cs221-afro-xlmr-large-29L-tir-finetuned-10-epochs
This model is a fine-tuned version of Davlan/afro-xlmr-large-29L on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3206
- F1: 0.6034
- Roc Auc: 0.7523
- Accuracy: 0.5285
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.3815 | 1.0 | 93 | 0.3525 | 0.2663 | 0.5759 | 0.3370 |
| 0.3246 | 2.0 | 186 | 0.3119 | 0.4880 | 0.6717 | 0.4484 |
| 0.2668 | 3.0 | 279 | 0.2831 | 0.5591 | 0.7152 | 0.5122 |
| 0.2333 | 4.0 | 372 | 0.2945 | 0.5655 | 0.7190 | 0.5340 |
| 0.1909 | 5.0 | 465 | 0.3088 | 0.5726 | 0.7342 | 0.5217 |
| 0.1501 | 6.0 | 558 | 0.3016 | 0.5866 | 0.7381 | 0.5163 |
| 0.1336 | 7.0 | 651 | 0.3136 | 0.5981 | 0.7521 | 0.5163 |
| 0.0933 | 8.0 | 744 | 0.3206 | 0.6034 | 0.7523 | 0.5285 |
| 0.088 | 9.0 | 837 | 0.3239 | 0.5968 | 0.7509 | 0.5149 |
| 0.0905 | 10.0 | 930 | 0.3246 | 0.5963 | 0.7507 | 0.5163 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0