Comments (11)
您可以试试epoch为1,train_batch_size为64看结果是否正常
from deepke.
您可以试试epoch为1,train_batch_size为64看结果是否正常
由于计算资源限制,我只能设置epoch为1,train_batch_size为32的结果,如下:
[2024-01-19 23:06:14,854][main][INFO] - ***** Eval results *****
[2024-01-19 23:06:14,854][main][INFO] -
precision recall f1-score support
好转 0.00 0.00 0.00 69
无法判断 0.00 0.00 0.00 17
未愈 0.00 0.00 0.00 22
痊愈 0.00 0.00 0.00 1
micro avg 0.00 0.00 0.00 109
macro avg 0.00 0.00 0.00 109
weighted avg 0.00 0.00 0.00 109
from deepke.
您好,看结果可能数据量只有100多条,太少了,epoch调大多训练几个epoch(GPU内存限制只会影响batch_size大小)。推荐使用fewshot NER
from deepke.
您好,看结果可能数据量只有100多条,太少了,epoch调大多训练几个epoch(GPU内存限制只会影响batch_size大小)。推荐使用fewshot NER
这个是验证集上的,训练集大概300,然后我epoch设置的是200,我觉得应该是够的,我用另外一个run_lstmcrf.py可以正常跑出结果。
from deepke.
对于bert来说可能样本有点少了,建议您多收集一些数据样本再试试。
from deepke.
请问您的问题是否解决?
from deepke.
请问您的问题是否解决?
暂时未解决,令我不解的是在训练集上的f1也都是0,预测出来的都是标签‘O’
from deepke.
您重新pull最新的代码,数据量扩大一些,多跑几个epoch再测下训练集效果,如果仍未全0请联系我们。
from deepke.
请问您的问题解决了吗
from deepke.
请问您的问题解决了吗
结果还是全0,我再仔细检查下是否是我数据方面的问题,之后有问题的话再进行咨询,感谢解答!
from deepke.
好的,您有问题可以随时问
from deepke.
Related Issues (20)
- transformer 4.33.0 can not load the New OneKe model weights HOT 2
- Deepke-LLM是否支持模型并行 HOT 12
- ValueError: If `eos_token_id` is defined, make sure that `pad_token_id` is defined. HOT 2
- 运行之后出现链接超时,但网络正常 HOT 4
- FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\m1879/.cache\\huggingface\\hub\\models--bert-base-chinese\\refs\\main' HOT 7
- Traceback (most recent call last): File "/root/miniconda3/lib/python3.8/site-packages/transformers/modeling_utils.py", line 928, in from_pretrained raise EnvironmentError HOT 2
- 老哥救救 HOT 5
- 量化运行 HOT 3
- 联合三元组抽取编码问题 HOT 2
- 关于run.py报错的问题
- 关于oneke使用
- 请问能用vllm或者sglang部署oneke后端么 HOT 10
- Lightner runtime error HOT 2
- re类任务中的standard用例能否增加采用bert等预训练模型为gcn、capsule等模型生成词嵌入的功能? HOT 3
- re类模型中,lm模型处理头实体和尾实体的逻辑是什么? HOT 1
- cmd 运行example/re/standard/run.py一直报错 HOT 17
- web demo HOT 2
- ner可以抽哪些类别,可以列举出来吗 HOT 5
- 如何提取所有可能存在的三元组 HOT 1
- 进行预测时,可以使用多张GPU加载模型吗? 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 deepke.