Edit model card

bert-base-cased-finetuned-ner

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

  • Loss: nan
  • Precision: 0.7641
  • Recall: 0.8182
  • F1: 0.7902
  • Accuracy: 0.9615

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: 8
  • eval_batch_size: 8
  • 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 1.0 432 nan 0.6807 0.7773 0.7258 0.9450
0.3019 2.0 864 nan 0.7244 0.7725 0.7476 0.9531
0.0871 3.0 1296 nan 0.7352 0.8192 0.7749 0.9571
0.0527 4.0 1728 nan 0.7455 0.7864 0.7654 0.9557
0.031 5.0 2160 nan 0.7334 0.7976 0.7642 0.9544
0.0223 6.0 2592 nan 0.7703 0.8343 0.8010 0.9624
0.0171 7.0 3024 nan 0.7279 0.8119 0.7676 0.9569
0.0171 8.0 3456 nan 0.7609 0.8067 0.7831 0.9613
0.012 9.0 3888 nan 0.7585 0.8152 0.7858 0.9608
0.0097 10.0 4320 nan 0.7641 0.8182 0.7902 0.9615

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
1
Safetensors
Model size
108M params
Tensor type
F32
·

Finetuned from

Dataset used to train GuiTap/bert-base-cased-finetuned-ner

Evaluation results