train_math.py model file save error

[Tshiyao]

System Info

ubuntu20
python=3.10
A100-SXM4-80GB

Who can help?

No response

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the codebase (such as scrips/, ...)
• My own task or dataset (give details below)

Reproduction

save model
total_num_steps:  64
average_step_rewards:  0.7349994
Process Process-5:
Traceback (most recent call last):
  File "/root/.conda/envs/open122/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/root/.conda/envs/open122/lib/python3.10/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/root/openr/train/mat/scripts/../../mat/envs/math/math_env_wrappers.py", line 117, in shareworker
    cmd, data = remote.recv()
  File "/root/.conda/envs/open122/lib/python3.10/multiprocessing/connection.py", line 250, in recv
    buf = self._recv_bytes()
  File "/root/.conda/envs/open122/lib/python3.10/multiprocessing/connection.py", line 414, in _recv_bytes
    buf = self._recv(4)
  File "/root/.conda/envs/open122/lib/python3.10/multiprocessing/connection.py", line 383, in _recv
    raise EOFError
EOFError

total 17
drwxr-xr-x 2 root root 4096 Dec  6 22:02 ./
drwxr-xr-x 4 root root 4096 Dec  6 22:02 ../
-rw-r--r-- 1 root root 5119 Dec  6 22:02 README.md
-rw-r--r-- 1 root root  667 Dec  6 22:02 adapter_config.json
-rw-r--r-- 1 root root   40 Dec  6 22:02 adapter_model.safetensors

Expected behavior

The program should exit normally, and the model weights should be saved properly.

[suanflower]

The same error, have you solved it?

[yy0525]

同样的错误

[meijuanwang]

同样的错误，感觉和设置了多个train env 有关，有没有哪位大佬解决了呀