metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: irony_en_Ireland
results: []
irony_en_Ireland
This model is a fine-tuned version of roberta-base on part of the EPIC dataset. It achieves the following results on the evaluation set:
- Loss: 0.0047
- Accuracy: 0.7114
- Precision: 0.4444
- Recall: 0.5049
- F1: 0.4727
Model description
The model is trained considering the annotation of annotators from Ireland 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 Ireland from the 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 | 76 | 0.0042 | 0.7289 | 0.3636 | 0.0777 | 0.128 |
| 0.004 | 2.0 | 152 | 0.0035 | 0.5945 | 0.35 | 0.6796 | 0.4620 |
| 0.0033 | 3.0 | 228 | 0.0032 | 0.6318 | 0.3669 | 0.6019 | 0.4559 |
| 0.0028 | 4.0 | 304 | 0.0030 | 0.6766 | 0.4069 | 0.5728 | 0.4758 |
| 0.0023 | 5.0 | 380 | 0.0027 | 0.5771 | 0.3537 | 0.7864 | 0.4880 |
| 0.0015 | 6.0 | 456 | 0.0027 | 0.6194 | 0.375 | 0.7282 | 0.4950 |
| 0.0012 | 7.0 | 532 | 0.0041 | 0.7289 | 0.4717 | 0.4854 | 0.4785 |
| 0.0009 | 8.0 | 608 | 0.0047 | 0.7114 | 0.4444 | 0.5049 | 0.4727 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1