afro-xlmr-base-amh-finetuned-augmentation-LUNAR-finetuned-augmentation
This model is a fine-tuned version of sercetexam9/afro-xlmr-base-amh-finetuned-augmentation-LUNAR on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0967
- F1: 0.9110
- Roc Auc: 0.9443
- Accuracy: 0.8865
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 |
|---|---|---|---|---|---|---|
| 0.0948 | 1.0 | 208 | 0.0875 | 0.9093 | 0.9482 | 0.8877 |
| 0.077 | 2.0 | 416 | 0.0868 | 0.9102 | 0.9421 | 0.8937 |
| 0.065 | 3.0 | 624 | 0.1004 | 0.9065 | 0.9459 | 0.8720 |
| 0.0517 | 4.0 | 832 | 0.1088 | 0.9046 | 0.9457 | 0.8659 |
| 0.0315 | 5.0 | 1040 | 0.0967 | 0.9110 | 0.9443 | 0.8865 |
| 0.0281 | 6.0 | 1248 | 0.1232 | 0.8957 | 0.9399 | 0.8635 |
| 0.0306 | 7.0 | 1456 | 0.1138 | 0.9050 | 0.9409 | 0.8623 |
| 0.0243 | 8.0 | 1664 | 0.1041 | 0.9090 | 0.9403 | 0.8816 |
| 0.0136 | 9.0 | 1872 | 0.1146 | 0.8981 | 0.9432 | 0.8804 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0