---
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: roberta-mqa-rat
  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. -->

# roberta-mqa-rat

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1161
- Accuracy: 0.5512
- F1: 0.5492
- Precision: 0.5522
- Recall: 0.5478

## 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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 1.4516        | 0.3233 | 1200  | 1.4043          | 0.4042   | 0.4014 | 0.4111    | 0.4008 |
| 1.3834        | 0.6466 | 2400  | 1.3420          | 0.4434   | 0.4417 | 0.4447    | 0.4418 |
| 1.3342        | 0.9698 | 3600  | 1.3308          | 0.4513   | 0.4489 | 0.4540    | 0.4470 |
| 1.263         | 1.2931 | 4800  | 1.2413          | 0.4907   | 0.4897 | 0.4941    | 0.4881 |
| 1.2209        | 1.6164 | 6000  | 1.2098          | 0.5095   | 0.5079 | 0.5134    | 0.5059 |
| 1.1856        | 1.9397 | 7200  | 1.1804          | 0.5174   | 0.5159 | 0.5200    | 0.5139 |
| 1.1134        | 2.2629 | 8400  | 1.1527          | 0.5337   | 0.5316 | 0.5373    | 0.5294 |
| 1.0924        | 2.5862 | 9600  | 1.1307          | 0.5456   | 0.5440 | 0.5475    | 0.5425 |
| 1.0556        | 2.9095 | 10800 | 1.1161          | 0.5512   | 0.5492 | 0.5522    | 0.5478 |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1