---
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: 0.3577
- F1: 0.8555
- F1 Weighted: 0.8534
- Roc Auc: 0.8534
- Accuracy: 0.5733
- Hamming Loss: 0.1465
- Jaccard Score: 0.7475
- Zero One Loss: 0.4267

## 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     | F1 Weighted | Roc Auc | Accuracy | Hamming Loss | Jaccard Score | Zero One Loss |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|:-------:|:--------:|:------------:|:-------------:|:-------------:|
| 0.5579        | 1.0   | 49   | 0.5012          | 0.7993 | 0.7864      | 0.7832  | 0.4267   | 0.2166       | 0.6657        | 0.5733        |
| 0.4039        | 2.0   | 98   | 0.4338          | 0.8318 | 0.8287      | 0.8218  | 0.5347   | 0.1780       | 0.7121        | 0.4653        |
| 0.3704        | 3.0   | 147  | 0.3728          | 0.8600 | 0.8604      | 0.8560  | 0.5861   | 0.1440       | 0.7544        | 0.4139        |
| 0.3117        | 4.0   | 196  | 0.3615          | 0.8568 | 0.8553      | 0.8528  | 0.5733   | 0.1472       | 0.7495        | 0.4267        |
| 0.2723        | 5.0   | 245  | 0.3514          | 0.8548 | 0.8537      | 0.8528  | 0.5784   | 0.1472       | 0.7464        | 0.4216        |
| 0.2709        | 6.0   | 294  | 0.3640          | 0.8469 | 0.8434      | 0.8438  | 0.5476   | 0.1562       | 0.7344        | 0.4524        |
| 0.224         | 7.0   | 343  | 0.3581          | 0.8488 | 0.8461      | 0.8477  | 0.5578   | 0.1523       | 0.7373        | 0.4422        |
| 0.2335        | 8.0   | 392  | 0.3622          | 0.8532 | 0.8510      | 0.8502  | 0.5656   | 0.1497       | 0.7440        | 0.4344        |
| 0.2453        | 9.0   | 441  | 0.3552          | 0.8573 | 0.8560      | 0.8554  | 0.5758   | 0.1446       | 0.7503        | 0.4242        |
| 0.2194        | 10.0  | 490  | 0.3577          | 0.8555 | 0.8534      | 0.8534  | 0.5733   | 0.1465       | 0.7475        | 0.4267        |


### Framework versions

- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1