---
license: mit
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: xlm-roberta-base-finetuned-on-REDv2
  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. -->

# xlm-roberta-base-finetuned-on-REDv2

This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an REDv2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3089
- F1: 0.6515
- Roc Auc: 0.7862
- Accuracy: 0.5506

## 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: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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     | Roc Auc | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
| No log        | 1.0   | 255  | 0.3295          | 0.4028 | 0.6293  | 0.2615   |
| 0.3619        | 2.0   | 511  | 0.2778          | 0.6014 | 0.7346  | 0.4678   |
| 0.3619        | 3.0   | 766  | 0.2667          | 0.6509 | 0.7781  | 0.5488   |
| 0.2296        | 4.0   | 1022 | 0.2640          | 0.6466 | 0.7745  | 0.5433   |
| 0.2296        | 5.0   | 1277 | 0.2791          | 0.6432 | 0.7775  | 0.5414   |
| 0.1639        | 6.0   | 1533 | 0.2896          | 0.6354 | 0.7743  | 0.5414   |
| 0.1639        | 7.0   | 1788 | 0.2895          | 0.6519 | 0.7838  | 0.5635   |
| 0.1213        | 8.0   | 2044 | 0.2984          | 0.6457 | 0.7811  | 0.5525   |
| 0.1213        | 9.0   | 2299 | 0.3082          | 0.6474 | 0.7821  | 0.5562   |
| 0.0975        | 9.98  | 2550 | 0.3089          | 0.6515 | 0.7862  | 0.5506   |


### Framework versions

- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2