Downloads · 30 days
6
25% of all-time downloads
cybs-ner
ddemirol/cybs-ner
cybs-ner is a token classification model from ddemirol. 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
24
Public
Parameters
66.4M
797 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors265 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Aug 1, 2024
- Updated
- Aug 1, 2024
- SHA
- e059593c
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. -->
cybs-ner
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2097
- Precision: 0.7881
- Recall: 0.7953
- F1: 0.7917
- Accuracy: 0.9516
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: 2e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 167 | 0.2259 | 0.6792 | 0.7943 | 0.7323 | 0.9375 |
| No log | 2.0 | 334 | 0.1860 | 0.7467 | 0.7362 | 0.7414 | 0.9416 |
| 0.2166 | 3.0 | 501 | 0.1916 | 0.7496 | 0.8211 | 0.7837 | 0.9483 |
| 0.2166 | 4.0 | 668 | 0.1915 | 0.7885 | 0.7950 | 0.7917 | 0.9518 |
| 0.2166 | 5.0 | 835 | 0.1980 | 0.7972 | 0.7802 | 0.7886 | 0.9515 |
| 0.0491 | 6.0 | 1002 | 0.1999 | 0.7813 | 0.8179 | 0.7992 | 0.9526 |
| 0.0491 | 7.0 | 1169 | 0.2096 | 0.7814 | 0.7969 | 0.7890 | 0.9507 |
| 0.0491 | 8.0 | 1336 | 0.2097 | 0.7881 | 0.7953 | 0.7917 | 0.9516 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Aug 1, 2024
- Updated
- Aug 1, 2024