Edit model card

detect-femicide-news-xlmr

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

  • Loss: 0.0161
  • Accuracy: 0.9973
  • Precision Neg: 0.9975
  • Precision Pos: 0.9967
  • Recall Neg: 0.9988
  • Recall Pos: 0.9933
  • F1 Score Neg: 0.9981
  • F1 Score Pos: 0.9950

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: 1e-05
  • train_batch_size: 128
  • eval_batch_size: 8
  • seed: 1996
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Neg Precision Pos Recall Neg Recall Pos F1 Score Neg F1 Score Pos
0.2758 1.0 204 0.1001 0.9718 0.9741 0.9654 0.9875 0.93 0.9808 0.9474
0.0782 2.0 408 0.0505 0.9809 0.9839 0.9729 0.99 0.9567 0.9869 0.9647
0.0501 3.0 612 0.0272 0.9927 0.9962 0.9834 0.9938 0.99 0.9950 0.9867
0.0389 4.0 816 0.0201 0.9945 0.9938 0.9966 0.9988 0.9833 0.9963 0.9899
0.031 5.0 1020 0.0175 0.9964 0.9963 0.9966 0.9988 0.99 0.9975 0.9933
0.0235 6.0 1224 0.0161 0.9973 0.9975 0.9967 0.9988 0.9933 0.9981 0.9950

Framework versions

  • Transformers 4.16.2
  • Pytorch 1.10.2+cu113
  • Datasets 1.18.3
  • Tokenizers 0.11.0
Downloads last month
12