BERT-sentiment-analysis-portuguese-with-undersampling-v2

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3082
• Accuracy: 0.8735
• F1: 0.8733
• Precision: 0.8737
• Recall: 0.8735

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.9
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.4125	1.0	1508	0.4269	0.8292	0.8290	0.8339	0.8292
0.3285	2.0	3016	0.3082	0.8735	0.8733	0.8737	0.8735

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1