annahaz's picture
update model card README.md
93e1a9a
metadata
license: mit
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: xlm-roberta-base-finetuned-misogyny-sexism
    results: []

xlm-roberta-base-finetuned-misogyny-sexism

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9064
  • Accuracy: 0.8334
  • F1: 0.3322
  • Precision: 0.2498
  • Recall: 0.4961
  • Mae: 0.1666

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 Accuracy F1 Precision Recall Mae
0.3869 1.0 2395 0.2905 0.8778 0.3528 0.3164 0.3988 0.1222
0.3539 2.0 4790 0.4143 0.8278 0.3465 0.2536 0.5467 0.1722
0.3124 3.0 7185 0.3327 0.8568 0.3583 0.2864 0.4786 0.1432
0.2817 4.0 9580 0.5621 0.7329 0.3092 0.1972 0.7160 0.2671
0.2651 5.0 11975 0.4376 0.8520 0.3607 0.2821 0.5 0.1480
0.2249 6.0 14370 0.5581 0.8326 0.3312 0.2485 0.4961 0.1674
0.1958 7.0 16765 0.6728 0.8382 0.3234 0.2484 0.4630 0.1618
0.1899 8.0 19160 0.7404 0.8304 0.3316 0.2471 0.5039 0.1696
0.1619 9.0 21555 0.8309 0.8461 0.3382 0.2639 0.4708 0.1539
0.1453 10.0 23950 0.9064 0.8334 0.3322 0.2498 0.4961 0.1666

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.12.0+cu102
  • Datasets 2.3.2
  • Tokenizers 0.12.1