---
library_name: transformers
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my-roberta-RQ3
  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. -->

# my-roberta-RQ3

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: 0.4223
- Accuracy: 0.9462
- F1 Macro: 0.5894
- F1 Weighted: 0.9458

## 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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|
| 0.3736        | 1.0   | 539  | 0.3766          | 0.9376   | 0.3041   | 0.9287      |
| 0.3358        | 2.0   | 1078 | 0.3330          | 0.9445   | 0.4096   | 0.9412      |
| 0.2991        | 3.0   | 1617 | 0.3182          | 0.9503   | 0.4425   | 0.9472      |
| 0.2410        | 4.0   | 2156 | 0.3319          | 0.9480   | 0.4913   | 0.9460      |
| 0.1962        | 5.0   | 2695 | 0.3398          | 0.9487   | 0.6223   | 0.9484      |
| 0.1727        | 6.0   | 3234 | 0.3461          | 0.9517   | 0.6410   | 0.9510      |
| 0.1506        | 7.0   | 3773 | 0.3586          | 0.9515   | 0.6507   | 0.9514      |
| 0.1136        | 8.0   | 4312 | 0.3881          | 0.9510   | 0.6519   | 0.9506      |
| 0.1293        | 9.0   | 4851 | 0.4080          | 0.9515   | 0.6367   | 0.9513      |
| 0.1075        | 10.0  | 5390 | 0.4134          | 0.9501   | 0.6309   | 0.9499      |


### Framework versions

- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2