-
Epoch / Total epochs: 41 / 200
100%|██████████| 568/568 [11:36
-
校友您好，能帮忙看下源码适配CPU运行吗？
2023-05-26 01:39:08 - INFO: dict_items([('dataset', 'resume-zh'), ('dist_emb_size', 20), ('type_emb_size', 20), ('lstm_hid_size', 512), ('conv_hid_size', 96), ('bert_hid_size'…
-
大佬，我的电脑太垃圾了，请问是否可以斗胆要一份训练好的模型呀，我就是想看一下后续代码是否可以执行
-
from optimization import BERTAdam
这行的BERTAdam，
谢谢
-
Hi guys!
I tried to run sample code . however I am facing this error . All comments are very welcomed and appreciated in this matter.
raise FileNotFoundError('graph optimization fails and retu…
-
I use the ml-backend and the pretrained bert-base-chinese model to train a NER model，The model is trained ok, but when I use it to predict, it always returns text='...' and start=0, in fact, the strin…
-
hi, i want convert realformer tf checkpoint to torch model, but get a error
```
torch.nn.modules.module.ModuleAttributeError: 'LayerNorm' object has no attribute 'beta'
```
I think this is cause…
-
想问下UER支持从断点加载模型重新训练吗？ 我设置50w个step的训练， 因为服务器不稳定的原因训练有时会中断，所以我设置了断点保存，然后每次从新训练的时候，都是将pretrain.sh 中的 pretrained_model_path 路径重新设置为断点路径，然后再修改下要训练的step数目。 我的数据大概200w+，使用的是 bert-wwm, 进行mlm训练， batch_size 为 1…
-
## 示例
```Shell
python run_classifier.py \
--task_name MRPC \
--do_train \
--do_eval \
--do_lower_case \
--data_dir $GLUE_DIR/MRPC/ \
--bert_model bert-base-uncased \
--max_seq_l…
-
['O', 'B-故障设备', 'I-故障设备', 'B-故障原因', 'I-故障原因']
{'O': 0, 'B-故障设备': 1, 'I-故障设备': 2, 'B-故障原因': 3, 'I-故障原因': 4}
Some weights of the model checkpoint at ./model_hub/chinese-bert-wwm-ext/ were not used whe…