Downloads · 30 days
6
1% of all-time downloads
Multilingual-Perspectivist-NLU
irony_es_Colombia
Multilingual-Perspectivist-NLU/irony_es_Colombia
irony_es_Colombia is a text classification model from Multilingual-Perspectivist-NLU. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
This model is a fine-tuned version of roberta-base on part of the MultiPICo dataset. It achieves the following results on the evaluation set: - Loss: 0.0037 - Accuracy: 0.6866 - Precision: 0.4235 - Recall: 0.4611 - F1…
All-time downloads
413
Public
Repo size
997 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin499 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Nov 6, 2023
- Updated
- Nov 6, 2023
- SHA
- ca8afe6a
Try a prompt
Base models
Model card
From the Hugging Face model README
irony_es_Colombia
This model is a fine-tuned version of roberta-base on part of the MultiPICo dataset. It achieves the following results on the evaluation set:
- Loss: 0.0037
- Accuracy: 0.6866
- Precision: 0.4235
- Recall: 0.4611
- F1: 0.4415
Model description
The model is trained considering the annotation of annotators from Colombia only, on instances in Spanish (all linguistic varieties). 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 Colombia from the MultiPICo dataset (instances in Spanish). 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 |
|---|---|---|---|---|---|---|---|
| 0.0043 | 1.0 | 126 | 0.0041 | 0.5940 | 0.3309 | 0.5 | 0.3982 |
| 0.0041 | 2.0 | 252 | 0.0039 | 0.5313 | 0.3308 | 0.7278 | 0.4549 |
| 0.004 | 3.0 | 378 | 0.0039 | 0.7015 | 0.4275 | 0.3278 | 0.3711 |
| 0.0038 | 4.0 | 504 | 0.0036 | 0.6522 | 0.3891 | 0.5167 | 0.4439 |
| 0.0037 | 5.0 | 630 | 0.0033 | 0.5940 | 0.3743 | 0.7611 | 0.5018 |
| 0.0034 | 6.0 | 756 | 0.0032 | 0.5925 | 0.3747 | 0.7722 | 0.5045 |
| 0.0031 | 7.0 | 882 | 0.0035 | 0.6627 | 0.4017 | 0.5222 | 0.4541 |
| 0.0026 | 8.0 | 1008 | 0.0037 | 0.6866 | 0.4235 | 0.4611 | 0.4415 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Nov 6, 2023
- Updated
- Nov 6, 2023