Comments (5)
3%|▎ | 20/725 [00:33<17:52, 1.52s/it]training batch: 20, loss: 29.96524, precision: -1.000 recall: 0.000 f1: -1.000 accuracy: 0.852 6%|▌ | 40/725 [01:04<17:31, 1.53s/it]training batch: 40, loss: 24.01720, precision: -1.000 recall: 0.000 f1: -1.000 accuracy: 0.889 8%|▊ | 60/725 [01:36<17:31, 1.58s/it]training batch: 60, loss: 21.02634, precision: -1.000 recall: 0.000 f1: -1.000 accuracy: 0.821 11%|█ | 80/725 [02:09<17:02, 1.59s/it]training batch: 80, loss: 17.43504, precision: -1.000 recall: 0.000 f1: -1.000 accuracy: 0.859 14%|█▍ | 100/725 [02:42<17:20, 1.66s/it]training batch: 100, loss: 12.46207, precision: -1.000 recall: 0.000 f1: -1.000 accuracy: 0.908 17%|█▋ | 120/725 [03:16<17:41, 1.75s/it]training batch: 120, loss: 9.91527, precision: 1.000 recall: 0.029 f1: 0.057 accuracy: 0.923 19%|█▉ | 140/725 [03:49<15:39, 1.61s/it]training batch: 140, loss: 11.09897, precision: 0.636 recall: 0.146 f1: 0.237 accuracy: 0.915
你是哪个模型?遇到了同样的问题。
from entity_extractor_by_ner.
3%|▎ | 20/725 [00:33<17:52, 1.52s/it]training batch: 20, loss: 29.96524, precision: -1.000 recall: 0.000 f1: -1.000 accuracy: 0.852 6%|▌ | 40/725 [01:04<17:31, 1.53s/it]training batch: 40, loss: 24.01720, precision: -1.000 recall: 0.000 f1: -1.000 accuracy: 0.889 8%|▊ | 60/725 [01:36<17:31, 1.58s/it]training batch: 60, loss: 21.02634, precision: -1.000 recall: 0.000 f1: -1.000 accuracy: 0.821 11%|█ | 80/725 [02:09<17:02, 1.59s/it]training batch: 80, loss: 17.43504, precision: -1.000 recall: 0.000 f1: -1.000 accuracy: 0.859 14%|█▍ | 100/725 [02:42<17:20, 1.66s/it]training batch: 100, loss: 12.46207, precision: -1.000 recall: 0.000 f1: -1.000 accuracy: 0.908 17%|█▋ | 120/725 [03:16<17:41, 1.75s/it]training batch: 120, loss: 9.91527, precision: 1.000 recall: 0.029 f1: 0.057 accuracy: 0.923 19%|█▉ | 140/725 [03:49<15:39, 1.61s/it]training batch: 140, loss: 11.09897, precision: 0.636 recall: 0.146 f1: 0.237 accuracy: 0.915
你是哪个模型?遇到了同样的问题。
看了源代码,发现作者使用的是exact match,如果没有match上,则使用初始化值,也就是-1,因此在前几轮中可能由于训练不充分,会出现-1,夸张的是,我用finetune bert+crf的前几个epoch都是-1,所以结论是:代码没有问题(或者,作者可以添加一些友好的提示,不成熟的建议。)
from entity_extractor_by_ner.
我也是这个问题。但是我都训练了20个epoch了,还是-1。除了batch_size改小了为24,其他都没变。感觉很无奈。
from entity_extractor_by_ner.
把learning_rate改小,设定为5e-5
from entity_extractor_by_ner.
已经修改为指标初始为0.0
from entity_extractor_by_ner.
Related Issues (20)
- predict接口 cpu下推理速度比GPU下快 HOT 1
- train_dataset, val_dataset = data_manager.get_training_set()两个返回TensorSliceDataset无法用len函数 HOT 2
- ValueError: Tensor's shape (300, 800) is not compatible with supplied shape (768, 800) HOT 5
- 换分词库 HOT 1
- 用了自己的标注数据集 结果报错 HOT 2
- ValueError: Shapes (27, 27) and (8, 8) are incompatible HOT 1
- tensorflow版本与tensorflow-addons版本冲突 HOT 1
- 导入自己标注的文本,显示数据集为0的问题 HOT 7
- 导入自建数据集,出现training set size: 0, validating set size: 0 HOT 2
- 自己重新训练报错 HOT 5
- 替换为自己的数据后,出现错误 HOT 1
- python版本 HOT 2
- 代码问题 HOT 1
- 更换预训练模型,比如albert HOT 3
- 为什么每次predict的结果会不同呢 HOT 1
- 当我训练完bilstm-crf和idcnn-crf模型的时候,开始训练bert-bilstm-crf模型,老是报错 HOT 2
- 使用微调的时候,训练老是0,为什么 HOT 1
- 将自己的数据集分为四类替换进去并且修改了suffix里面的标签为自己的标签 ,出现如下错误 HOT 2
- tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[24,95] = -7 is not in [0, 100)出现这个问题应该怎么办 HOT 1
- idcnn训练时出现准确率和召回率全0 HOT 2
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 entity_extractor_by_ner.