Edit model card

xlm-roberta-base-ncbi_disease-en

This model is a fine-tuned version of xlm-roberta-base on the ncbi_disease dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0496
  • Precision: 0.8562
  • Recall: 0.8628
  • F1: 0.8595
  • Accuracy: 0.9869

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 170 0.0555 0.7949 0.7980 0.7964 0.9833
No log 2.0 340 0.0524 0.7404 0.8551 0.7936 0.9836
0.0803 3.0 510 0.0484 0.7932 0.8869 0.8374 0.9849
0.0803 4.0 680 0.0496 0.8562 0.8628 0.8595 0.9869
0.0803 5.0 850 0.0562 0.7976 0.8615 0.8283 0.9848
0.0152 6.0 1020 0.0606 0.8086 0.8856 0.8454 0.9846
0.0152 7.0 1190 0.0709 0.8412 0.8412 0.8412 0.9866
0.0152 8.0 1360 0.0735 0.8257 0.8666 0.8456 0.9843
0.0059 9.0 1530 0.0730 0.8343 0.8767 0.8550 0.9866
0.0059 10.0 1700 0.0855 0.8130 0.8895 0.8495 0.9843
0.0059 11.0 1870 0.0868 0.8263 0.8767 0.8508 0.9860
0.0026 12.0 2040 0.0862 0.8273 0.8767 0.8513 0.9858
0.0026 13.0 2210 0.0875 0.8329 0.8806 0.8561 0.9859
0.0026 14.0 2380 0.0889 0.8287 0.8793 0.8533 0.9859
0.0013 15.0 2550 0.0884 0.8321 0.8755 0.8533 0.9861

Framework versions

  • Transformers 4.26.1
  • Pytorch 1.13.1+cu116
  • Datasets 2.9.0
  • Tokenizers 0.13.2

Citation

If you used the datasets and models in this repository, please cite it.

@misc{https://doi.org/10.48550/arxiv.2302.09611,
  doi = {10.48550/ARXIV.2302.09611},
  url = {https://arxiv.org/abs/2302.09611},
  author = {Sartipi, Amir and Fatemi, Afsaneh},
  keywords = {Computation and Language (cs.CL), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Exploring the Potential of Machine Translation for Generating Named Entity Datasets: A Case Study between Persian and English},
  publisher = {arXiv},
  year = {2023},
  copyright = {arXiv.org perpetual, non-exclusive license}
}
Downloads last month
1

Dataset used to train Amir13/xlm-roberta-base-ncbi_disease-en

Evaluation results