metadata
base_model: csebuetnlp/banglabert
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: banglabert-MLTC-BB1
results: []
banglabert-MLTC-BB1
This model is a fine-tuned version of csebuetnlp/banglabert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4011
- F1: 0.8602
- Roc Auc: 0.8579
- Accuracy: 0.5758
- Hamming Loss: 0.1420
- Jaccard Score: 0.7547
- Zero One Loss: 0.4242
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: 24
- eval_batch_size: 24
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.2462 | 1.0 | 49 | 0.3759 | 0.8582 | 0.8534 | 0.5758 | 0.1465 | 0.7516 | 0.4242 |
| 0.2099 | 2.0 | 98 | 0.3534 | 0.8656 | 0.8650 | 0.5964 | 0.1350 | 0.7630 | 0.4036 |
| 0.2067 | 3.0 | 147 | 0.3660 | 0.8613 | 0.8599 | 0.5861 | 0.1401 | 0.7564 | 0.4139 |
| 0.168 | 4.0 | 196 | 0.3672 | 0.8582 | 0.8567 | 0.5835 | 0.1433 | 0.7517 | 0.4165 |
| 0.1425 | 5.0 | 245 | 0.3745 | 0.8555 | 0.8547 | 0.5656 | 0.1452 | 0.7475 | 0.4344 |
| 0.1545 | 6.0 | 294 | 0.3894 | 0.8544 | 0.8522 | 0.5578 | 0.1478 | 0.7459 | 0.4422 |
| 0.1115 | 7.0 | 343 | 0.3995 | 0.8579 | 0.8560 | 0.5681 | 0.1440 | 0.7511 | 0.4319 |
| 0.1158 | 8.0 | 392 | 0.4054 | 0.8580 | 0.8554 | 0.5681 | 0.1446 | 0.7514 | 0.4319 |
| 0.1055 | 9.0 | 441 | 0.3996 | 0.8575 | 0.8560 | 0.5681 | 0.1440 | 0.7506 | 0.4319 |
| 0.105 | 10.0 | 490 | 0.4011 | 0.8602 | 0.8579 | 0.5758 | 0.1420 | 0.7547 | 0.4242 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1