Comments (5)
我给的示例代码,学习率固定,没有weight_decay,额外增加的网络结构我是随机初始化,这些一致不?我之前也跑了实验结果在performance里面,你跑的结果差不多嘛?方便的话可以把hugging face的代码发我,我这也排查下?防止是我的代码问题
from bert4torch.
我猜想是不是你的预训练模型有部分权重没有正确加载,使用bert4torch时候你warning提示吗
from bert4torch.
早上拉取了bert4torch的最新代码,测试了开源情感数据和一个我们自己的标注数据分类模型,收敛很快,3~6轮之间基本上达到最佳表现。
上面的问题我大概是五六月份用bert4torch测试的时候出现的,然后工作中就都用hugging face的tokenizer和model。尴尬...大佬牛逼
预训练模型加载,如果是hugging face上面的bert-base,'LayerNorm.gamma', 'LayerNorm.beta'和框架不一致,会有warning。以前我改了bert4torch/models.py中的映射,后来看到convert_scripts,改了权重里面的名称。改完效果提升在2~3个点之间。
from bert4torch.
嗯嗯,预训练权重有的不匹配,目前是convert脚本来修改后适配的
from bert4torch.
刚刚发现前两天修改的一个tokenizer读vocab.txt有个bug,刚刚已经修复,后续使用建议重新拉最新代码哈~
from bert4torch.
Related Issues (20)
- convert sequence labeling model to onnx HOT 1
- 训练进度条中,loss一直显示Nan的问题 HOT 5
- 询问一个bert4torch和bert4keras的差异 HOT 1
- 单机多卡BaseModelDDP初始化错误,AttributeError: can't set attribute HOT 12
- tokenizer_encode_config和tokenizer_decode_config问题 HOT 3
- 预训练模型加载 HOT 5
- DataLoader的num_workers设置为大于0时出错 HOT 3
- 请问怎么调整最后的输出结果的小数点位数,目前最后的测试结果是两位,在哪里可以调整一下啊? HOT 7
- 请问在用bart bert等模型生成标题时,如果修改标题的最大长度? HOT 3
- 显示每个epoch的已用时间和预估剩余时间 HOT 3
- chinese-xlnet-mid载入 HOT 1
- XLnet分类报错 HOT 4
- simbert微调问题 HOT 2
- LLM:chatGLM2推理加速 HOT 1
- bert4torch版本0.2.8升级到0.3.4问题 HOT 2
- 分类算法sentence句子编码的时候,没理解到mask处理逻辑 HOT 1
- Trainer.compile与torch2.0新加的model.compile重名 HOT 3
- bert4torch中,使用单卡多GPU训练,使用accelerate后,不能使用梯度剪裁。 HOT 3
- bert4torch/examples/llm /task_chatglm2_lora.py中的config_path = dir_path + 'bert4torch_config.json' 在哪里? HOT 3
- callback变红 HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from bert4torch.