metadata
base_model: csebuetnlp/banglabert
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: banglabert-MLTC-BB
results: []
banglabert-MLTC-BB
This model is a fine-tuned version of csebuetnlp/banglabert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3730
- F1: 0.8628
- Roc Auc: 0.8612
- Accuracy: 0.5784
- Hamming Loss: 0.1388
- Jaccard Score: 0.7587
- Zero One Loss: 0.4216
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | Hamming Loss | Jaccard Score | Zero One Loss |
|---|---|---|---|---|---|---|---|---|---|
| 0.4126 | 1.0 | 146 | 0.4229 | 0.8333 | 0.8303 | 0.5527 | 0.1697 | 0.7143 | 0.4473 |
| 0.381 | 2.0 | 292 | 0.3605 | 0.8551 | 0.8541 | 0.5835 | 0.1459 | 0.7469 | 0.4165 |
| 0.2885 | 3.0 | 438 | 0.3745 | 0.8589 | 0.8521 | 0.5656 | 0.1478 | 0.7527 | 0.4344 |
| 0.2324 | 4.0 | 584 | 0.3612 | 0.8597 | 0.8579 | 0.5835 | 0.1420 | 0.7539 | 0.4165 |
| 0.2618 | 5.0 | 730 | 0.3458 | 0.8632 | 0.8631 | 0.5861 | 0.1369 | 0.7593 | 0.4139 |
| 0.2535 | 6.0 | 876 | 0.3673 | 0.8611 | 0.8579 | 0.5758 | 0.1420 | 0.7561 | 0.4242 |
| 0.1701 | 7.0 | 1022 | 0.3932 | 0.8559 | 0.8528 | 0.5681 | 0.1472 | 0.7481 | 0.4319 |
| 0.1835 | 8.0 | 1168 | 0.3641 | 0.8668 | 0.8650 | 0.5887 | 0.1350 | 0.7648 | 0.4113 |
| 0.1714 | 9.0 | 1314 | 0.3796 | 0.8617 | 0.8605 | 0.5707 | 0.1395 | 0.7570 | 0.4293 |
| 0.1311 | 10.0 | 1460 | 0.3730 | 0.8628 | 0.8612 | 0.5784 | 0.1388 | 0.7587 | 0.4216 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1