|
--- |
|
base_model: csebuetnlp/banglabert |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: banglabert-MLTC-BB1 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# banglabert-MLTC-BB1 |
|
|
|
This model is a fine-tuned version of [csebuetnlp/banglabert](https://huggingface.co/csebuetnlp/banglabert) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3670 |
|
- F1: 0.8559 |
|
- Roc Auc: 0.8534 |
|
- Accuracy: 0.5681 |
|
- Hamming Loss: 0.1465 |
|
- Jaccard Score: 0.7481 |
|
- Zero One Loss: 0.4319 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|:------------:|:-------------:|:-------------:| |
|
| 0.5656 | 1.0 | 49 | 0.5135 | 0.7799 | 0.7750 | 0.4113 | 0.2249 | 0.6392 | 0.5887 | |
|
| 0.4157 | 2.0 | 98 | 0.4203 | 0.8359 | 0.8309 | 0.5398 | 0.1690 | 0.7181 | 0.4602 | |
|
| 0.3652 | 3.0 | 147 | 0.3970 | 0.8507 | 0.8431 | 0.5604 | 0.1568 | 0.7401 | 0.4396 | |
|
| 0.3096 | 4.0 | 196 | 0.3716 | 0.8530 | 0.8489 | 0.5656 | 0.1510 | 0.7437 | 0.4344 | |
|
| 0.2674 | 5.0 | 245 | 0.3693 | 0.8521 | 0.8489 | 0.5527 | 0.1510 | 0.7423 | 0.4473 | |
|
| 0.2709 | 6.0 | 294 | 0.3660 | 0.8532 | 0.8509 | 0.5630 | 0.1491 | 0.7439 | 0.4370 | |
|
| 0.2208 | 7.0 | 343 | 0.3626 | 0.8550 | 0.8534 | 0.5656 | 0.1465 | 0.7467 | 0.4344 | |
|
| 0.2388 | 8.0 | 392 | 0.3723 | 0.8573 | 0.8541 | 0.5630 | 0.1459 | 0.7503 | 0.4370 | |
|
| 0.2466 | 9.0 | 441 | 0.3685 | 0.8562 | 0.8541 | 0.5656 | 0.1459 | 0.7486 | 0.4344 | |
|
| 0.2187 | 10.0 | 490 | 0.3670 | 0.8559 | 0.8534 | 0.5681 | 0.1465 | 0.7481 | 0.4319 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
