afro-xlmr-base-ary-finetuned-augmentation-LUNAR-ary-MICRO
This model is a fine-tuned version of sercetexam9/afro-xlmr-base-ary-finetuned-augmentation-LUNAR on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1392
- F1: 0.7574
- Roc Auc: 0.8609
- Accuracy: 0.7505
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: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.1752 | 1.0 | 135 | 0.1524 | 0.7129 | 0.8343 | 0.6983 |
| 0.1647 | 2.0 | 270 | 0.1392 | 0.7574 | 0.8609 | 0.7505 |
| 0.1311 | 3.0 | 405 | 0.1426 | 0.7350 | 0.8376 | 0.7449 |
| 0.1001 | 4.0 | 540 | 0.1483 | 0.7014 | 0.7945 | 0.7207 |
| 0.0774 | 5.0 | 675 | 0.1606 | 0.7308 | 0.8394 | 0.7281 |
| 0.073 | 6.0 | 810 | 0.1745 | 0.7141 | 0.8344 | 0.7095 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0