envesca/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "mypath/Esca_Code/BERT/src/models/model_builder.py", line 266, in forward
    sent_scores = self.cal_matrix0(sents_vec, mask_cls)
  File "mypath/Esca_Code/BERT/src/models/model_builder.py", line 241, in cal_matrix0
    D_ = torch.inverse(tmp_D)
RuntimeError: MAGMA getrf : U(4,4) is 0, U is singular at /opt/conda/conda-bld/pytorch_1556653099582/work/aten/src/THC/generic/THCTensorMathMagma.cu:363

mypath/anaconda3/envs/envesca/lib/python3.6/multiprocessing/semaphore_tracker.py:143: UserWarning: semaphore_tracker: There appear to be 3 leaked semaphores to clean up at shutdown
  len(cache))
mypath/anaconda3/envs/envesca/lib/python3.6/multiprocessing/semaphore_tracker.py:143: UserWarning: semaphore_tracker: There appear to be 3 leaked semaphores to clean up at shutdown
  len(cache))
mypath/anaconda3/envs/envesca/lib/python3.6/multiprocessing/semaphore_tracker.py:143: UserWarning: semaphore_tracker: There appear to be 3 leaked semaphores to clean up at shutdown
  len(cache))

wanghn95 / esca_code Goto Github PK

esca_code's People

Contributors

Stargazers

Watchers

Forkers

esca_code's Issues

code

咨询pretrain extractor时的问题，以及如果正确运行应该会输出什么

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent