---
library_name: transformers
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
model-index:
- name: bengali_qa_model_AGGRO_roberta-base
  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. -->

# bengali_qa_model_AGGRO_roberta-base

This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.2878
- Exact Match: 24.7143
- F1 Score: 63.3563

## 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: 4
- eval_batch_size: 4
- seed: 3407
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 50

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Exact Match | F1 Score |
|:-------------:|:------:|:----:|:---------------:|:-----------:|:--------:|
| 5.9561        | 0.0053 | 1    | 5.9848          | 0.0         | 46.8295  |
| 5.9358        | 0.0107 | 2    | 5.9287          | 0.0         | 46.9461  |
| 5.9153        | 0.0160 | 3    | 5.8180          | 0.0         | 48.6568  |
| 5.8287        | 0.0214 | 4    | 5.6566          | 0.0752      | 52.8081  |
| 5.6816        | 0.0267 | 5    | 5.4437          | 5.5639      | 58.2723  |
| 5.4698        | 0.0321 | 6    | 5.1322          | 20.0        | 62.7335  |
| 5.2037        | 0.0374 | 7    | 4.7557          | 29.7744     | 65.3137  |
| 4.8684        | 0.0428 | 8    | 4.2898          | 26.8421     | 65.3919  |
| 4.4376        | 0.0481 | 9    | 3.7808          | 19.6241     | 63.6051  |
| 3.9423        | 0.0535 | 10   | 3.3519          | 14.2105     | 62.4085  |
| 3.7279        | 0.0588 | 11   | 3.0749          | 12.7820     | 61.8234  |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3