metadata
license: mit
base_model: sagorsarker/bangla-bert-base
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: bangla-bert-base-MLTC-BBAU
results: []
bangla-bert-base-MLTC-BBAU
This model is a fine-tuned version of sagorsarker/bangla-bert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3665
- F1: 0.8465
- F1 Weighted: 0.8455
- Roc Auc: 0.8412
- Accuracy: 0.5424
- Hamming Loss: 0.1587
- Jaccard Score: 0.7338
- Zero One Loss: 0.4576
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: 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 | F1 | F1 Weighted | Roc Auc | Accuracy | Hamming Loss | Jaccard Score | Zero One Loss |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.4152 | 1.0 | 73 | 0.4083 | 0.8201 | 0.8155 | 0.8181 | 0.4987 | 0.1819 | 0.6950 | 0.5013 |
| 0.3506 | 2.0 | 146 | 0.3671 | 0.8504 | 0.8509 | 0.8496 | 0.5681 | 0.1504 | 0.7397 | 0.4319 |
| 0.2992 | 3.0 | 219 | 0.3665 | 0.8465 | 0.8455 | 0.8412 | 0.5424 | 0.1587 | 0.7338 | 0.4576 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1