Comments (8)
没看出来什么问题, 是否没有贴全
from m3tl.
没看出来什么问题, 是否没有贴全
训练得acc 一直很低
from m3tl.
明白, 我有空看看
from m3tl.
I have the same with a low accuracy. It seems using "|" for the problems will have better results than "&".
problem = 'c2_cls|c3_cls|c4_cls|c5_cls|c6_cls'
from m3tl.
I have the same with a low accuracy. It seems using "|" for the problems will have better results than "&".
problem = 'c2_cls|c3_cls|c4_cls|c5_cls|c6_cls'
Thanks for the info. Will take a look tomorrow. BTW, are the results significantly better(meaning it can reach expected accuracy) when chaining with "|" or just slightly better?
from m3tl.
It is slightly better only. Btw, thank for your hard works but it seems there is a problem with the accuracy. When using your code for my case (offensive language detection), the accuracy gets stuck about 63% while I can obtain 83% with mt-dnn.
from m3tl.
In that case, I think there's a bug. Will further investigate.
from m3tl.
没看出来什么问题, 是否没有贴全
训练得acc 一直很低
好像无法复现. 我在我自己这边跑是正常的, mean_acc
计算有点问题, 但是不影响效果.
Epoch 2/20
48/48 [==============================] - 5s 95ms/step - mean_acc: 0.5634 - weibo_ner_acc: 0.9591 - BertMultiTaskTop/weibo_ner/losses/0: 0.1731
Epoch 3/20
48/48 [==============================] - 4s 74ms/step - mean_acc: 0.5293 - weibo_ner_acc: 0.9703 - BertMultiTaskTop/weibo_ner/losses/0: 0.0904
Epoch 4/20
48/48 [==============================] - 4s 74ms/step - mean_acc: 0.5181 - weibo_ner_acc: 0.9772 - BertMultiTaskTop/weibo_ner/losses/0: 0.0574
Epoch 5/20
48/48 [==============================] - 4s 74ms/step - mean_acc: 0.5119 - weibo_ner_acc: 0.9814 - BertMultiTaskTop/weibo_ner/losses/0: 0.0445
Epoch 6/20
48/48 [==============================] - 4s 73ms/step - mean_acc: 0.5135 - weibo_ner_acc: 0.9845 - BertMultiTaskTop/weibo_ner/losses/0: 0.0412
Epoch 7/20
48/48 [==============================] - 5s 95ms/step - mean_acc: 0.5121 - weibo_ner_acc: 0.9863 - BertMultiTaskTop/weibo_ner/losses/0: 0.0391
不知道是否tf和transformers版本导致.
我测试的版本:
tf.__version__: 2.6.2
transformers.__version__: 4.19.2
from m3tl.
Related Issues (20)
- 同一任务不同数据集 HOT 1
- How to use early stopping for saving the best train accuracy? HOT 1
- NameError: name 'decode_predictions' is not defined HOT 1
- ModuleAttributeError: 'Embedding' object has no attribute 'weights' HOT 1
- [cls] or pooled embedding? HOT 1
- Problem_info.txt not generated. HOT 2
- Unused attribute in object (root).body.bert.embedding_layer.token_type_embeddings: ['VARIABLE_VALUE'] HOT 1
- 使用rdrop, it shows a tf.split error. 大佬帮忙看看 HOT 1
- Performance issue in m3tl/read_write_tfrecord.py HOT 1
- 日志:大佬支持 tfevent 输出效果? HOT 5
- 疑惑:没有看到哪里执行了 text 2 tokens 的过程 HOT 1
- 讨论:大佬,这个框架怎么适配未训练大模型推理 HOT 1
- notebook is not working HOT 3
- 该项目是否支持文本摘要生成任务 HOT 1
- 'TFBertEmbeddings' object has no attribute 'word_embeddings' HOT 4
- error: Invalid argument: cycle_length must be > 0
- 如何进行推理? HOT 1
- 关于创建数据处理函数问题 HOT 3
- 文档打不开 HOT 1
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 m3tl.