xueyouluo / ccks2021-track2-code Goto Github PK
View Code? Open in Web Editor NEW“英特尔创新大师杯”深度学习挑战赛 赛道2:CCKS2021中文NLP地址要素解析
“英特尔创新大师杯”深度学习挑战赛 赛道2:CCKS2021中文NLP地址要素解析
您好,因为计算机资源不够,无法进行模型训练,请问能给一份训练好的模型数据吗?###
大佬~能求一份比赛数据集吗?原来的数据集已经在官网下架了,[email protected] 谢谢大佬
您好~请问一下我再运行您代码的时候
在code/assemble.py里
assert len(data[0)==len(weights)出现了AssertionError的错误,请问您了解解决方案吗,或者具体是哪里出的问题呢
用多张Tesla T4(16G)的机器来跑,报显存不足,虽然有多张卡,但只用到其中一张的资源
把预训练的batch调小后能跑通,但后面模型训练还是会报显存不足,后来用simple跑下来了。
现在就想怎么能充分利用多张卡的性能,请教大佬,假如要支持多卡跑的话,需要改哪些地方?谢谢~
`2022-05-07 21:34:05.589168: I tensorflow/core/common_runtime/bfc_allocator.cc:824] Stats:
Limit: 14854298010
InUse: 14655244288
MaxInUse: 14662447616
NumAllocs: 8390
MaxAllocSize: 216728064
2022-05-07 21:34:05.589326: W tensorflow/core/common_runtime/bfc_allocator.cc:319] ****************************************************************************************************
2022-05-07 21:34:05.589344: W tensorflow/core/framework/op_kernel.cc:1502] OP_REQUIRES failed at cast_op.cc:109 : Resource exhausted: OOM when allocating tensor with shape[24,43,64,1024] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1356, in _do_call
return fn(*args)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1341, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1429, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: 2 root error(s) found.
(0) Resource exhausted: OOM when allocating tensor with shape[43,21128,1024] and type half on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[{{node gradients/generator_predictions/MatMul_grad/MatMul_1}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
[[cond_1/LogicalAnd_1/_25229]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
(1) Resource exhausted: OOM when allocating tensor with shape[43,21128,1024] and type half on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[{{node gradients/generator_predictions/MatMul_grad/MatMul_1}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
0 successful operations.
0 derived errors ignored.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "run_pretraining.py", line 425, in
main()
File "run_pretraining.py", line 421, in main
args.model_name, args.data_dir, **hparams))
File "run_pretraining.py", line 384, in train_or_eval
max_steps=config.num_train_steps)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 367, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 1158, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 1192, in _train_model_default
saving_listeners)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 1484, in _train_with_estimator_spec
_, loss = mon_sess.run([estimator_spec.train_op, estimator_spec.loss])
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/monitored_session.py", line 754, in run
run_metadata=run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/monitored_session.py", line 1252, in run
run_metadata=run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/monitored_session.py", line 1353, in run
raise six.reraise(*original_exc_info)
File "/usr/local/lib/python3.6/dist-packages/six.py", line 693, in reraise
raise value
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/monitored_session.py", line 1338, in run
return self._sess.run(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/monitored_session.py", line 1411, in run
run_metadata=run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/monitored_session.py", line 1169, in run
return self._sess.run(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 950, in run
run_metadata_ptr)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1173, in _run
feed_dict_tensor, options, run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1350, in _do_run
run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1370, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: 2 root error(s) found.
(0) Resource exhausted: OOM when allocating tensor with shape[43,21128,1024] and type half on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node gradients/generator_predictions/MatMul_grad/MatMul_1 (defined at /code/electra-pretrain/model/optimization.py:66) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
[[cond_1/LogicalAnd_1/_25229]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
(1) Resource exhausted: OOM when allocating tensor with shape[43,21128,1024] and type half on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node gradients/generator_predictions/MatMul_grad/MatMul_1 (defined at /code/electra-pretrain/model/optimization.py:66) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
0 successful operations.
0 derived errors ignored.
`
大佬你好啊~我不太理解github主页的实验中,实验8:biaffine+bert+electra 为什么两个预训练模型,他们分别的作用是啥?
是把两个预训练模型融合成一个预训练模型的意思么?
另外electra pretain 是指用自己的数据重新预训练了一下吗?
感谢
大佬可以发一份.conll的完整数据吗,官网的数据看起来是乱码,邮箱是 [email protected]
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.