metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: xlm-roberta-base-misogyny-sexism-indomain-mix-bal
results: []
xlm-roberta-base-misogyny-sexism-indomain-mix-bal
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: 0.6715
- Accuracy: 0.802
- F1: 0.7735
- Precision: 0.9037
- Recall: 0.676
- Mae: 0.198
- Tn: 464
- Fp: 36
- Fn: 162
- Tp: 338
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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Mae | Tn | Fp | Fn | Tp |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0.3727 | 1.0 | 2714 | 0.6816 | 0.735 | 0.6683 | 0.8930 | 0.534 | 0.265 | 468 | 32 | 233 | 267 |
0.3257 | 2.0 | 5428 | 0.6787 | 0.753 | 0.6893 | 0.9288 | 0.548 | 0.247 | 479 | 21 | 226 | 274 |
0.2785 | 3.0 | 8142 | 0.5640 | 0.779 | 0.7397 | 0.8997 | 0.628 | 0.221 | 465 | 35 | 186 | 314 |
0.25 | 4.0 | 10856 | 0.6715 | 0.802 | 0.7735 | 0.9037 | 0.676 | 0.198 | 464 | 36 | 162 | 338 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1