distilbert-base-sentiment-analysis-pt

This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased trained on the AiresPucrs/sentiment-analysis-pt dataset available on Hugging Face. It achieves the following results on the evaluation set:

• Loss: 0.3191
• Accuracy: 0.9076

Quick Start

from transformers import pipeline

classifier = pipeline(
    "text-classification",
    model="Octavio-Santana/distilbert-base-sentiment-analysis-pt"
)
classifier.model.config.id2label = {0: 'negativo', 1: 'positivo'}

result = classifier("Fiquei extremamente satisfeito com o atendimento, superou todas as minhas expectativas.")
# [{'label': 'positivo', 'score': 0.7609153985977173}]

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
0.2665	1.0	4252	0.8872	0.2863
0.2095	2.0	8504	0.9064	0.2736
0.1450	3.0	12756	0.9076	0.3191

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.5.0
• Tokenizers 0.22.2