Edit model card

bert-base-arabert-BioNER-EN-AR

This model is a fine-tuned version of StivenLancheros/bert-base-arabert-BioNER-EN on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4250
  • Precision: 0.7143
  • Recall: 0.8209
  • F1: 0.7639
  • Accuracy: 0.9197

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: 3e-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: 20

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.6376 1.0 680 0.7457 0.4379 0.6384 0.5195 0.8242
0.4549 2.0 1360 0.7120 0.4878 0.7113 0.5787 0.8346
0.3214 3.0 2040 0.5576 0.5676 0.7529 0.6473 0.8749
0.2883 4.0 2720 0.5304 0.5916 0.7745 0.6708 0.8808
0.2596 5.0 3400 0.4942 0.6117 0.7884 0.6889 0.8906
0.2168 6.0 4080 0.5229 0.6204 0.7977 0.6979 0.8898
0.2105 7.0 4760 0.4630 0.6501 0.7935 0.7147 0.8999
0.1889 8.0 5440 0.5048 0.6407 0.8066 0.7141 0.8958
0.1714 9.0 6120 0.4538 0.6909 0.7986 0.7409 0.9105
0.1626 10.0 6800 0.4433 0.6912 0.8070 0.7446 0.9130
0.1559 11.0 7480 0.4282 0.7006 0.8054 0.7493 0.9144
0.1451 12.0 8160 0.4475 0.6978 0.8150 0.7519 0.9135
0.1384 13.0 8840 0.4535 0.6928 0.8215 0.7517 0.9145
0.1331 14.0 9520 0.4250 0.7143 0.8209 0.7639 0.9197
0.1282 15.0 10200 0.4350 0.7108 0.8237 0.7631 0.9200
0.1216 16.0 10880 0.4385 0.7096 0.8231 0.7621 0.9188
0.1195 17.0 11560 0.4376 0.7134 0.8275 0.7662 0.9204
0.1187 18.0 12240 0.4461 0.7092 0.8297 0.7647 0.9183
0.1159 19.0 12920 0.4359 0.7215 0.8264 0.7704 0.9219
0.1121 20.0 13600 0.4358 0.7198 0.8264 0.7694 0.9217

Framework versions

  • Transformers 4.27.2
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1
  • Tokenizers 0.13.2
Downloads last month
27
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.