xlm-roberta-base-finetuned-deduplicate_PersianQuAD
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8350
- {'exact_match': 82.3470411233701, 'f1': 84.88648626287544}
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1195 | 1.0 | 1456 | 0.8632 |
| 0.7203 | 2.0 | 2912 | 0.7668 |
| 0.5723 | 3.0 | 4368 | 0.8350 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Downloads last month
- 8
Model tree for Z-Jafari/xlm-roberta-base-finetuned-deduplicate_PersianQuAD
Base model
FacebookAI/xlm-roberta-base