CS221-xlm-roberta-base-afr-noaug-finetuned-afr-tapt
This model is a fine-tuned version of Kuongan/xlm-roberta-base-afr-noaug on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1639
- F1: 0.4638
- Roc Auc: 0.7141
- Accuracy: 0.7694
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.1592 | 1.0 | 89 | 0.1403 | 0.4453 | 0.6993 | 0.8029 |
| 0.1701 | 2.0 | 178 | 0.1415 | 0.4579 | 0.7051 | 0.8092 |
| 0.1534 | 3.0 | 267 | 0.1636 | 0.4201 | 0.6829 | 0.7631 |
| 0.1107 | 4.0 | 356 | 0.1639 | 0.4638 | 0.7141 | 0.7694 |
| 0.1037 | 5.0 | 445 | 0.1579 | 0.4530 | 0.7092 | 0.7736 |
| 0.077 | 6.0 | 534 | 0.1597 | 0.4535 | 0.7183 | 0.7883 |
| 0.0655 | 7.0 | 623 | 0.1730 | 0.4581 | 0.7090 | 0.7820 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0