metadata
license: cc
base_model: davidmasip/racism
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: racism-finetuned-detests24
results: []
racism-finetuned-detests24
This model is a fine-tuned version of davidmasip/racism on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1060
- Accuracy: 0.8429
- F1-score: 0.7668
- Precision: 0.7800
- Recall: 0.7562
- Auc: 0.7562
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-score | Precision | Recall | Auc |
|---|---|---|---|---|---|---|---|---|
| 0.3373 | 1.0 | 153 | 0.3420 | 0.8478 | 0.7336 | 0.8355 | 0.6985 | 0.6985 |
| 0.2465 | 2.0 | 306 | 0.7181 | 0.8478 | 0.7747 | 0.7873 | 0.7644 | 0.7644 |
| 0.0004 | 3.0 | 459 | 0.9072 | 0.8380 | 0.7689 | 0.7696 | 0.7682 | 0.7682 |
| 0.0002 | 4.0 | 612 | 0.9867 | 0.8429 | 0.7668 | 0.7800 | 0.7562 | 0.7562 |
| 0.0001 | 5.0 | 765 | 1.0289 | 0.8429 | 0.7655 | 0.7807 | 0.7537 | 0.7537 |
| 0.0001 | 6.0 | 918 | 1.0580 | 0.8445 | 0.7686 | 0.7829 | 0.7572 | 0.7572 |
| 0.0001 | 7.0 | 1071 | 1.0791 | 0.8429 | 0.7668 | 0.7800 | 0.7562 | 0.7562 |
| 0.0001 | 8.0 | 1224 | 1.0939 | 0.8429 | 0.7668 | 0.7800 | 0.7562 | 0.7562 |
| 0.0001 | 9.0 | 1377 | 1.1029 | 0.8429 | 0.7668 | 0.7800 | 0.7562 | 0.7562 |
| 0.0001 | 10.0 | 1530 | 1.1060 | 0.8429 | 0.7668 | 0.7800 | 0.7562 | 0.7562 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1