irony_it_Italy

Multilingual-Perspectivist-NLU/irony_it_Italy

irony_it_Italy 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: 0.0025 - Accuracy: 0.6653 - Precision: 0.4091 - Recall: 0.7377 - F1…

Downloads · 30 days

2% of all-time downloads

All-time downloads

500

Public

Repo size

5.5 GB

Likes

Public

Hugging Face

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: Oct 31, 2023
Updated: Nov 6, 2023
SHA: bc1cc3ea

Try a prompt

Base models

Model card

From the Hugging Face model README

irony_it_Italy

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: 0.0025
Accuracy: 0.6653
Precision: 0.4091
Recall: 0.7377
F1: 0.5263

Model description

The model is trained considering the annotation of annotators from Italy only, on the French instances. The Italian 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 Italy from the MultiPICo 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
0.0046	1.0	46	0.0043	0.4256	0.2759	0.7869	0.4085
0.0043	2.0	92	0.0042	0.5579	0.3083	0.6066	0.4088
0.0042	3.0	138	0.0041	0.5785	0.3084	0.5410	0.3929
0.0039	4.0	184	0.0039	0.5041	0.3072	0.7705	0.4393
0.0036	5.0	230	0.0036	0.5537	0.3309	0.7541	0.46
0.0032	6.0	276	0.0032	0.6281	0.3802	0.7541	0.5055
0.0025	7.0	322	0.0028	0.6777	0.4190	0.7213	0.5301
0.0019	8.0	368	0.0023	0.6033	0.3684	0.8033	0.5052
0.0016	9.0	414	0.0023	0.6074	0.3712	0.8033	0.5078
0.0014	10.0	460	0.0025	0.6653	0.4091	0.7377	0.5263

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: Oct 31, 2023
Updated: Nov 6, 2023