---
license: apache-2.0
base_model: BSC-LT/roberta-base-bne
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: services-ucacue
  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. -->

# services-ucacue

This model is a fine-tuned version of [BSC-LT/roberta-base-bne](https://huggingface.co/BSC-LT/roberta-base-bne) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5312
- Accuracy: 0.8260

## 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: 5e-05
- train_batch_size: 40
- eval_batch_size: 48
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 160
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.3007        | 1.0   | 158  | 0.6027          | 0.7798   |
| 0.5036        | 2.0   | 316  | 0.4827          | 0.8213   |
| 0.3994        | 3.0   | 474  | 0.4975          | 0.8213   |
| 0.2731        | 4.0   | 632  | 0.4928          | 0.8181   |
| 0.2132        | 5.0   | 790  | 0.5312          | 0.8260   |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2