---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: irony_en_United_States
  results: []
---


# irony_en_United_States

This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on part of the [EPIC](https://huggingface.co/datasets/Multilingual-Perspectivist-NLU/EPIC) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0033
- Accuracy: 0.5800
- Precision: 0.3515
- Recall: 0.8
- F1: 0.4884

## Model description

The model is trained considering the annotation of English-speaking annotators from the United States only. The annotations from these annotators are aggregated using majority voting and then used to train the model.

## Training and evaluation data

The model has been trained on the annotation from annotators from the United States from the [EPIC](https://huggingface.co/datasets/Multilingual-Perspectivist-NLU/EPIC) dataset. The data has been randomly split into a train and a validation set.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.0044        | 1.0   | 79   | 0.0042          | 0.6587   | 0.3538    | 0.4381 | 0.3915 |
| 0.0042        | 2.0   | 158  | 0.0040          | 0.6014   | 0.3297    | 0.5714 | 0.4181 |
| 0.0038        | 3.0   | 237  | 0.0035          | 0.6396   | 0.3647    | 0.5905 | 0.4509 |
| 0.0032        | 4.0   | 316  | 0.0032          | 0.5967   | 0.3545    | 0.7429 | 0.48   |
| 0.0024        | 5.0   | 395  | 0.0029          | 0.6062   | 0.3544    | 0.6952 | 0.4695 |
| 0.0016        | 6.0   | 474  | 0.0033          | 0.6778   | 0.4051    | 0.6095 | 0.4867 |
| 0.0012        | 7.0   | 553  | 0.0033          | 0.5800   | 0.3515    | 0.8    | 0.4884 |


### Framework versions

- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1