afro-xlmr-base-finetuned-augmentation-som-finetuned-augmentation-LUNAR
This model is a fine-tuned version of sercetexam9/afro-xlmr-base-finetuned-augmentation on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1727
- F1: 0.6955
- Roc Auc: 0.8146
- Accuracy: 0.7259
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 |
|---|---|---|---|---|---|---|
| 0.1196 | 1.0 | 283 | 0.1727 | 0.6955 | 0.8146 | 0.7259 |
| 0.0993 | 2.0 | 566 | 0.1939 | 0.6648 | 0.7966 | 0.7020 |
| 0.0668 | 3.0 | 849 | 0.2148 | 0.5940 | 0.7559 | 0.6950 |
| 0.06 | 4.0 | 1132 | 0.2150 | 0.6546 | 0.8040 | 0.7029 |
| 0.0585 | 5.0 | 1415 | 0.2285 | 0.6314 | 0.7770 | 0.7003 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0