afro-xlmr-base-sun-finetuned-augmentation-LUNAR-sun-MICRO
This model is a fine-tuned version of sercetexam9/afro-xlmr-base-sun-finetuned-augmentation-LUNAR on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2646
- F1: 0.8086
- Roc Auc: 0.8631
- Accuracy: 0.6707
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 |
|---|---|---|---|---|---|---|
| 0.1462 | 1.0 | 526 | 0.2223 | 0.8049 | 0.8625 | 0.6488 |
| 0.1051 | 2.0 | 1052 | 0.2646 | 0.8086 | 0.8631 | 0.6707 |
| 0.051 | 3.0 | 1578 | 0.3375 | 0.7961 | 0.8642 | 0.6341 |
| 0.0376 | 4.0 | 2104 | 0.3652 | 0.7854 | 0.8506 | 0.6098 |
| 0.0199 | 5.0 | 2630 | 0.4148 | 0.7847 | 0.8626 | 0.5829 |
| 0.0108 | 6.0 | 3156 | 0.4401 | 0.7917 | 0.8588 | 0.6268 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0