Downloads · 30 days
6
16% of all-time downloads
IgboBERT-NER-finetuned-Final-Version
chymaks/IgboBERT-NER-finetuned-Final-Version
IgboBERT-NER-finetuned-Final-Version is a token classification model from chymaks. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
38
Public
Parameters
82.9M
6.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors331 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Oct 5, 2024
- Updated
- Oct 5, 2024
- SHA
- feed3f55
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. -->
IgboBERT-NER-finetuned-Final-Version
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2420
- Precision: 0.8000
- Recall: 0.8188
- F1: 0.8093
- Accuracy: 0.9751
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1164 | 1.0 | 1234 | 0.1290 | 0.6049 | 0.7572 | 0.6726 | 0.9612 |
| 0.0637 | 2.0 | 2468 | 0.1195 | 0.7329 | 0.7507 | 0.7417 | 0.9693 |
| 0.0364 | 3.0 | 3702 | 0.1288 | 0.6905 | 0.7683 | 0.7274 | 0.9698 |
| 0.0219 | 4.0 | 4936 | 0.1475 | 0.7554 | 0.7848 | 0.7699 | 0.9730 |
| 0.0172 | 5.0 | 6170 | 0.1592 | 0.7596 | 0.7977 | 0.7782 | 0.9743 |
| 0.0115 | 6.0 | 7404 | 0.1980 | 0.7488 | 0.7493 | 0.7491 | 0.9697 |
| 0.0097 | 7.0 | 8638 | 0.1754 | 0.7728 | 0.7758 | 0.7743 | 0.9725 |
| 0.0069 | 8.0 | 9872 | 0.1872 | 0.7473 | 0.7862 | 0.7663 | 0.9717 |
| 0.0058 | 9.0 | 11106 | 0.1870 | 0.7797 | 0.8079 | 0.7936 | 0.9744 |
| 0.0039 | 10.0 | 12340 | 0.2041 | 0.7741 | 0.7937 | 0.7837 | 0.9735 |
| 0.0039 | 11.0 | 13574 | 0.2263 | 0.7836 | 0.7964 | 0.7899 | 0.9741 |
| 0.0021 | 12.0 | 14808 | 0.2201 | 0.7867 | 0.7769 | 0.7818 | 0.9720 |
| 0.002 | 13.0 | 16042 | 0.2060 | 0.7842 | 0.7957 | 0.7899 | 0.9738 |
| 0.0015 | 14.0 | 17276 | 0.2047 | 0.7862 | 0.8204 | 0.8029 | 0.9750 |
| 0.001 | 15.0 | 18510 | 0.2270 | 0.7732 | 0.8068 | 0.7896 | 0.9743 |
| 0.0007 | 16.0 | 19744 | 0.2402 | 0.7983 | 0.8122 | 0.8052 | 0.9745 |
| 0.0008 | 17.0 | 20978 | 0.2235 | 0.7874 | 0.8244 | 0.8055 | 0.9751 |
| 0.0005 | 18.0 | 22212 | 0.2303 | 0.7956 | 0.8181 | 0.8067 | 0.9750 |
| 0.0001 | 19.0 | 23446 | 0.2424 | 0.8012 | 0.8133 | 0.8072 | 0.9751 |
| 0.0003 | 20.0 | 24680 | 0.2420 | 0.8000 | 0.8188 | 0.8093 | 0.9751 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- roberta
- Created
- Oct 5, 2024
- Updated
- Oct 5, 2024