ner_produtos_catmat

This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on an unknown dataset. O modelo faz parte do pipeline de sobrepreços e de serviços relacionados ao catmat. It achieves the following results on the evaluation set:

• Loss: 0.2107
• Precision: 0.8770
• Recall: 0.9103
• F1: 0.8934
• Accuracy: 0.9412

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.3569	1.0	1189	0.2203	0.8637	0.8896	0.8764	0.9363
0.1759	2.0	2378	0.2107	0.8770	0.9103	0.8934	0.9412
0.1369	3.0	3567	0.2136	0.8773	0.9110	0.8938	0.9414
0.1114	4.0	4756	0.2406	0.8819	0.9184	0.8998	0.9397
0.0894	5.0	5945	0.2642	0.8903	0.9131	0.9015	0.9428

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1