Downloads · 30 days
4
1% of all-time downloads
bert-base-cased
om-ashish-soni/bert-base-cased
bert-base-cased is a token classification model from om-ashish-soni. 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
277
Public
Repo size
1.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin431 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Sep 9, 2023
- Updated
- Sep 9, 2023
- SHA
- 5e05f9ff
Try a prompt
Datasets
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. -->
bert-base-cased
This model was trained from scratch on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3045
- Precision: 0.9245
- Recall: 0.9319
- F1: 0.9282
- Accuracy: 0.9333
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2707 | 1.0 | 1756 | 0.3120 | 0.9171 | 0.9263 | 0.9217 | 0.9267 |
| 0.1829 | 2.0 | 3512 | 0.2928 | 0.9189 | 0.9295 | 0.9242 | 0.9299 |
| 0.1411 | 3.0 | 5268 | 0.3045 | 0.9245 | 0.9319 | 0.9282 | 0.9333 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Sep 9, 2023
- Updated
- Sep 9, 2023