Edit model card

distilbert-base-uncased-finetuned-ner-lenerBr

This model is a fine-tuned version of distilbert/distilbert-base-uncased on the lener_br dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1555
  • Precision: 0.7846
  • Recall: 0.7810
  • F1: 0.7828
  • Accuracy: 0.9672

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
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 490 0.1861 0.6380 0.6661 0.6518 0.9446
0.2629 2.0 980 0.1618 0.7063 0.7303 0.7181 0.9537
0.0756 3.0 1470 0.1299 0.7299 0.8010 0.7638 0.9645
0.0443 4.0 1960 0.1422 0.7634 0.7708 0.7671 0.9643
0.0279 5.0 2450 0.1508 0.7870 0.7679 0.7773 0.9648
0.0203 6.0 2940 0.1457 0.7693 0.7815 0.7753 0.9681
0.0143 7.0 3430 0.1508 0.7767 0.7714 0.7740 0.9663
0.0105 8.0 3920 0.1537 0.7812 0.7669 0.7739 0.9671
0.0085 9.0 4410 0.1564 0.7809 0.7681 0.7745 0.9669
0.0064 10.0 4900 0.1555 0.7846 0.7810 0.7828 0.9672

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.1.2
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
10
Safetensors
Model size
66.4M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for GuiTap/distilbert-base-uncased-finetuned-ner-lenerBr

Finetuned
(6387)
this model

Dataset used to train GuiTap/distilbert-base-uncased-finetuned-ner-lenerBr

Evaluation results