Downloads · 30 days
6
29% of all-time downloads
ner_lemmatized
PawanJain409/ner_lemmatized
ner_lemmatized is a token classification model from PawanJain409. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
21
Public
Parameters
109M
4.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors436 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 19, 2024
- Updated
- Mar 19, 2024
- SHA
- 54f5c3ba
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
ner_lemmatized
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2151
- Precision: 0.7983
- Recall: 0.8232
- F1: 0.8106
- Accuracy: 0.9681
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1302 | 1.0 | 469 | 0.1124 | 0.7933 | 0.7949 | 0.7941 | 0.9666 |
| 0.0897 | 2.0 | 938 | 0.1188 | 0.7781 | 0.8085 | 0.7930 | 0.9658 |
| 0.0561 | 3.0 | 1407 | 0.1275 | 0.7646 | 0.8103 | 0.7868 | 0.9646 |
| 0.0326 | 4.0 | 1876 | 0.1559 | 0.7916 | 0.8165 | 0.8039 | 0.9675 |
| 0.0197 | 5.0 | 2345 | 0.1685 | 0.7882 | 0.8073 | 0.7976 | 0.9664 |
| 0.0119 | 6.0 | 2814 | 0.1812 | 0.7880 | 0.8177 | 0.8026 | 0.9674 |
| 0.0064 | 7.0 | 3283 | 0.1987 | 0.7925 | 0.8165 | 0.8043 | 0.9676 |
| 0.0043 | 8.0 | 3752 | 0.2079 | 0.8032 | 0.8208 | 0.8119 | 0.9683 |
| 0.0026 | 9.0 | 4221 | 0.2130 | 0.7994 | 0.8230 | 0.8110 | 0.9681 |
| 0.0018 | 10.0 | 4690 | 0.2151 | 0.7983 | 0.8232 | 0.8106 | 0.9681 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Mar 19, 2024
- Updated
- Mar 19, 2024