I am training a model with PyTorch backend. The setup is the same as what I used in the Tensorflow backend. However, it raises the AttributeError.
DeePMD-kit Version
3.0.0a0
Backend and its version
PyTorch v2.0.0.post200-gc263bd43e8e
How did you download the software?
docker
Input Files, Running Commands, Error Log, etc.
Error log:
[2024-05-11 04:58:48,328] DEEPMD INFO found 1 system(s):
[2024-05-11 04:58:48,328] DEEPMD INFO system natoms bch_sz n_bch prob pbc
[2024-05-11 04:58:48,328] DEEPMD INFO O64H128 192 1 100 1.000e+00 T
[2024-05-11 04:58:48,328] DEEPMD INFO --------------------------------------------------------------------------------------
[2024-05-11 04:58:48,331] DEEPMD INFO Start to train 400000 steps.
[2024-05-11 04:58:54,615] DEEPMD INFO batch 0: trn: rmse = 2.36e+01, rmse_e = 5.74e-01, rmse_f = 7.45e-01, lr = 1.00e-03
Traceback (most recent call last):
File "/opt/deepmd-kit/bin/dp", line 10, in
sys.exit(main())
^^^^^^
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/main.py", line 805, in main
deepmd_main(args)
File "/opt/deepmd-kit/lib/python3.11/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 346, in wrapper
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/pt/entrypoints/main.py", line 308, in main
train(FLAGS)
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/pt/entrypoints/main.py", line 280, in train
trainer.run()
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/pt/train/training.py", line 859, in run
step(step_id, model_key)
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/pt/train/training.py", line 757, in step
format_training_message_per_task(
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/loggers/training.py", line 29, in format_training_message_per_task
rmse = dict(sorted(rmse.items()))
^^^^^^^^^^
AttributeError: 'tuple' object has no attribute 'items'
Bug summary
I am training a model with PyTorch backend. The setup is the same as what I used in the Tensorflow backend. However, it raises the AttributeError.
DeePMD-kit Version
3.0.0a0
Backend and its version
PyTorch v2.0.0.post200-gc263bd43e8e
How did you download the software?
docker
Input Files, Running Commands, Error Log, etc.
Error log:
[2024-05-11 04:58:48,328] DEEPMD INFO found 1 system(s): [2024-05-11 04:58:48,328] DEEPMD INFO system natoms bch_sz n_bch prob pbc [2024-05-11 04:58:48,328] DEEPMD INFO O64H128 192 1 100 1.000e+00 T
sys.exit(main())
^^^^^^
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/main.py", line 805, in main
deepmd_main(args)
File "/opt/deepmd-kit/lib/python3.11/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 346, in wrapper
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/pt/entrypoints/main.py", line 308, in main
train(FLAGS)
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/pt/entrypoints/main.py", line 280, in train
trainer.run()
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/pt/train/training.py", line 859, in run
step(step_id, model_key)
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/pt/train/training.py", line 757, in step
format_training_message_per_task(
File "/opt/deepmd-kit/lib/python3.11/site-packages/deepmd/loggers/training.py", line 29, in format_training_message_per_task
rmse = dict(sorted(rmse.items()))
^^^^^^^^^^
AttributeError: 'tuple' object has no attribute 'items'
[2024-05-11 04:58:48,328] DEEPMD INFO -------------------------------------------------------------------------------------- [2024-05-11 04:58:48,331] DEEPMD INFO Start to train 400000 steps. [2024-05-11 04:58:54,615] DEEPMD INFO batch 0: trn: rmse = 2.36e+01, rmse_e = 5.74e-01, rmse_f = 7.45e-01, lr = 1.00e-03 Traceback (most recent call last): File "/opt/deepmd-kit/bin/dp", line 10, in
Steps to Reproduce
See the tarball.
Further Information, Files, and Links
issue_logger.tar.gz