Downloads · 30 days
148
2% of all-time downloads
camembert-ner-articles-nomination
evangeliazve/camembert-ner-articles-nomination
camembert-ner-articles-nomination is a token classification model from evangeliazve. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
8.8K
Public
Parameters
110M
880 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin440 MB · 50%
Parameter types
How the weights are stored.
F32110M · 100%
Try a prompt
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. -->
camembert-base-articles-ner-backup
This model is a fine-tuned version of camembert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6701
- F1: 0.8723
Model description
This model identifies Name Entities : PERSON, ORGANISATION, JOB TITLE Another Model is being developped to predict relationships between these entities (nomination, départure)
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.9205 | 1.0 | 6 | 1.7426 | 0.0 |
| 1.6476 | 2.0 | 12 | 1.5415 | 0.0 |
| 1.4607 | 3.0 | 18 | 1.3944 | 0.0635 |
| 1.3299 | 4.0 | 24 | 1.2587 | 0.4848 |
| 1.1973 | 5.0 | 30 | 1.1287 | 0.6207 |
| 1.0707 | 6.0 | 36 | 1.0110 | 0.8043 |
| 0.972 | 7.0 | 42 | 0.9266 | 0.8696 |
| 0.8877 | 8.0 | 48 | 0.8632 | 0.8602 |
| 0.8231 | 9.0 | 54 | 0.8279 | 0.8511 |
| 0.7723 | 10.0 | 60 | 0.8001 | 0.8511 |
| 0.7309 | 11.0 | 66 | 0.7617 | 0.8602 |
| 0.6902 | 12.0 | 72 | 0.7364 | 0.8602 |
| 0.6601 | 13.0 | 78 | 0.7104 | 0.8723 |
| 0.6306 | 14.0 | 84 | 0.7062 | 0.8723 |
| 0.6127 | 15.0 | 90 | 0.6896 | 0.8602 |
| 0.605 | 16.0 | 96 | 0.6743 | 0.8723 |
| 0.5892 | 17.0 | 102 | 0.6801 | 0.8723 |
| 0.5843 | 18.0 | 108 | 0.6797 | 0.8723 |
| 0.5731 | 19.0 | 114 | 0.6731 | 0.8723 |
| 0.5707 | 20.0 | 120 | 0.6701 | 0.8723 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0+cu117
- Datasets 2.7.0
- Tokenizers 0.13.2
- Task
- Token Classification
- Library
- transformers
- Type
- camembert
- License
- mit
- Created
- Nov 21, 2022
- Updated
- Sep 13, 2023