xlm-roberta-base-hin-finetuned
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1533
- F1: 0.7972
- Roc Auc: 0.8712
- Accuracy: 0.77
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.4175 | 1.0 | 109 | 0.3690 | 0.0 | 0.5 | 0.31 |
| 0.3344 | 2.0 | 218 | 0.2807 | 0.1111 | 0.5445 | 0.37 |
| 0.21 | 3.0 | 327 | 0.2053 | 0.6797 | 0.8067 | 0.68 |
| 0.163 | 4.0 | 436 | 0.1533 | 0.7972 | 0.8712 | 0.77 |
| 0.1295 | 5.0 | 545 | 0.1884 | 0.7004 | 0.8255 | 0.69 |
| 0.1125 | 6.0 | 654 | 0.1590 | 0.7621 | 0.8558 | 0.75 |
| 0.0841 | 7.0 | 763 | 0.1770 | 0.7533 | 0.8653 | 0.73 |
| 0.0678 | 8.0 | 872 | 0.1517 | 0.7867 | 0.8813 | 0.75 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0