问一下这个是为什么呢?

[citePerson]

运行train_model_ner.py
loss_fn = nn.CrossEntropyLoss()
loss函数报错。

[jsksxs360]

你好，经测试 train_model_ner.py 是可以正常运行的。你是否修改了代码？

特别注意 loss = loss_fn(pred.permute(0, 2, 1), y) 这一行，需要调换一下维度。

torch==2.0.1
transformers==4.34.0

[jsksxs360]

You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
/Users/sxu/miniconda3/envs/inst/lib/python3.8/site-packages/transformers/optimization.py:411: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
  warnings.warn(
Epoch 1/3
-------------------------------
loss: 1.614589:   0%|                        | 4/5216 [00:03<1:07:20,  1.29it/s]

[jsksxs360]

建议在 Linux 环境下运行代码，Windows 下运行可能会遇到各种问题。

新版 Windows 都自带 Linux 子系统，也可以在该系统下运行，如果不清楚的话可以搜索一下 WSL2