Downloads · 30 days
12
6% of all-time downloads
bangla-bert-base-finetuned-ner-generated_data
noor-raghib-12/bangla-bert-base-finetuned-ner-generated_data
bangla-bert-base-finetuned-ner-generated_data is a token classification model from noor-raghib-12. 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
210
Public
Parameters
164M
17.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors655 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Jul 29, 2025
- Updated
- Jul 30, 2025
- SHA
- bb21d36d
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. -->
bangla-bert-base-finetuned-ner-generated_data
This model is a fine-tuned version of sagorsarker/bangla-bert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4748
- Precision: 0.7043
- Recall: 0.6659
- F1: 0.6846
- Accuracy: 0.8884
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: 50
- eval_batch_size: 50
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 353 | 0.4835 | 0.6698 | 0.5814 | 0.6225 | 0.8740 |
| 0.498 | 2.0 | 706 | 0.4389 | 0.7019 | 0.6218 | 0.6594 | 0.8856 |
| 0.3208 | 3.0 | 1059 | 0.4310 | 0.6945 | 0.6567 | 0.6751 | 0.8906 |
| 0.3208 | 4.0 | 1412 | 0.4419 | 0.7138 | 0.6521 | 0.6816 | 0.8939 |
| 0.2343 | 5.0 | 1765 | 0.4555 | 0.6919 | 0.6753 | 0.6835 | 0.8914 |
| 0.1868 | 6.0 | 2118 | 0.4640 | 0.6974 | 0.6734 | 0.6852 | 0.8927 |
Framework versions
- Transformers 4.54.0
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Jul 29, 2025
- Updated
- Jul 30, 2025