afro-xlmr-base-finetuned-augmentation-swe-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: 0.1851
- F1: 0.5211
- Roc Auc: 0.7451
- Accuracy: 0.7243
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 |
|---|---|---|---|---|---|---|
| 0.2442 | 1.0 | 129 | 0.2068 | 0.4118 | 0.6719 | 0.6777 |
| 0.1976 | 2.0 | 258 | 0.1842 | 0.5100 | 0.7403 | 0.7107 |
| 0.1771 | 3.0 | 387 | 0.1754 | 0.5210 | 0.7450 | 0.7165 |
| 0.1568 | 4.0 | 516 | 0.1851 | 0.5211 | 0.7451 | 0.7243 |
| 0.1379 | 5.0 | 645 | 0.1897 | 0.5026 | 0.7287 | 0.7146 |
| 0.1202 | 6.0 | 774 | 0.1943 | 0.5148 | 0.7437 | 0.6951 |
| 0.0769 | 7.0 | 903 | 0.2036 | 0.5009 | 0.7262 | 0.7010 |
| 0.0685 | 8.0 | 1032 | 0.1903 | 0.5141 | 0.7372 | 0.7107 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0