Edit model card

bert-base-portuguese-cased_harem-selective-lowC-CRF-first-ner

This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on the harem dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0687
  • Precision: 0.8030
  • Recall: 0.8933
  • F1: 0.8457
  • Accuracy: 0.9748

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: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.0646 1.0 2517 0.0924 0.7822 0.8876 0.8316 0.9670
0.0263 2.0 5034 0.0644 0.7598 0.8708 0.8115 0.9685
0.0234 3.0 7551 0.0687 0.8030 0.8933 0.8457 0.9748

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.10.2+cu102
  • Datasets 2.2.2
  • Tokenizers 0.12.1
Downloads last month
6
Unable to determine this model’s pipeline type. Check the docs .

Dataset used to train jordyvl/bert-base-portuguese-cased_harem-selective-lowC-CRF-first-ner