metadata
library_name: transformers
license: mit
base_model: sagorsarker/bangla-bert-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bangla-bert-base-finetuned-ner-generated_data
results: []
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: 0.4845
- Precision: 0.7016
- Recall: 0.6578
- F1: 0.6790
- Accuracy: 0.8859
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 | 0.4879 | 0.6705 | 0.5821 | 0.6232 | 0.8735 |
| 0.4957 | 2.0 | 706 | 0.4439 | 0.7046 | 0.6172 | 0.6580 | 0.8855 |
| 0.3208 | 3.0 | 1059 | 0.4374 | 0.6977 | 0.6563 | 0.6764 | 0.8895 |
| 0.3208 | 4.0 | 1412 | 0.4482 | 0.7183 | 0.6470 | 0.6808 | 0.8933 |
| 0.2344 | 5.0 | 1765 | 0.4610 | 0.6920 | 0.6715 | 0.6816 | 0.8908 |
| 0.1868 | 6.0 | 2118 | 0.4703 | 0.6987 | 0.6680 | 0.6830 | 0.8917 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2