cs221-afro-xlmr-large-76L-hau-finetuned-10-epochs
This model is a fine-tuned version of Davlan/afro-xlmr-large-76L on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2415
- F1: 0.7285
- Roc Auc: 0.8197
- Accuracy: 0.5618
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.491 | 1.0 | 54 | 0.4615 | 0.0 | 0.5 | 0.1538 |
| 0.4482 | 2.0 | 108 | 0.3915 | 0.2562 | 0.5720 | 0.2354 |
| 0.3407 | 3.0 | 162 | 0.2965 | 0.6125 | 0.7398 | 0.4476 |
| 0.288 | 4.0 | 216 | 0.2779 | 0.6596 | 0.7747 | 0.4918 |
| 0.2309 | 5.0 | 270 | 0.2545 | 0.704 | 0.8037 | 0.5501 |
| 0.1891 | 6.0 | 324 | 0.2415 | 0.7285 | 0.8197 | 0.5618 |
| 0.1647 | 7.0 | 378 | 0.2543 | 0.7162 | 0.8167 | 0.5571 |
| 0.1397 | 8.0 | 432 | 0.2452 | 0.72 | 0.8185 | 0.5571 |
| 0.1309 | 9.0 | 486 | 0.2499 | 0.7138 | 0.8160 | 0.5571 |
| 0.12 | 10.0 | 540 | 0.2502 | 0.7148 | 0.8156 | 0.5594 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0