Amir13's picture
Update README.md
994964c
metadata
license: mit
tags:
  - generated_from_trainer
datasets:
  - wnut_17
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: xlm-roberta-base-wnut2017-en
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: wnut_17
          type: wnut_17
          config: wnut_17
          split: validation
          args: wnut_17
        metrics:
          - name: Precision
            type: precision
            value: 0.7219662058371735
          - name: Recall
            type: recall
            value: 0.562200956937799
          - name: F1
            type: f1
            value: 0.6321452589105581
          - name: Accuracy
            type: accuracy
            value: 0.9589398080467807

xlm-roberta-base-wnut2017-en

This model is a fine-tuned version of xlm-roberta-base on wnut_17 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2319
  • Precision: 0.7220
  • Recall: 0.5622
  • F1: 0.6321
  • Accuracy: 0.9589

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 1.0 107 0.2789 0.4679 0.3397 0.3936 0.9408
No log 2.0 214 0.2092 0.6875 0.5 0.5789 0.9518
No log 3.0 321 0.1968 0.6194 0.5431 0.5787 0.9567
No log 4.0 428 0.2172 0.7212 0.5383 0.6164 0.9586
0.1523 5.0 535 0.2319 0.7220 0.5622 0.6321 0.9589
0.1523 6.0 642 0.2023 0.6180 0.5514 0.5828 0.9577
0.1523 7.0 749 0.2494 0.6895 0.5419 0.6068 0.9589
0.1523 8.0 856 0.2844 0.7018 0.5263 0.6015 0.9578
0.1523 9.0 963 0.2568 0.6808 0.5562 0.6122 0.9592
0.0294 10.0 1070 0.2453 0.6718 0.5754 0.6198 0.9596
0.0294 11.0 1177 0.2538 0.6933 0.5706 0.6260 0.9600
0.0294 12.0 1284 0.2638 0.6865 0.5658 0.6203 0.9593
0.0294 13.0 1391 0.2744 0.6764 0.5526 0.6083 0.9587
0.0294 14.0 1498 0.2714 0.6812 0.5622 0.6160 0.9590
0.0135 15.0 1605 0.2724 0.6830 0.5670 0.6196 0.9593

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}
}