# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("EsferSami/BanglaHealthNER-Model")
model = AutoModelForTokenClassification.from_pretrained("EsferSami/BanglaHealthNER-Model")Quick Links
BanglaHealthNER-Model
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2844
- Precision: 0.5616
- Recall: 0.6298
- F1: 0.5937
- Accuracy: 0.8980
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: 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2916 | 1.0 | 1590 | 0.2980 | 0.4946 | 0.5763 | 0.5323 | 0.8890 |
| 0.256 | 2.0 | 3180 | 0.2833 | 0.5443 | 0.5831 | 0.5630 | 0.8974 |
| 0.2332 | 3.0 | 4770 | 0.2768 | 0.5378 | 0.6292 | 0.5799 | 0.8991 |
| 0.1965 | 4.0 | 6360 | 0.2797 | 0.5527 | 0.6208 | 0.5848 | 0.9005 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.1.1
- Tokenizers 0.21.2
- Downloads last month
- 13
Model tree for EsferSami/BanglaHealthNER-Model
Base model
FacebookAI/xlm-roberta-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="EsferSami/BanglaHealthNER-Model")