关于CENET模型训练时的报错

[mskmei]

首先非常感谢团队的工作！

我在按照默认参数训练CENet时（python -m MMSA -d mosi -m cenet -s 1111 -s 1112）遇到了一个意料之外的报错，由于其他模型都可以成功运行所以我想有可能是CENet单独的问题？报错文本如下：
Traceback (most recent call last):
File "/root/miniconda3/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/root/miniconda3/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/root/miniconda3/lib/python3.10/site-packages/MMSA/main.py", line 46, in
MMSA_run(
File "/root/miniconda3/lib/python3.10/site-packages/MMSA/run.py", line 221, in MMSA_run
result = _run(args, num_workers, is_tune)
File "/root/miniconda3/lib/python3.10/site-packages/MMSA/run.py", line 246, in _run
model = AMIO(args).to(args['device'])
File "/root/miniconda3/lib/python3.10/site-packages/MMSA/models/AMIO.py", line 49, in init
self.Model = CENET.from_pretrained(args.pretrained, config=config, pos_tag_embedding=True, senti_embedding=True, polarity_embedding=True, args=args)
File "/root/miniconda3/lib/python3.10/site-packages/pytorch_transformers/modeling_utils.py", line 539, in from_pretrained
state_dict = torch.load(resolved_archive_file, map_location='cpu')
File "/root/miniconda3/lib/python3.10/site-packages/torch/serialization.py", line 1028, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/root/miniconda3/lib/python3.10/site-packages/torch/serialization.py", line 1264, in _legacy_load
typed_storage._untyped_storage._set_from_file(
RuntimeError: storage has wrong byte size: expected %ld got %ld03072

除此以外，训练时模型后面中括号的三个数字可以请教一下分别是什么吗，比如[4/7/1]

[mskmei]

抱歉，最后一个问题我搞懂了，是[距离最佳epoch的距离/当前epoch数/随机种子]